Communication method and apparatus

Abstract

A communication method and an apparatus. The method comprises: obtaining parameter information of a first task; determining a first topological relationship graph on the basis of the parameter information of the first task, wherein the first topological relationship graph indicates a connection relationship between at least two intelligent devices, the first topological relationship graph is a directed acyclic graph, the connection relationship at least comprises a source node intelligent device and an adjacent vertex intelligent device of the source node intelligent device, and the at least two intelligent devices include the source node intelligent device and the adjacent vertex intelligent device. By means of the method, the first topological relationship graph is established for the first task on the basis of the parameter information of the first task, and the at least two intelligent devices comprised in the first topological relationship graph can assist in executing the first task. Because the first topological relationship graph is a directed acyclic graph, in the process of multiple intelligent devices cooperating to execute the first task, conflicts caused by the intelligent devices requesting assistance from each other for the same task can be avoided, thereby improving task execution efficiency.

Description

A communication method and apparatus

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510188676.6, filed on February 19, 2025, entitled "A Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0004] Artificial intelligence (AI) agents, also known simply as intelligent agents, possess core capabilities in autonomous decision-making, tool invocation, and interaction with the external environment. With the rapid development of AI technologies such as big data and deep learning, especially the emergence of large language models, intelligent agents can handle complex tasks, understand and generate natural language, and make efficient decisions by invoking these models, demonstrating enormous potential in various applications. Simultaneously, multi-agent technology has emerged, where multiple intelligent agents with different responsibilities and capabilities collaborate to complete complex tasks. Combining multi-agent technology with mobile networks not only enhances the network's intelligence level but also strengthens its adaptability and performance in the face of large-scale data flows and complex dynamic environments.

[0005] When multiple agents collaborate to execute the same task, conflicts or competition may arise among them, or they may get caught in a loop of information exchange, affecting task execution and reducing efficiency. Therefore, how to improve the efficiency of multiple agents collaborating to execute the same task is an urgent problem to be solved. Summary of the Invention

[0006] This application provides a communication method and apparatus to improve the efficiency of multiple smart devices cooperating in performing the same task.

[0007] Firstly, this application provides a communication method, wherein the executing entity of the method is a proxy management device or a module or chip within the proxy management device; the method is described here using the proxy management device as an example. The method includes: obtaining parameter information of a first task; and determining a first topology graph based on the parameter information of the first task. The first topology graph indicates the connection relationship between at least two intelligent devices. The first topology graph is a directed acyclic graph, and the connection relationship includes at least a source node intelligent device and adjacent vertex intelligent devices of the source node intelligent device. The at least two intelligent devices include the source node intelligent device and the adjacent vertex intelligent devices.

[0008] This method establishes a first topological relationship graph for the first task based on the parameter information of the first task. The first topological relationship graph includes at least two intelligent devices that can assist in executing the first task. Since the first topological relationship graph is a directed acyclic graph, this allows for clear calling relationships between intelligent devices during the collaborative execution of the first task. This avoids conflicts and ineffective information exchange caused by intelligent devices requesting assistance from each other for the same task, thereby improving the execution efficiency of the task.

[0009] In one possible implementation, the parameter information includes at least one of the following: the capability requirements of the first task;

[0010] The latency requirements of the first task; the Quality of Service (QoS) requirements of the first task; or, the data provider of the first task.

[0011] In one possible implementation, determining the first topological relationship graph based on the parameter information of the first task includes:

[0012] Based on the parameter information of the first task, determine the at least two smart devices in the first topology graph and the connection relationship of the at least two smart devices in the first topology graph.

[0013] In one possible implementation, determining the first topological relationship graph based on the parameter information of the first task includes:

[0014] Based on the parameter information of the first task, determine the at least two smart devices in the first topology graph;

[0015] The connection relationship of the at least two smart devices in the first topology graph is determined based on the capability information or status information of the at least two smart devices.

[0016] In one possible implementation, the parameter information includes the capability requirements of the first task, and the sum of the capabilities of the at least two smart devices satisfies the capability requirements of the first task.

[0017] This method ensures that the capabilities of the intelligent devices in the first topological relationship graph meet the requirements for performing the first task, thereby improving the success rate of performing the first task.

[0018] In one possible implementation, the parameter information includes the QoS requirements of the first task; the services provided by the at least two smart devices are able to meet the QoS requirements.

[0019] This method ensures that the services provided by the intelligent devices in the first topology graph meet the QoS requirements of the first task, thereby improving the service quality of the first task.

[0020] In one possible implementation, the parameter information includes the latency requirement of the first task; the latency between the at least two smart devices can meet the latency requirement.

[0021] This method ensures that the latency between intelligent devices in the first topology graph meets the latency requirements of the first task, thereby improving the service quality of the first task.

[0022] In one possible implementation, the method further includes: sending first information to the source node intelligent device, the first information instructing the source node intelligent device to perform the first task, and instructing the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; both the source node intelligent device and the adjacent vertex intelligent devices are included in the first topology graph.

[0023] In one possible implementation, the method further includes: sending second information to the source node intelligent device according to the first topology graph, the second information indicating that the source node intelligent device is a source node in the first topology graph, and indicating that a first intelligent device is an adjacent vertex intelligent device of the source node intelligent device in the first topology graph.

[0024] In one possible implementation, the second information is further used to indicate a first capability used to authorize the source node smart device to perform the first task, wherein the first capability is part or all of the capabilities of the source node smart device.

[0025] In one possible implementation, the method further includes: sending third information to a second intelligent device according to the first topology graph; wherein the third information indicates that the predecessor vertex intelligent device of the second intelligent device is a third intelligent device, the first topology graph also includes the second intelligent device and the third intelligent device, and the second intelligent device is an adjacent vertex intelligent device of the third intelligent device in the first topology graph.

[0026] This method enables the second intelligent device to determine its topological relationship in the first topological relationship graph, and enables the second intelligent device to identify intelligent devices that can request assistance when performing a task.

[0027] In one possible implementation, the method further includes: receiving fourth information, the fourth information indicating that the condition for stopping the execution of the first task has been met; sending fifth information to the source node intelligent device according to the fourth information, the fifth information indicating that the execution of the first task has been stopped; receiving the execution result of the first task from the source node intelligent device, the execution result indicating at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

[0028] In one possible implementation, before receiving the fourth information, the method further includes sending a sixth information to the source node smart device, the sixth information indicating the conditions for stopping the execution of the first task.

[0029] In one possible implementation, the method further includes: receiving collaborative execution information of the first task; if the condition for stopping the execution of the first task is met according to the collaborative execution information, then sending fifth information to the source node intelligent device, the fifth information indicating stopping the execution of the first task; receiving the execution result of the first task from the source node intelligent device, the execution result indicating at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

[0030] In one possible implementation, the method further includes: sending first deregistration information to the source node smart device, the first deregistration information being used to instruct the deregistration of the source node smart device in the first topology graph.

[0031] Secondly, this application provides a communication method, wherein the executing entity of the method is a source node intelligent device or a module or chip within the source node intelligent device; the method is described here using the source node intelligent device as the executing entity as an example. The method includes: receiving first information from a proxy management device, the first information instructing the source node intelligent device to perform a first task and instructing adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; both the source node intelligent device and the adjacent vertex intelligent devices are included in a first topology graph, the first task is associated with the first topology graph, the first topology graph indicates the connection relationship of at least two intelligent devices, the first topology graph is a directed acyclic graph, and the connection relationship includes at least the source node intelligent device and the adjacent vertex intelligent devices of the source node intelligent device; executing the first task according to the first information, and sending first indication information to the adjacent vertex intelligent devices, the first indication information instructing the adjacent vertex intelligent devices to assist in performing the first task.

[0032] In one possible implementation, the method further includes: receiving second information from the agent management device, the second information indicating that the source node smart device is a source node in the first topology graph, and indicating that the first smart device is an adjacent vertex smart device of the source node smart device in the first topology graph.

[0033] In one possible implementation, the second information is further used to indicate a first capability used to authorize the source node smart device to perform the first task, wherein the first capability is part or all of the capabilities of the source node smart device.

[0034] In one possible implementation, the method further includes: performing the first task based on the first capability.

[0035] In one possible implementation, the method further includes: receiving fifth information from the agent management device, the fifth information indicating to stop executing the first task; sending the execution result of the first task to the agent management device, the execution result indicating at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

[0036] In one possible implementation, the method further includes: receiving sixth information from the agent management device, the sixth information indicating conditions for stopping the execution of the first task.

[0037] In one possible implementation, before receiving the fifth information from the agent management device, the method further includes: sending a fourth message to the agent management device, the fourth message indicating that the condition for stopping the execution of the first task has been met; or, sending collaborative execution information of the first task to the agent management device, the collaborative execution information being used to determine whether the condition for stopping the execution of the first task has been met.

[0038] Thirdly, this application provides a communication method, wherein the executing entity of the method is a proxy management device or a module or chip within the proxy management device, and the method is described here using the proxy management device as an example. The method includes: determining a first topology graph corresponding to a first task; the first topology graph indicating the connection relationship between at least two intelligent devices, the at least two intelligent devices including a source node intelligent device and an adjacent vertex intelligent device of the source node intelligent device in the first topology graph; and, according to the first topology graph, sending first information to the source node intelligent device, the first information instructing the source node intelligent device to execute the first task and instructing the adjacent vertex intelligent device to assist in executing the first task.

[0039] Using the method provided in this application, after establishing a first topology graph for the first task, the agent management device can indicate to the source node intelligent device in the first topology graph the adjacent vertex intelligent devices, and indicate to the source node intelligent device that it can assist in executing the first task through the assistance of the adjacent vertex intelligent devices. This enables multiple intelligent devices to assist in executing the first task, ensuring that the first task can be completed. Since the agent management device instructs the source node intelligent device to request the assistance of the adjacent vertex intelligent devices in executing the first task, there is a clear calling relationship between the intelligent devices during the collaborative execution of the first task. This avoids conflicts and ineffective information exchange caused by intelligent devices requesting assistance from each other for the same task, thereby improving the execution efficiency of the task.

[0040] In one possible implementation, the method further includes: sending second information to the source node intelligent device according to the first topology graph, the second information indicating that the source node intelligent device is the source node of the first topology graph, and indicating that the first intelligent device is the adjacent vertex intelligent device of the source node intelligent device.

[0041] In one possible implementation, the second information is further used to indicate a first capability used to authorize the source node smart device to perform the first task, wherein the first capability is part or all of the capabilities of the source node smart device.

[0042] In one possible implementation, the method further includes: sending third information to a second intelligent device according to the first topology graph; wherein the third information indicates that the predecessor vertex intelligent device of the second intelligent device is a third intelligent device, the first topology graph also includes the second intelligent device and the third intelligent device, and the second intelligent device is an adjacent vertex intelligent device of the third intelligent device in the first topology graph.

[0043] In one possible implementation, the method further includes: receiving fourth information, the fourth information indicating that the condition for stopping the execution of the first task has been met; sending fifth information to the source node intelligent device according to the fourth information, the fifth information indicating that the execution of the first task has been stopped; receiving the execution result of the first task from the source node intelligent device, the execution result indicating at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

[0044] In one possible implementation, before receiving the fourth information, the method further includes sending a sixth information to the source node smart device, the sixth information indicating the conditions for stopping the execution of the first task.

[0045] In one possible implementation, the method further includes: receiving collaborative execution information of the first task; if the condition for stopping the execution of the first task is met according to the collaborative execution information, then sending fifth information to the source node intelligent device, the fifth information indicating stopping the execution of the first task; receiving the execution result of the first task from the source node intelligent device, the execution result indicating at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

[0046] In one possible implementation, the method further includes: sending first deregistration information to the source node smart device, the first deregistration information being used to instruct the deregistration of the source node smart device in the first topology graph.

[0047] Fourthly, this application also provides a communication device capable of implementing any of the methods provided in any of the first to second aspects described above. This communication device can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the aforementioned functions.

[0048] In one possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions of the agent management device or source node intelligent device in the methods described above. The communication device may also include a memory coupled to the processor, which stores necessary program instructions and data for the communication device. Optionally, the communication device further includes interface circuitry for supporting communication between the communication device and devices such as terminal devices.

[0049] In one possible implementation, the communication device includes corresponding functional modules, each used to implement the steps in the above method. The functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

[0050] In one possible implementation, the communication device includes a processing unit and a communication unit, which can perform the corresponding functions in the above method examples, as described in the methods provided in any of the first or second aspects, and will not be repeated here.

[0051] Fifthly, a communication device is provided, including a processor and an interface circuit. The interface circuit is used to receive signals from other communication devices outside the communication device and transmit them to the processor, or to send signals from the processor to other communication devices outside the communication device. The processor implements the functional modules of the methods in any possible implementation of any of the first to second aspects through logic circuits or by executing computer programs or instructions. Optionally, the communication device further includes a memory for storing computer programs or instructions.

[0052] In a sixth aspect, a computer program product storing instructions is provided, which, when read and executed by a computer, implements the method in any possible implementation of any of the first to second aspects described above.

[0053] In a seventh aspect, a circuit is provided for performing the methods in any possible implementation of any of the first to second aspects described above. The circuit may include chip circuitry. Optionally, the circuit may also be coupled to a memory.

[0054] Eighthly, a chip is provided, comprising a processor, which, when executing a computer program or instructions, implements the methods in any possible implementation of any of the first to second aspects described above. Optionally, the chip may further include a memory, and the chip may be composed of chips or may include chips and other discrete devices.

[0055] A ninth aspect provides a communication device including a processor that implements the method in any possible implementation of any of the first to second aspects by means of logic circuits or by executing computer programs or instructions.

[0056] In a tenth aspect, a communication apparatus is provided, comprising a unit or module for performing a method in any possible implementation of any of the first to second aspects described above.

[0057] Eleventhly, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed by a processor, implement the method in any possible implementation of any of the first to second aspects.

[0058] In a twelfth aspect, embodiments of this application also provide a communication system. The communication system includes: a proxy management device for implementing the methods of the first aspect and any possible implementations thereof; a source node intelligent device for implementing the methods of the second aspect and any possible implementations thereof; or, the communication system includes: a proxy management device for implementing the methods of the third aspect and any possible implementations thereof; and a source node intelligent device for implementing the methods of the second aspect and any possible implementations thereof. Attached Figure Description

[0059] Figure 1 is a schematic diagram of a network architecture;

[0060] Figure 2 is a schematic diagram of a topology diagram provided in an embodiment of this application;

[0061] Figure 3 is a schematic diagram of a topological relationship provided in an embodiment of this application;

[0062] Figure 4 is a schematic flowchart of a communication method provided in an embodiment of this application;

[0063] Figure 5 is a schematic flowchart of a communication method provided in an embodiment of this application;

[0064] Figure 6 is a schematic flowchart of a communication method provided in an embodiment of this application;

[0065] Figure 7 is a schematic flowchart of a communication method provided in an embodiment of this application;

[0066] Figure 8 is a schematic flowchart of a communication method provided in an embodiment of this application;

[0067] Figure 9 is a schematic diagram of a communication device structure provided in an embodiment of this application;

[0068] Figure 10 is a schematic diagram of a communication device structure provided in an embodiment of this application;

[0069] Figure 11 is a schematic diagram of a communication device structure provided in an embodiment of this application. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. The terms "first," "second," and corresponding terminology in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be interchanged where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or device that comprises a series of units is not necessarily limited to those units, but may include other units not explicitly listed or inherent to these processes, methods, products, or devices. The methods and apparatus provided in the embodiments of this application are based on the same or similar technical concepts. Since the principles by which the methods and apparatus solve problems are similar, the implementations of the apparatus and methods can refer to each other, and repeated details will not be repeated.

[0071] The method provided in this application can be applied to various mobile communication systems, such as the Internet of Things (IoT), narrowband Internet of Things (NB-IoT), fourth-generation (4G) communication systems (e.g., Long Term Evolution (LTE)), fifth-generation (5G) communication systems (e.g., 5G New Radio (NR)), LTE and NR hybrid architectures, or new communication systems emerging in future communication developments. The communication system can also include machine-to-machine (M2M) networks, machine-type communication (MTC) networks, or other networks.

[0072] The following section will first explain some of the terms used in the embodiments of this application so that those skilled in the art can understand them.

[0073] In this embodiment, the network device can be a device in a wireless network, and can also be referred to as a network apparatus, a radio access network device, or an access network device. For example, the network device can be a radio access network (RAN) node that connects a terminal device to a wireless network, and can also be referred to as an access network device. The network device includes, but is not limited to: base station, evolved NodeB (eNodeB), transmission reception point (TRP), next-generation NodeB (gNB) in a 5th generation (5G) mobile communication system, access network device in an open radio access network (O-RAN), base station in a future mobile communication system, or access node in a wireless fidelity (WiFi) system; or it can be a module or unit that performs some functions of a base station, such as a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP) module, or a central unit user plane (CU-UP) module. Access network equipment can be macro base stations, micro base stations, indoor stations, relay nodes, or donor nodes, etc. This application does not limit the specific technologies or equipment forms used in the network equipment.

[0074] In some implementations, network devices can include centralized units (CUs) and distributed units (DUs). This includes RAN devices at CU and DU nodes that separate the protocol layers of the gNB in ​​the NR system. Some protocol layer functions are centrally controlled by the CU, while the remaining partial or complete protocol layer functions are distributed across the DUs, which are then centrally controlled by the CU. Furthermore, the CU can be divided into a control plane (CU-CP) and a user plane (CU-UP). The CU-CP handles control plane functions, primarily including radio resource control (RRC) and the corresponding packet data convergence protocol (PDCP) (PDCP-C). PDCP-C is mainly responsible for control plane data encryption / decryption, integrity protection, and data transmission. The CU-UP handles user plane functions, primarily including the service data adaptation protocol (SDAP) and the corresponding PDCP (PDCP-U). SDAP is mainly responsible for processing core network data and mapping flows to bearers. PDCP-U is primarily responsible for data plane encryption / decryption, integrity protection, header compression, sequence number maintenance, and data transmission. CU-CP and CU-UP are connected via the E1 interface. CU-CP represents the gNB connected to the core network via the NG interface and to the DU via the F1 interface control plane (F1-C). CU-UP is connected to the DU via the F1 interface user plane (F1-U). Alternatively, PDCP-C may also be located within CU-UP.

[0075] It is understood that CU (including CU-CP or CU-UP) or DU may have different names in different systems, but those skilled in the art will understand their meaning. For example, in an open radio access network (O-RAN) 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, and CU-UP can also be called O-CU-UP. For ease of description, this application uses CU, CU-CP, CU-UP, and DU as examples. Network devices may also include active antenna units (AAU). CU implements some of the functions of gNB, and DU implements some of the functions of gNB. For example, CU is responsible for handling non-real-time protocols and services, implementing the functions of the RRC layer. DU is responsible for handling physical layer protocols and real-time services, implementing the functions of the radio link control (RLC) layer, media / medium access control (MAC) layer, and physical (PHY) layer. In some deployments, the CU can also be divided into a centralized unit control plane (CU-CP) node and a centralized unit user plane (CU-UP) node. The CU-CP is responsible for control plane functions, while the CU-UP is responsible for user plane functions.

[0076] The terminal device involved in this application embodiment can be a wireless terminal device capable of receiving network device scheduling and instruction information. The terminal device can be referred to as a terminal device, user equipment (UE), terminal, mobile station (MS), mobile terminal (MT), etc. The terminal device can also be a chip or system-on-a-chip, which is built into the aforementioned user equipment (UE), terminal, mobile station (MS), or mobile terminal (MT). The terminal device can be a device including wireless communication functions (providing voice / data connectivity to the user). For example, a handheld device with wireless connectivity, or an in-vehicle device, in-vehicle module, etc. Currently, examples of terminal devices include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in vehicle-to-everything (V2X) communication, wireless terminals in vehicle-to-everything (V2X) communication, intelligent vehicles, in-vehicle infotainment systems (or onboard transmitters) (T-boxes), machine-to-machine / machine-type communications (M2M / MTC) terminal devices, and the Internet of Things (IoT). of things, IoT (Internet of Things) terminal devices, etc.For example, terminal devices can be in-vehicle equipment, vehicle-mounted equipment, in-vehicle modules, vehicles, on-board units (OBU), roadside units (RSU), T-boxes, chips, or systems-on-chips (SOCs), which can be installed in vehicles, OBUs, RSUs, or T-boxes. Wireless terminals in industrial control can be cameras, robots, etc. Wireless terminals in smart homes can be televisions, air conditioners, robot vacuums, speakers, set-top boxes, etc. Terminal devices can also be V2X devices, such as smart cars, digital cars, unmanned cars, driverless cars, pilotless cars, autonomous cars, pure electric vehicles (EVs), hybrid electric vehicles (HEVs), range-extended electric vehicles (REEVs), plug-in hybrid electric vehicles (PHEVs), new energy vehicles, and roadside units (RSUs). Terminal devices can also be devices in device-to-device (D2D) communication, such as electricity meters and water meters. Furthermore, in this embodiment, the terminal device can also be a terminal device in an IoT system. IoT is an important component of future information technology development, and its main technical characteristic is connecting objects to networks through communication technologies, thereby realizing an intelligent network of human-machine interconnection and machine-to-machine interconnection.

[0077] An intelligent agent, also known as an intelligent device, intelligent agent device, artificial intelligence agent, or artificial intelligence agent device, etc., refers to a device or software based on artificial intelligence technology in this application, capable of autonomous decision-making, tool invocation, and interaction with the external environment or devices. An intelligent agent can be an independent device; it can be deployed on the terminal device side, the radio access network side, or the core network side. For example, an intelligent agent can be a module or chip in a terminal device, or an application deployed in the terminal device. As another example, an intelligent agent can be a module or chip on the radio access network side (e.g., a base station), or an application deployed on the radio access network side.

[0078] Figure 1 illustrates a network architecture applicable to an embodiment of this application. In the network architecture of Figure 1, network-side functions and services can be implemented through intelligent agents. These agents can connect and interact through standardized interfaces and protocols, and there can be calling relationships between them. For example, the wireless access network side may include cloud service orchestration network (CSON) agents, fault management control agents, data collection agents, and other intelligent agents.

[0079] Among them, the CSON agent can orchestrate cloud-based services on the radio access network side; the fault management and control agent can manage and control faults on the radio access network side; and the data collection agent can collect various data from the radio access network side. The above are just examples; the radio access network side can also include other agents, which will not be listed here.

[0080] On the core network side, it can include intelligent agents with capabilities such as accelerated computing and cloud load-balancing (ACCL), configuration management control, and performance management control.

[0081] The above are just examples. The core network side can also include other intelligent agents, which will not be listed one by one here.

[0082] The network shown in Figure 1 may also include agent management devices. Agent management devices can be deployed within the network operation and maintenance system. These devices can dynamically create and manage the topology graph. The topology graph indicates the connection relationships between multiple intelligent devices; it is a directed acyclic graph and may include a source node (also referred to as the source node intelligent device).

[0083] In this application, there is a unidirectional directed edge between two adjacent smart devices in the topology graph. The direction of the directed edge is from the tail end of the directed edge to the head end of the directed edge. The smart device corresponding to the tail end of the directed edge is the predecessor vertex smart device of the two smart devices, and the smart device corresponding to the head end of the directed edge is the adjacent vertex smart device of the two smart devices.

[0084] For example, as shown in Figure 2, the topology graph includes four intelligent devices: Z, X, Y1, Y2, and Y3. Z is the source node intelligent device. A directed edge connects Z and X, with Z at the tail and X at the head. Z is the predecessor of X, and X is its adjacent vertex intelligent device. Similarly, a directed edge connects X and Y1, with X at the tail and Y1 at the head. X is the predecessor of Y1, and Y1 is its adjacent vertex intelligent device. A directed edge connects X and Y2, with X being the predecessor of Y2 and Y2 being its adjacent vertex intelligent device. Finally, a directed edge connects X and Y3, with X being the predecessor of Y3 and Y3 being its adjacent vertex intelligent device.

[0085] In the topology graph, the out-degree of a smart device can refer to the number of directed edges originating from that smart device (or starting point); the in-degree of a smart device can refer to the number of directed edges originating from that smart device (or ending point). A smart device with an in-degree of 0 can also be called a source node or source smart device; a smart device with an out-degree of 0 can also be called a sink node or sink smart device. For example, taking the topology graph in Figure 2 as an example, Z has an out-degree of 1 and an in-degree of 0, so Z is a source smart device; X has an out-degree of 3 and an in-degree of 1; Y1 has an out-degree of 0 and an in-degree of 1, so Y1 is a sink smart device. Y2 and Y3 are also sink smart devices.

[0086] If a path in a topological graph starts from a smart device, goes through a loop, and then returns to the same smart device, then the topological graph contains a "cycle". The topological graph shown in Figure 2 is a directed acyclic graph, so it does not contain cycles. For example, if there is an edge pointing from Y1 to Z between Y1 and Z in Figure 2 (see Figure 3 for details), then the topological graph contains a cycle from Z to X, then from X to Y1, and then from Y1 to Z.

[0087] This application provides a method that enables multiple agents to collaborate in performing the same task, thereby avoiding goal conflicts or competition among the agents during task execution and improving the efficiency of task execution.

[0088] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0089] It is understood that this application does not specifically limit the structure of the execution entity of the method provided in the embodiments of this application. It can be applied to smart devices or modules in smart devices, as long as it can communicate according to the method provided in the embodiments of this application by running a program that records the code of the method provided in the embodiments of this application. The following description takes the interaction between the agent management device and the source node smart device as an example. The source node smart device can be deployed on the wireless access network side or on the core network side. The source node smart device can also be a terminal device or a module or application in a terminal device. This application does not limit it in this respect.

[0090] Figure 4 shows a flowchart of a communication method provided in an embodiment of this application. The method includes:

[0091] Step 401: The agent management device obtains the parameter information for the first task.

[0092] This application does not limit how the agent management device obtains the parameter information of the first task. For example, the agent management device receives task description information from a third-party device, which includes the parameter information of the first task. The third-party device can be a smart device or other types of devices; this application does not limit this.

[0093] A third-party device can be the initiator of the first task and can execute the first task. Alternatively, the third-party device may not execute the task but only need to obtain the result of the first task.

[0094] In this application, the specific content of the first task is not limited. For example, the first task can refer to a functional operation that the intelligent agent device needs to perform. For instance, if the first task is an AI model training task, then the AI ​​model specified in the first task can be trained. For instance, if the first task is a network fault detection task, then fault detection can be performed on the network specified in the first task. For instance, if the first task is a large language model deployment task, then the large language model can be deployed on the device specified in the first task. For instance, if the first task is a route optimization task, then route optimization can be performed on the network specified in the first task.

[0095] In this application, the specific content of the parameter information for the first task is not limited. For example, the parameter information includes at least one of the following:

[0096] The capability requirements of the first task include, for example, at least one of the following: computing power and bandwidth.

[0097] The latency requirements of the first task;

[0098] The Quality of Service (QoS) requirements of the first task; or,

[0099] The data (or input parameters) provider for the first task; wherein, if a device is a data provider, then the first topology diagram may include that device; if a device is not a data provider, then the first topology diagram may not include that device.

[0100] Optionally, the task description information may also include at least one of the following: an identifier for the first task; data feedback requirements for the first task; the data feedback requirements for the first task may indicate the output parameters of the first task, the data format of the output parameters, etc.

[0101] The task description information can also indicate the input parameters of the first task, the data format of the input parameters, and other information.

[0102] Prior to step 401, the agent management device can send capability reporting requests to all smart devices within its coverage area, requesting each smart device to report its own capabilities. Furthermore, the agent management device can obtain capability information from multiple smart devices, with each smart device's capability information indicating at least one of the following: data transmission volume, load rate, latency, QoS capability, processing capacity, and large language model (task orchestration) capability.

[0103] Step 402: The agent management device determines the first topology diagram based on the parameter information of the first task.

[0104] The first topology graph indicates the connection relationship between at least two smart devices. The first topology graph is a directed acyclic graph. The connection relationship includes at least the source node smart device and the adjacent vertex smart devices of the source node smart device. The at least two smart devices include the source node smart device and the adjacent vertex smart devices.

[0105] The first topology diagram determined by the agent management device based on the parameter information of the first task is associated with the first task, which can be understood as the first topology diagram being applicable to the first task.

[0106] In this application, the first topological graph is a directed acyclic graph, which means that the first topological graph does not contain a cycle containing multiple directed edges. For example, taking the topological graph of Figure 3 as an example, Figure 3 includes a cycle, which includes a directed edge from Z to X, a directed edge from X to Y1, and a directed edge from Y1 to Z.

[0107] In one implementation, the agent management device determines at least two smart devices in the first topology graph and the connection relationship between the at least two smart devices in the first topology graph based on the parameter information of the first task.

[0108] For example, the parameter information includes the capability requirements of the first task. The agent management device selects at least two smart devices based on these requirements, such as selecting at least two smart devices from the aforementioned plurality of smart devices, where the sum of the capabilities of these at least two smart devices satisfies the capability requirements of the first task. If the parameter information of the first task includes the data provider of the first task, then the at least two smart devices include the data provider of the first task, and the agent management device uses this data provider as the source node smart device in the first topology graph. If the parameter information of the first task does not include the data provider of the first task, then the agent management device uses the smart device with the largest data transmission volume indicated by the capability information among the at least two smart devices as the source node smart device in the first topology graph. This can save transmission latency caused by data transmission and improve task processing efficiency.

[0109] The agent management device can arrange at least two smart devices in order of data transmission volume, and then establish connections with the source node smart device sequentially according to this arrangement, forming a first topology graph. For example, among the at least two smart devices, excluding the source node smart device, the smart device with the largest data transmission volume is designated as the adjacent vertex smart device of the source node smart device, and then the smart device with the second largest data transmission volume is designated as the adjacent vertex smart device of the source node smart device, and so on, ultimately obtaining a directed acyclic first topology graph.

[0110] In one implementation, the agent management device determines at least two smart devices in the first topology graph based on the parameter information of the first task. The agent management device then determines the connection relationship between the at least two smart devices in the first topology graph based on the capability information of the at least two smart devices.

[0111] For example, based on the capability information of at least two smart devices, the agent management device designates the smart device with the lowest load rate among the at least two smart devices as the source node smart device in the first topological graph, and the smart device with the second lowest load rate as the adjacent vertex smart device of the source node smart device, and so on, ultimately obtaining a directed acyclic first topological graph. Optionally, other capabilities of the smart devices can also be considered during the establishment of the first topological graph. For example, among multiple smart devices, the smart device whose processing capability does not support parallel execution of the same task can be designated as the source node smart device, and the smart device whose processing capability supports parallel execution of the same task can be designated as the adjacent vertex smart device of the source node smart device.

[0112] For example, based on the capability information of at least two smart devices, the agent management device selects the smart device with the strongest (task orchestration) capability in the large language model as the source node smart device of the first topological graph, and the smart device with the second strongest (task orchestration) capability in the large language model as the adjacent vertex smart device of the source node smart device. Other cases are deduced in the same way, and finally a directed acyclic first topological graph can be obtained.

[0113] The above is just an example. Agent management devices can also determine the first topology diagram using other methods, which will not be elaborated here.

[0114] It is understandable that the agent management device identifies at least two smart devices that meet the parameter information for the first task. For example, the parameter information includes the capability requirements of the first task, and the sum of the capabilities of at least two smart devices must meet the capability requirements of the first task.

[0115] For example, the parameter information includes the QoS requirements of the first task, and the services provided by at least two smart devices can meet the QoS requirements.

[0116] For example, the parameter information includes the latency requirements of the first task, and the latency between at least two smart devices can meet the latency requirements.

[0117] Step 403: The agent management device sends the first information to the source node smart device.

[0118] Correspondingly, the source node intelligent device receives the first information from the agent management device.

[0119] The first information instructs the source node intelligent device to perform the first task, and also instructs the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; both the source node intelligent device and the adjacent vertex intelligent devices are included in the first topology graph. This can be understood as the first information instructing the source node intelligent device to perform the first task, and instructing the adjacent vertex intelligent devices of the source node intelligent device in the first topology graph to assist in performing the first task.

[0120] In this application, the source node intelligent device can perform a first task based on the first information.

[0121] In one implementation, the source node intelligent device performs the first task according to a first capability, where the first capability is part or all of the capabilities of the source node intelligent device. For example, the first capability is preset, or the first capability is indicated by a proxy management device. For example, the proxy management device indicates the first capability through second information.

[0122] In this application, the agent management device can also send second information to the source node intelligent device according to the first topology diagram.

[0123] Correspondingly, the source node intelligent device receives the second information from the agent management device.

[0124] The second information indicates that the source node intelligent device is the source node in the first topology graph, and indicates that the first intelligent device is an adjacent vertex intelligent device of the source node intelligent device in the first topology graph. The first intelligent device is one of at least two intelligent devices. In this application, the number of adjacent vertex intelligent devices of the source node intelligent device can be greater than or equal to 1, and the specific number is not limited.

[0125] Optionally, the second information may also be used to instruct the first capability used by the authorized source node intelligent device to perform the first task, wherein the first capability is part or all of the capabilities of the source node intelligent device.

[0126] Optionally, the second information may also be used to instruct the first intelligent device to use a second capability to assist in performing the first task, wherein the second capability is part or all of the capabilities of the first intelligent device.

[0127] Optionally, the agent management device can also send a sixth message to the source node intelligent device, indicating the conditions for stopping the execution of the first task. This application does not limit the specific content of the conditions for stopping the execution of the first task. For example, the conditions for stopping the execution of the first task may include at least one of the following: the duration of executing the first task is greater than or equal to a first duration; the amount of resources consumed in executing the first task is greater than or equal to a first quantity. The above are merely examples; other forms of conditions for stopping the execution of the first task may also exist, which will not be elaborated upon here.

[0128] For example, based on the preceding description and taking Figure 2 as an example, the information sent by the agent management device to the source node intelligent device Z includes the content shown in Table 1.

[0129] Table 1

[0130] As shown in Table 1, the adjacent vertex intelligent device of the source node intelligent device is X, and its first authorized capability is capability 1; X is authorized to have capability 2; the conditions for stopping the execution of the first task are condition 1 and condition 2.

[0131] Optionally, the agent management device can also send a seventh message to the source node intelligent device. The seventh message indicates the reporting of the collaborative execution information of the first task. The collaborative execution information of the first task is used to determine whether the conditions for stopping the execution of the first task have been met. The collaborative execution information of the first task may include relevant information during the execution of the first task. For example, the collaborative execution information of the first task may include at least one of the following: the duration of the execution of the first task; the amount of resources consumed in the execution of the first task.

[0132] Optionally, the agent management device may also send a sixth and a seventh message to each of at least two smart devices, which is not limited in this application.

[0133] This application does not limit the conditions for stopping the execution of the first task. For example, the conditions for stopping the execution of the first task may include at least one of the following: the duration of the execution of the first task is greater than or equal to the first duration, and the amount of resources consumed in the execution of the first task is greater than or equal to the first quantity.

[0134] Optionally, the seventh information indicates the reporting conditions for collaborative execution information. The reporting conditions for collaborative execution information can be periodic reporting or triggering reporting by the agent management device through instructions; this application does not limit this.

[0135] For example, based on the preceding description and taking Figure 2 as an example, the information sent by the agent management device to the source node intelligent device Z includes the content shown in Table 2.

[0136] Table 2

[0137] In this application, the second and seventh information can be carried in the same message or in different messages, and this application does not limit this.

[0138] In this application, the agent management device can also send third information to the reachable node intelligent device according to the first topology diagram. The third information indicates the predecessor vertex intelligent device of the reachable node intelligent device in the first topology diagram. The predecessor vertex intelligent device is the source node intelligent device or one of at least one reachable node intelligent device.

[0139] The agent management device can send third information to the second intelligent device; the specific process will not be elaborated further. The second intelligent device can be any intelligent device other than the source intelligent node device among at least two intelligent devices.

[0140] Optionally, the third information also indicates that the predecessor vertex intelligent device of the second intelligent device is the third intelligent device, and the first topology graph also includes the second intelligent device and the third intelligent device, wherein the second intelligent device is the adjacent vertex intelligent device of the third intelligent device in the first topology graph.

[0141] Optionally, the third information may also indicate the adjacent vertex intelligent devices of the second intelligent device in the first topology graph. It should be noted that if the second intelligent device has no adjacent vertex intelligent devices in the first topology graph, the third information may not indicate such adjacent vertex intelligent devices.

[0142] Step 404: The source node intelligent device sends the first instruction information to the adjacent vertex intelligent devices of the source node intelligent device according to the first information.

[0143] The first instruction information directs the adjacent vertex intelligent devices to assist in executing the first task. In this way, the source node intelligent device requests the assistance of adjacent vertex intelligent devices to ensure the completion of the first task and improve task execution efficiency.

[0144] Optionally, the agent management device can also send a first deregistration message to the source node intelligent device. The first deregistration message is used to instruct the source node intelligent device to deregister in the first topology. The source node intelligent device can delete information such as its adjacency relationship with the first intelligent device in the first topology relationship graph based on the first deregistration message; the specific process will not be elaborated further.

[0145] Using the method provided in this application, the agent management device establishes a first topology graph for the first task based on the parameter information of the first task. The first topology graph includes at least two intelligent devices that can assist in executing the first task. Since the first topology graph is a directed acyclic graph, this allows multiple intelligent devices to collaborate in executing the first task, with clear calling relationships between the intelligent devices. This avoids conflicts and ineffective information exchange caused by intelligent devices requesting assistance from each other for the same task, thereby improving the execution efficiency of the task.

[0146] Figure 5 shows a flowchart of a communication method provided in an embodiment of this application. The method includes:

[0147] Step 501: The agent management device determines the first topology diagram corresponding to the first task.

[0148] The first topology graph includes a source node intelligent device and at least one reachable node intelligent device of the source node intelligent device. The source node intelligent device is used to receive a first task, and the reachable node intelligent device is used to assist in the execution of the first task. The first topology graph indicates the connection relationship between the source node intelligent device and at least one reachable node intelligent device. The first topology graph is a directed acyclic graph.

[0149] The first topology diagram determined by the agent management device is associated with the first task, which can be understood as the first topology diagram being applicable to the first task.

[0150] In this application, a smart device in the first topological graph may have multiple adjacent vertex smart devices.

[0151] In this application, for a smart device in the first topological graph, when performing a task, if the smart device's capabilities are less than the capabilities required to perform the task, it can request or invoke the assistance of its adjacent vertex smart devices to perform the task. If the smart device's capabilities plus the sum of the capabilities of all its adjacent vertex smart devices are less than the capabilities required to perform the task, it can request the assistance of its predecessor vertex smart device to perform the task.

[0152] In this application, the source node intelligent device can refer to the source node of the first topological graph. The reachable node intelligent device of the source node intelligent device can refer to an intelligent device in the first topological graph that can be reached from the first intelligent device through one or more directed edges. For example, taking Figure 2 as an example, Z is the source node intelligent device, and the reachable node intelligent devices of Z are X, Y1, Y2, and Y3.

[0153] Optionally, in this application, direct communication between non-adjacent smart devices in the topology graph is prohibited. For example, taking Figure 2 as an example, Z and Y1 are not adjacent in Figure 2, and direct communication between Z and Y1 is prohibited; however, Z and X can communicate, and X and Y1 can communicate. This avoids two non-adjacent smart devices requesting each other to assist in performing the same task, thereby improving communication efficiency and task execution efficiency.

[0154] Before step 501, the agent management device can obtain the parameter information of the first task, and thus determine the first topology diagram based on the parameter information of the first task. For details, please refer to the description in step 401, which will not be repeated here.

[0155] In this application, the source node intelligent device and at least one reachable node intelligent device can be at least two intelligent devices selected by the agent management device from a plurality of intelligent devices. In one implementation, before step 501, the agent management device can send a capability reporting request to all intelligent devices within its coverage area, requesting the intelligent devices to report their own capabilities. Further, the agent management device can obtain capability information from multiple intelligent devices, whereby the capability information of each intelligent device indicates its capabilities; for example, the capability information can indicate the size of the intelligent device's capabilities and / or the type of task the intelligent device can perform. That is, the source node intelligent device can send first capability information to the agent management device, and the reachable node intelligent device can send second capability information to the agent management device; the first capability information indicates the capabilities of the source node intelligent device, and the second capability information indicates the capabilities of the reachable node intelligent device.

[0156] It should be noted that the capabilities of the intelligent device involved in this application may include at least one of the intelligent device's storage and processing capabilities. The capabilities of the intelligent device may also include a set of tools that the intelligent device can use, such as the ability to download AI model parameters from the AI ​​model's official website, generate environment configuration instructions for computing nodes, and generate model deployment scripts; the capabilities of the intelligent device may also include the types of tasks that the intelligent device can perform, such as the ability to deploy AI models in a network or to train AI models.

[0157] The agent management device can determine at least two smart devices that meet the first task from among multiple smart devices based on the capability information of multiple smart devices, namely, the source node smart device and at least one reachable node smart device that meet the first task.

[0158] For example, the agent management device can determine the capabilities of each of the multiple smart devices based on the capability information of the multiple smart devices. The sum of the capabilities of at least two smart devices determined by the agent management device from the multiple smart devices is greater than or equal to the capability required to perform the first task, that is, the sum of the capability of the source node smart device and the capability of at least one reachable node smart device is greater than or equal to the capability required to perform the first task.

[0159] For example, the agent management device can determine the task type that each of the multiple smart devices can perform based on the capability information of the multiple smart devices. The agent management device determines that at least two of the multiple smart devices can perform the first task type (i.e., the task type of the first task), that is, the source node smart device and at least one reachable node smart device can both perform the first task type.

[0160] Step 502: The agent management device sends the first information to the source node smart device.

[0161] Correspondingly, the source node intelligent device receives the first information from the agent management device.

[0162] The first information indicates that the source node intelligent device performs the first task, and indicates that the adjacent vertex intelligent devices assist in performing the first task.

[0163] In this application, the source node intelligent device can execute a first task based on the first information. The source node intelligent device can also send first instruction information to its neighboring vertex intelligent devices based on the first information, instructing the neighboring vertex intelligent devices to assist in executing the first task. In this way, by requesting assistance from neighboring vertex intelligent devices, the source node intelligent device ensures the completion of the first task and improves task execution efficiency.

[0164] The agent management device can also send second information to the source node intelligent device based on the first topology diagram. Correspondingly, the source node intelligent device receives the second information from the agent management device.

[0165] The second information indicates that the source node intelligent device is the source node in the first topology graph, and the source node intelligent device is the adjacent vertex intelligent device in the first topology graph. The adjacent vertex intelligent device is one of at least one reachable node intelligent device. In this application, the number of adjacent vertex intelligent devices can be greater than or equal to 1, and the specific number is not limited.

[0166] Optionally, the second information may also be used to instruct the first capability used by the authorized source node intelligent device to perform the first task, wherein the first capability is part or all of the capabilities of the source node intelligent device.

[0167] Optionally, the second information can also be used to instruct the adjacent vertex intelligent devices of the authorized source node intelligent device on the second capability used to assist in performing the first task, wherein the second capability is part or all of the capabilities of the adjacent vertex intelligent devices.

[0168] Optionally, the agent management device can also send a sixth message to the source node intelligent device, indicating the conditions for stopping the execution of the first task. This application does not limit the specific content of the conditions for stopping the execution of the first task. For example, the conditions for stopping the execution of the first task may include at least one of the following: the duration of executing the first task is greater than or equal to a first duration; the amount of resources consumed in executing the first task is greater than or equal to a first quantity. The above are merely examples; other forms of conditions for stopping the execution of the first task may also exist, which will not be elaborated upon here.

[0169] Optionally, the agent management device can also send a seventh message to the source node intelligent device. The seventh message indicates the reporting of the collaborative execution information of the first task. The collaborative execution information of the first task is used to determine whether the conditions for stopping the execution of the first task have been met. The collaborative execution information of the first task may include relevant information during the execution of the first task. For example, the collaborative execution information of the first task may include at least one of the following: the duration of the execution of the first task; the amount of resources consumed in the execution of the first task.

[0170] This application does not limit the conditions for stopping the execution of the first task. For example, the conditions for stopping the execution of the first task may include at least one of the following: the duration of the execution of the first task is greater than or equal to the first duration, and the amount of resources consumed in the execution of the first task is greater than or equal to the first quantity.

[0171] Optionally, the seventh information indicates the reporting conditions for collaborative execution information. The reporting conditions for collaborative execution information can be periodic reporting or triggering reporting by the agent management device through instructions; this application does not limit this.

[0172] In this application, the second and seventh information can be carried in the same message or in different messages, and this application does not limit this.

[0173] Optionally, the agent management device may also send sixth and seventh information to each smart device in the first topology diagram, which is not limited in this application.

[0174] In this application, the agent management device can also send third information to the second intelligent device according to the first topology diagram; the second intelligent device is any intelligent device other than the source intelligent node device among at least two intelligent devices.

[0175] Optionally, the third information also indicates that the predecessor vertex intelligent device of the second intelligent device is the third intelligent device, and the first topology graph also includes the second intelligent device and the third intelligent device, wherein the second intelligent device is the adjacent vertex intelligent device of the third intelligent device in the first topology graph.

[0176] Optionally, the third information may also indicate the adjacent vertex intelligent devices of the second intelligent device in the first topology graph. It should be noted that if the second intelligent device has no adjacent vertex intelligent devices in the first topology graph, the third information may not indicate such adjacent vertex intelligent devices.

[0177] Step 503: The source node intelligent device sends the first instruction information to the adjacent vertex intelligent devices of the source node intelligent device according to the first information.

[0178] The first instruction information directs the adjacent vertex intelligent devices to assist in executing the first task. In this way, the source node intelligent device requests the assistance of adjacent vertex intelligent devices to ensure the completion of the first task and improve task execution efficiency.

[0179] Using the method provided in this application, after establishing a first topology graph for the first task, the agent management device can indicate to the source node intelligent device in the first topology graph the adjacent vertex intelligent devices, and indicate to the source node intelligent device that it can assist in executing the first task through the assistance of the adjacent vertex intelligent devices. This enables multiple intelligent devices to assist in executing the first task, ensuring that the first task can be completed. Since the agent management device instructs the source node intelligent device to request the assistance of the adjacent vertex intelligent devices in executing the first task, there is a clear calling relationship between the intelligent devices during the collaborative execution of the first task. This avoids conflicts and ineffective information exchange caused by intelligent devices requesting assistance from each other for the same task, thereby improving the execution efficiency of the task.

[0180] In this application, the method by which the source node intelligent device performs the first task is not limited. An example is given below.

[0181] Figure 6 shows a flowchart of a communication method provided in an embodiment of this application. The method includes:

[0182] Step 601: The source node intelligent device determines the first subtask and the second subtask based on the first task.

[0183] The source node intelligent device can orchestrate the first task, thereby dividing it into multiple subtasks. This explanation only uses the example of the source node intelligent device dividing the first task into a first subtask and a second subtask; the number of subtasks is not limited.

[0184] Step 602: The source node intelligent device sends a first instruction message to the first intelligent device, which instructs the first intelligent device to assist in performing the first task.

[0185] The first intelligent device is the adjacent vertex device of the source node device.

[0186] In one implementation, if the second information is also used to indicate the second capability used by the authorized first smart device to assist in performing the first task, and the source node smart device determines, based on the second information, that the capability required to perform the first sub-task is less than or equal to the second capability, then it can send the first instruction information to the first smart device.

[0187] Optionally, in this implementation, the first instruction information may instruct the first intelligent device to assist in performing a first subtask of the first task. The first instruction information may also instruct at least one of the following: an identifier of the first subtask; a description of the first subtask; and a data feedback request for the first subtask.

[0188] The description information of the first subtask can indicate the input parameters and data format of the input parameters; the data feedback requirement information of the first subtask can indicate the output parameters and data format of the output parameters.

[0189] Step 603: The first intelligent device executes the first subtask and sends the execution result of the first subtask to the source node intelligent device.

[0190] The first intelligent device can execute the first sub-task independently or request the assistance of adjacent vertex intelligent devices to execute the first sub-task; this application does not limit this.

[0191] For example, the first intelligent device can receive third information from the agent management device, which instructs the first intelligent device to be adjacent vertex intelligent devices in the first topology graph. The first intelligent device can divide the first subtask into a third subtask and a fourth subtask. The first intelligent device can instruct the adjacent vertex intelligent devices to execute the third subtask, and the first intelligent device to execute the fourth subtask.

[0192] The execution result of the first subtask can indicate that the first subtask was executed successfully; optionally, the execution result of the first subtask may also include information such as the output parameters of the first subtask.

[0193] Step 604: The source node intelligent device executes the second subtask and obtains the execution result of the second subtask.

[0194] The execution result of the second subtask can indicate that the second subtask was executed successfully; optionally, the execution result of the second subtask may also include information such as the output parameters of the second subtask.

[0195] The execution order of steps 603 and 604 is merely an example; other execution orders of steps 603 and 604 may also exist, and this application does not limit this.

[0196] The specific processes of steps 604 and 605 are not limited in this application and will not be described in detail here.

[0197] Step 605: The source node intelligent device determines the execution result of the first task based on the execution results of the first subtask and the second subtask.

[0198] The specific content of the execution result of the first task is not limited. For example, if the first task is executed successfully, the execution result of the first task can indicate that the first task was executed successfully; optionally, the execution result of the first task can also include information such as the output parameters of the first task.

[0199] The above example assumes the first task was successfully executed. The first task may also fail; several examples are given below.

[0200] Figure 7 shows a flowchart of a communication method provided in an embodiment of this application. In the following process, the agent management device first indicates the conditions for stopping the execution of the first task to the source node intelligent device and other devices. When the source node intelligent device and other devices determine that the conditions for stopping the execution of the first task are met, they report to the agent management device that the conditions for stopping the execution of the first task are met.

[0201] Step 701: The source node intelligent device performs the first task.

[0202] Here, we take the source node intelligent device as an example. The source node intelligent device can also be replaced by any reachable node intelligent device that assists in performing the first task. For example, the source node intelligent device can be replaced by the first intelligent device.

[0203] The description of the source node intelligent device performing the first task can also be replaced with the description of the source node intelligent device performing the second sub-task of the first task, etc., and this application does not limit it in this way.

[0204] If the source node intelligent device determines that the condition for stopping the execution of the first task has been met during the execution of the first task, then step 702 can be executed.

[0205] For example, the conditions for stopping the execution of the first task include: the duration of the first task execution is greater than or equal to the first duration. When the source node intelligent device executes the first task, if it determines that the duration of the first task execution is greater than or equal to the first duration, then it determines that the conditions for stopping the execution of the first task have been met.

[0206] For example, the conditions for stopping the execution of the first task include: the amount of resources consumed in executing the first task is greater than or equal to a first quantity. When the source node intelligent device executes the first task, if it determines that the amount of resources consumed in executing the first task is greater than or equal to the first quantity, then it determines that the conditions for stopping the execution of the first task have been met.

[0207] The above are just examples. There may be other conditions for stopping the execution of the first task, which will not be elaborated here.

[0208] Step 702: The source node intelligent device sends a fourth message to the agent management device, indicating that the condition for stopping the execution of the first task has been met.

[0209] Step 703: The agent management device sends the fifth information to the source node smart device based on the fourth information. The fifth information indicates that the first task should be stopped.

[0210] The fifth piece of information can also instruct the reporting of the execution results of the first task.

[0211] In this application, for other intelligent devices that assist in performing the first task, such as the first intelligent device, the agent management device or the source node intelligent device may instruct the first intelligent device to stop assisting in performing the first task. Examples are given below.

[0212] Implementation Method 1, Step 704a: The agent management device sends the eighth information to the first intelligent device based on the fourth information. The eighth information indicates to stop assisting in the execution of the first task and reports the execution result of assisting in the execution of the first task.

[0213] Implementation Method 2, Step 704b: The source node intelligent device sends the eighth information to the first intelligent device according to the fifth information. The eighth information indicates to stop assisting in the execution of the first task and reports the execution result of assisting in the execution of the first task.

[0214] The first intelligent device can report the results of its assistance in executing the first task based on the eighth piece of information. For example, the first intelligent device can report the execution results of the first sub-task.

[0215] Step 705: The source node intelligent device sends the execution result of the first task to the agent management device.

[0216] The source node intelligent device determines the execution result of the first task by referring to the previous description, which will not be repeated here.

[0217] The execution result of the first task may include at least one of the following: the failure of the first task and the reason for the failure; the completion progress of the first task. For example, if the first task is a computation task, the reason for failure may be insufficient computing resources; if the first task is a large language model configuration task, the reason for failure may be the absence of a configuration file for the large language model.

[0218] After obtaining the execution result of the first task, the agent management device can re-determine multiple smart devices for the first task and generate a topology diagram corresponding to the first task based on these smart devices. The agent management device can then instruct the source node smart device in this topology diagram to execute the first task; the specific process will not be elaborated further.

[0219] The agent management device can also deregister the first topology diagram. Please refer to the following procedure for details.

[0220] Step 706: The agent management device sends a first deregistration message to the source node smart device. The first deregistration message is used to instruct the source node smart device to deregister in the first topology.

[0221] The source node intelligent device can delete the adjacency relationship and other information between the source node intelligent device and the first intelligent device in the first topology graph based on the first deregistration information. The specific process will not be described in detail.

[0222] The agent management device can also send deregistration information to other reachable node intelligent devices in the first topology graph; the specific process will not be elaborated further. For example, the agent management device sends a second deregistration message to the reachable node intelligent device, which instructs the deregistration of the reachable node intelligent device's topological relationship in the first topology graph. Similarly, the reachable intelligent node device can delete its adjacency information with adjacent vertex intelligent devices, predecessor vertex intelligent devices, etc., in the first topology graph based on the second deregistration message.

[0223] In this application, the agent management device may also determine whether the conditions for stopping the execution of the first task are met, as shown in the example below.

[0224] Figure 8 shows a flowchart of a communication method provided in an embodiment of this application. In the following process, the agent management device first instructs the source node intelligent device and other devices to report the collaborative execution information of the first task. When the agent management device determines that the condition for stopping the execution of the first task is met based on the collaborative execution information, it instructs the source node intelligent device to stop executing the first task.

[0225] Step 801: The source node intelligent device performs the first task.

[0226] Here, we take the source node intelligent device as an example. The source node intelligent device can also be replaced by any reachable node intelligent device that assists in performing the first task. For example, the source node intelligent device can be replaced by the first intelligent device.

[0227] The description of the source node intelligent device performing the first task can also be replaced with the description of the source node intelligent device performing the second sub-task of the first task, etc., and this application does not limit it in this way.

[0228] Step 802: The source node intelligent device sends the collaborative execution information of the first task to the agent management device.

[0229] The collaborative execution information of the first task may include relevant information during the execution of the first task. For example, the collaborative execution information of the first task may include at least one of the following: the duration of the execution of the first task; and the amount of resources consumed in the execution of the first task.

[0230] It should be noted that if the first intelligent device assists in performing the first task, the first intelligent device can also send collaborative execution information of the first task to the agent management device; the specific process will not be elaborated here.

[0231] Step 803: The agent management device determines that the conditions for stopping the execution of the first task have been met, sends the fifth message to the source node intelligent device, the fifth message instructs to stop the execution of the first task, and reports the execution result of the first task.

[0232] For example, the conditions for stopping the execution of the first task include: the duration of the first task execution is greater than or equal to the first duration. When the source node intelligent device executes the first task, if it determines that the duration of the first task execution is greater than or equal to the first duration, then it determines that the conditions for stopping the execution of the first task have been met.

[0233] For example, the conditions for stopping the execution of the first task include: the amount of resources consumed in executing the first task is greater than or equal to a first quantity. When the source node intelligent device executes the first task, if it determines that the amount of resources consumed in executing the first task is greater than or equal to the first quantity, then it determines that the conditions for stopping the execution of the first task have been met.

[0234] The above are just examples. There may be other conditions for stopping the execution of the first task, which will not be elaborated here.

[0235] In this application, for other intelligent devices that assist in performing the first task, such as the first intelligent device, the agent management device or the source node intelligent device may instruct the first intelligent device to stop assisting in performing the first task. Examples are given below.

[0236] Implementation Method 1, Step 804a: The agent management device sends the eighth message to the first intelligent device. The eighth message indicates to stop assisting in the execution of the first task and reports the execution result of the first task.

[0237] Implementation Method 2, Step 804b: The source node intelligent device sends the eighth information to the first intelligent device according to the fifth information. The eighth information indicates to stop assisting in the execution of the first task and reports the execution result of the first task.

[0238] Step 805: The source node intelligent device sends the execution result of the first task to the agent management device.

[0239] The source node intelligent device determines the execution result of the first task by referring to the previous description, which will not be repeated here.

[0240] The specific details of the execution results can be found in the preceding description and will not be repeated here.

[0241] After obtaining the execution result of the first task, the agent management device can re-determine multiple smart devices for the first task and generate a topology diagram corresponding to the first task based on these smart devices. The agent management device can then instruct the source node smart device in this topology diagram to execute the first task; the specific process will not be elaborated further.

[0242] The agent management device can also deregister the first topology diagram. Please refer to the following procedure for details.

[0243] Step 806: The agent management device sends a first deregistration message to the source node smart device. The first deregistration message is used to instruct the source node smart device to deregister in the first topology.

[0244] The source node intelligent device can delete the adjacency relationship and other information between the source node intelligent device and the first intelligent device in the first topology graph based on the first deregistration information. The specific process will not be described in detail.

[0245] The agent management device can also send deregistration information to other reachable node intelligent devices in the first topology graph; the specific process will not be elaborated further. For example, the agent management device sends a second deregistration message to a reachable node intelligent device. Similarly, the reachable intelligent node device can delete its adjacency information with adjacent vertex intelligent devices, predecessor vertex intelligent devices, etc., in the first topology graph based on the second deregistration message.

[0246] It is understood that the various processes described above in this application can be implemented individually or in combination. For example, the processes in Figure 4 and Figure 6 or Figure 7 can be implemented in combination, and this application does not limit this.

[0247] It is understood that, in order to achieve the functions in the above embodiments, the agent management device or source node intelligent device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0248] The following are schematic diagrams of possible communication devices provided in the embodiments of this application. These communication devices can be used to implement the functions of the agent management device or the source node intelligent device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0249] As shown in Figure 9, the communication device 900 includes a processing unit 910 and a communication unit 920. The communication device 900 is used to implement the functions of the agent management device or the source node intelligent device in the various method embodiments shown above.

[0250] When the communication device 900 is used to implement the function of the agent management device:

[0251] A communication unit is used to obtain parameter information for the first task;

[0252] The processing unit is configured to determine a first topology graph based on the parameter information of the first task. The first topology graph indicates the connection relationship of at least two intelligent devices. The first topology graph is a directed acyclic graph. The connection relationship includes at least a source node intelligent device and an adjacent vertex intelligent device of the source node intelligent device. The at least two intelligent devices include the source node intelligent device and the adjacent vertex intelligent device.

[0253] When the communication device 900 is used to implement the functions of the source node intelligent device:

[0254] A communication unit is configured to receive first information from a proxy management device, the first information instructing the source node intelligent device to perform a first task and instructing the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; both the source node intelligent device and the adjacent vertex intelligent devices are included in a first topology graph, the first task is associated with the first topology graph, the first topology graph indicates the connection relationship of at least two intelligent devices, the first topology graph is a directed acyclic graph, and the connection relationship includes at least the source node intelligent device and the adjacent vertex intelligent devices of the source node intelligent device;

[0255] The processing unit is configured to execute the first task based on the first information and send first indication information to the adjacent vertex intelligent device, wherein the first indication information instructs the adjacent vertex intelligent device to assist in executing the first task.

[0256] When the communication device 900 is used to implement the function of the agent management device:

[0257] A processing unit is configured to determine a first topology graph corresponding to a first task; the first topology graph indicates the connection relationship between at least two intelligent devices, wherein the at least two intelligent devices include a source node intelligent device and an adjacent vertex intelligent device of the source node intelligent device in the first topology graph;

[0258] A communication unit is configured to send first information to the source node intelligent device according to the first topology graph, wherein the first information instructs the source node intelligent device to perform the first task and instructs the adjacent vertex intelligent devices to assist in performing the first task.

[0259] When the communication device 900 is used to implement the function of the agent management device:

[0260] A processing unit is configured to determine a first topology graph corresponding to a first task, the first topology graph including a source node intelligent device and at least one reachable node intelligent device of the source node intelligent device; the first topology graph indicates the connection relationship between the source node intelligent device and the at least one reachable node intelligent device, and the first topology graph is a directed acyclic graph.

[0261] A communication unit is configured to send second information to the source node intelligent device according to the first topology graph, the second information indicating that the source node intelligent device is the source node of the first topology graph, and the source node intelligent device is an adjacent vertex intelligent device in the first topology graph, the adjacent vertex intelligent device being one of the at least one reachable node intelligent devices;

[0262] The communication unit is configured to send first information to the source node intelligent device, the first information instructing the source node intelligent device to perform the first task, and instructing the adjacent vertex intelligent devices to assist in performing the first task.

[0263] When the communication device 900 is used to implement the functions of the source node intelligent device:

[0264] The processing unit is configured to receive second information from the agent management device via a communication unit. The second information indicates that the source node intelligent device is a source node in a first topology graph, and that the source node intelligent device is an adjacent vertex intelligent device in the first topology graph. The first topology graph includes the source node intelligent device and at least one reachable node intelligent device of the source node intelligent device. The first topology graph indicates the connection relationship between the source node intelligent device and the at least one reachable node intelligent device, and the first topology graph is a directed acyclic graph. The adjacent vertex intelligent device is one of the at least one reachable node intelligent devices.

[0265] The processing unit is configured to receive first information from the agent management device through the communication unit, the first information instructing the source node intelligent device to perform the first task, and instructing the adjacent vertex intelligent device to assist in performing the first task.

[0266] When the communication device 900 is used to implement the function of the agent management device:

[0267] The communication unit is used to receive the initial capability request;

[0268] The processing unit is configured to determine a first topology graph based on the first capability requirement. The first topology graph includes a source node intelligent device and at least one reachable node intelligent device of the source node intelligent device, wherein the source node intelligent device and the at least one reachable node intelligent device satisfy the first capability requirement. The first topology graph indicates the connection relationship between the source node intelligent device and the at least one reachable node intelligent device, and the first topology graph is a directed acyclic graph.

[0269] The communication unit is configured to send second information to the source node intelligent device according to the first topology graph, the second information indicating that the source node intelligent device is the source node of the first topology graph, and the source node intelligent device is an adjacent vertex intelligent device in the first topology graph, the adjacent vertex intelligent device being one of the at least one reachable node intelligent devices; and to send first information to the source node intelligent device, the first information indicating that the source node intelligent device performs the first task, and indicating that the adjacent vertex intelligent device assists in performing the first task.

[0270] More detailed descriptions of the processing unit 910 and the communication unit 920 can be obtained directly from the relevant descriptions in the above method embodiments, and will not be repeated here.

[0271] It should be understood that the division of units in the above device is merely 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, all units in the device can be implemented entirely through software calls from processing elements; all units can be implemented entirely in hardware; or some units can be implemented through software calls from processing elements, while others are implemented in hardware. For example, each unit can be a separate processing element, or it can be integrated into a chip within the device. Alternatively, it can be stored as a program in memory, called and executed by a processing element of the device. Moreover, these units can be fully or partially integrated together, or implemented independently. The processing element here can also be called a processor, which can be an integrated circuit with signal processing capabilities. In the implementation process, the operations or units described above can be implemented through integrated logic circuits in the processor element or through software calls from processing elements.

[0272] In one example, a unit in any of the above devices can be one or more integrated circuits configured to implement the methods described above, such as: one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these forms of integrated circuits. As another example, when a unit in the device can be implemented in the form of a processing element scheduler, the processing element can be a processor, such as a general-purpose central processing unit (CPU), or other processor capable of calling programs. Furthermore, these units can be integrated together to implement a system-on-a-chip (SOC).

[0273] The receiving unit described above is an interface circuit of the device, used to receive signals from other devices. For example, when the device is implemented as a chip, the receiving unit is an interface circuit for the chip to receive signals from other chips or devices. The transmitting unit described above is an interface circuit of the device, used to transmit signals to other devices. For example, when the device is implemented as a chip, the transmitting unit is an interface circuit for the chip to transmit signals to other chips or devices.

[0274] As another possible product form, the agent management device or source node intelligent device of this application embodiment can be implemented by a general bus architecture. For ease of explanation, refer to FIG10, which is a schematic diagram of the structure of a communication device 1000 provided in an embodiment of this application. The communication device 1000 includes a processor 1001 and a transceiver 1002. The communication device 1000 can be an agent management device or a source node intelligent device, or a chip or chip system thereof. FIG10 only shows the main components of the communication device 1000. In addition to the processor 1001 and the transceiver 1002, the communication device 1000 may further include a memory 1003 and input / output devices (not shown in the figure).

[0275] Optionally, the processor 1001 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs. The memory 1003 is mainly used to store software programs and data. The transceiver 1002 may include radio frequency (RF) circuitry and an antenna. The RF circuitry is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0276] Optionally, the processor 1001, transceiver 1002, and memory 1003 can be connected via a communication bus.

[0277] When the communication device is powered on, the processor 1001 can read the software program in the memory 1003, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1001 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1001. The processor 1001 converts the baseband signal into data and processes the data.

[0278] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor that performs baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0279] In some embodiments, those skilled in the art will recognize that the above-described communication device 900 can take the form of the communication device 1000 shown in FIG10 in terms of hardware implementation.

[0280] As an example, the function / implementation process of the processing unit 910 in FIG9 can be implemented by the processor 1001 in the communication device 1000 shown in FIG10 calling computer execution instructions stored in the memory 1003. The function / implementation process of the communication unit 920 in FIG9 can be implemented by the transceiver 1002 in the communication device 1000 shown in FIG10.

[0281] As another possible product form, the agent management device or source node intelligent device in this application can adopt the composition structure shown in Figure 11, or include the components shown in Figure 11. Figure 11 is a schematic diagram of the composition of a communication device 1100 provided in this application.

[0282] As shown in Figure 11, the communication device 1100 includes at least one processor 1101. Optionally, the communication device also includes a communication interface 1102.

[0283] When the relevant program instructions are executed in the at least one processor 1101, the communication device 1100 can implement the methods and any possible designs provided in any of the foregoing embodiments. Alternatively, the processor 1101 can implement the methods and any possible designs provided in any of the foregoing embodiments through logic circuits or executable code instructions.

[0284] The communication interface 1102 can be used to receive program instructions and transmit them to the processor, or the communication interface 1102 can be used for communication interaction between the communication device 1100 and other communication devices, such as exchanging control signaling and / or service data. For example, the communication interface 1102 can be used to receive signals from other devices besides the communication device 1100 and transmit them to the processor 1101, or to send signals from the processor 1101 to other communication devices besides the communication device 1100.

[0285] Optionally, the communication interface 1102 can be a code and / or data read / write interface circuit, or the communication interface 1102 can be a signal transmission interface circuit between a communication processor and a transceiver, or a chip pin.

[0286] Optionally, the communication device 1100 may further include at least one memory 1103, which can be used to store the required program instructions and / or data. It should be noted that the memory 1103 may exist independently of the processor 1101 or may be integrated with the processor 1101. The memory 1103 may be located within or outside the communication device 1100, without limitation.

[0287] Optionally, the communication device 1100 may further include a power supply circuit 1104, which can be used to power the processor 1101. The power supply circuit 1104 may be located in the same chip as the processor 1101, or in a separate chip outside the chip containing the processor 1101.

[0288] Optionally, the communication device 1100 may also include a bus, through which the various parts of the communication device 1100 can be interconnected.

[0289] In some embodiments, those skilled in the art will recognize that the communication device 900 shown in FIG9 can take the form of the communication device 1100 shown in FIG11 in terms of hardware implementation.

[0290] As an example, the function / implementation process of the processing unit 910 in FIG9 can be implemented by the processor 1101 in the communication device 1100 shown in FIG11 calling the computer execution instructions stored in the memory 1103. The function / implementation process of the communication unit 920 in FIG9 can be implemented by the communication interface 1102 in the communication device 1100 shown in FIG11.

[0291] It should be noted that the structure shown in Figure 11 does not constitute a specific limitation on the agent management device or the source node intelligent device. For example, in other embodiments of this application, the agent management device or the source node intelligent device may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0292] It is understood that the processor in the embodiments of this application may 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, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0293] Based on the above embodiments, this application also provides a computer-readable storage medium storing instructions that, when executed, cause the methods executed by the devices in any of the above method embodiments to be implemented. The computer-readable storage medium may include various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory, random access memory, magnetic disk, or optical disk.

[0294] Based on the above embodiments, this application provides a communication system, which includes the agent management device and source node intelligent device mentioned in any of the above method embodiments. The agent management device can be used to execute the method executed by the agent management device in any of the above method embodiments, and the source node intelligent device can be used to execute the method executed by the source node intelligent device in any of the above method embodiments.

[0295] Based on the above embodiments, this application also provides a computer-readable storage medium storing a computer program or instructions. When the computer program or instructions are executed, they implement the methods performed by the agent management device or source node intelligent device in the aforementioned method embodiments. Thus, the functions described in the above embodiments can be implemented as software functional units and sold or used as independent products.

[0296] Based on the above embodiments, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the method executed by the agent management device or the source node intelligent device in any of the foregoing method embodiments.

[0297] Based on the above embodiments, this application also provides a communication device, including a processor and an interface; the processor is used to execute the methods executed by the agent management device or the source node intelligent device in any of the above method embodiments.

[0298] Based on the above embodiments, this application also provides a chip, including a processor coupled to a memory, for executing computer programs or instructions stored in the memory, so that the chip implements the methods executed by the agent management device or the source node intelligent device in any of the above method embodiments.

[0299] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. Of course, the processor and storage medium can also exist as discrete components in the base station or terminal.

[0300] 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 programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless 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 medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0301] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0302] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0303] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0304] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0305] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A communication method, characterized in that, The method is applied to agent management devices, including: Obtain the parameter information for the first task; Based on the parameter information of the first task, a first topological relationship graph is determined. The first topological relationship graph indicates the connection relationship of at least two intelligent devices. The first topological relationship graph is a directed acyclic graph. The connection relationship includes at least the source node intelligent device and the adjacent vertex intelligent devices of the source node intelligent device. The at least two intelligent devices include the source node intelligent device and the adjacent vertex intelligent devices.

2. The method according to claim 1, characterized in that, The parameter information includes at least one of the following: The capability requirements for the first task; The latency requirements of the first task; The Quality of Service (QoS) requirements of the first task; or, The data provider for the first task.

3. The method according to claim 2, characterized in that, Determining the first topological relationship graph based on the parameter information of the first task includes: Based on the parameter information of the first task, determine the at least two smart devices in the first topology graph and the connection relationship of the at least two smart devices in the first topology graph.

4. The method according to claim 1 or 2, characterized in that, Determining the first topological relationship graph based on the parameter information of the first task includes: Based on the parameter information of the first task, determine the at least two smart devices in the first topology graph; Based on the capability information or status information of the at least two smart devices, the connection relationship of the at least two smart devices in the first topology graph is determined.

5. The method according to any one of claims 2 to 4, characterized in that, The parameter information includes the capability requirements of the first task, and the sum of the capabilities of the at least two smart devices satisfies the capability requirements of the first task.

6. The method according to any one of claims 2 to 5, characterized in that, The parameter information includes the QoS requirements of the first task; the services provided by the at least two smart devices can meet the QoS requirements.

7. The method according to any one of claims 2 to 6, characterized in that, The parameter information includes the latency requirement of the first task; the latency between the at least two smart devices can meet the latency requirement.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: A first message is sent to the source node intelligent device, the first message instructing the source node intelligent device to perform the first task, and instructing the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; both the source node intelligent device and the adjacent vertex intelligent devices are included in the first topology graph.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: According to the first topology graph, a second message is sent to the source node intelligent device, the second message indicating that the source node intelligent device is the source node in the first topology graph, and indicating that the first intelligent device is the adjacent vertex intelligent device of the source node intelligent device in the first topology graph.

10. The method according to claim 9, characterized in that, The second information is also used to indicate the first capability used to authorize the source node intelligent device to perform the first task, wherein the first capability is part or all of the capabilities of the source node intelligent device.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Based on the first topology diagram, send the third information to the second smart device; The third information indicates that the predecessor vertex intelligent device of the second intelligent device is the third intelligent device, and the first topology graph also includes the second intelligent device and the third intelligent device. The second intelligent device is the adjacent vertex intelligent device of the third intelligent device in the first topology graph.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: Receive a fourth message, which indicates that the condition for stopping the execution of the first task has been met; Based on the fourth information, a fifth information is sent to the source node intelligent device, and the fifth information indicates that the first task should be stopped. The execution result of the first task is received from the source node smart device, and the execution result indicates at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

13. The method according to claim 12, characterized in that, Before receiving the fourth information, the method further includes: A sixth message is sent to the source node intelligent device, the sixth message indicating the conditions for stopping the execution of the first task.

14. The method according to any one of claims 1 to 11, characterized in that, The method further includes: Receive the collaborative execution information of the first task; If the condition for stopping the execution of the first task is met according to the collaborative execution information, then a fifth message is sent to the source node intelligent device, and the fifth message indicates that the execution of the first task should be stopped. The execution result of the first task is received from the source node smart device, and the execution result indicates at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

15. The method according to any one of claims 1 to 14, characterized in that, The method further includes: Send a first deregistration message to the source node intelligent device, the first deregistration message being used to instruct the source node intelligent device to deregister its topological relationship in the first topological relationship graph.

16. A communication method, characterized in that, The method is applied to source node intelligent devices, including: The system receives first information from a proxy management device, which instructs the source node intelligent device to perform a first task and instructs the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task. Both the source node intelligent device and the adjacent vertex intelligent devices are included in a first topology graph. The first task is associated with the first topology graph, which indicates the connection relationship between at least two intelligent devices. The first topology graph is a directed acyclic graph, and the connection relationship includes at least the source node intelligent device and the adjacent vertex intelligent devices of the source node intelligent device. Based on the first information, the first task is executed, and a first instruction message is sent to the adjacent vertex intelligent device, the first instruction message instructing the adjacent vertex intelligent device to assist in executing the first task.

17. The method according to claim 16, characterized in that, The method further includes: The system receives second information from the agent management device, the second information indicating that the source node smart device is the source node in the first topology graph, and indicating that the first smart device is the adjacent vertex smart device of the source node smart device in the first topology graph.

18. The method according to claim 17, characterized in that, The second information is also used to indicate the first capability used to authorize the source node intelligent device to perform the first task, wherein the first capability is part or all of the capabilities of the source node intelligent device.

19. The method according to claim 18, characterized in that, The method further includes: Perform the first task based on the first capability.

20. The method according to any one of claims 16 to 19, characterized in that, The method further includes: Receive a fifth message from the agent management device, the fifth message indicating to stop executing the first task; The execution result of the first task is sent to the agent management device, and the execution result indicates at least one of the following: the first task failed and the reason for the failure; the completion progress of the first task.

21. The method according to claim 20, characterized in that, The method further includes: A sixth message is received from the agent management device, the sixth message indicating the conditions for stopping the execution of the first task.

22. The method according to claim 18, characterized in that, Before receiving the fifth piece of information from the agent management device, the method further includes: Send a fourth message to the agent management device, the fourth message indicating that the condition for stopping the execution of the first task has been met; Alternatively, the agent management device may be sent collaborative execution information of the first task, which is used to determine whether the condition for stopping the execution of the first task has been met.

23. A communication device, characterized in that, include: A communication unit is used to obtain parameter information for the first task; The processing unit is configured to determine a first topology graph based on the parameter information of the first task. The first topology graph indicates the connection relationship of at least two intelligent devices. The first topology graph is a directed acyclic graph. The connection relationship includes at least a source node intelligent device and an adjacent vertex intelligent device of the source node intelligent device. The at least two intelligent devices include the source node intelligent device and the adjacent vertex intelligent device.

24. A communication device, characterized in that, include: A communication unit is configured to receive first information from a proxy management device, the first information instructing the source node intelligent device to perform a first task, and instructing the adjacent vertex intelligent devices of the source node intelligent device to assist in performing the first task; The source node intelligent device and the adjacent vertex intelligent device are both included in the first topology graph. The first task is associated with the first topology graph. The first topology graph indicates the connection relationship of at least two intelligent devices. The first topology graph is a directed acyclic graph. The connection relationship includes at least the source node intelligent device and the adjacent vertex intelligent devices of the source node intelligent device. The processing unit is configured to execute the first task based on the first information and send first indication information to the adjacent vertex intelligent device, wherein the first indication information instructs the adjacent vertex intelligent device to assist in executing the first task.

25. A communication device, characterized in that, Including processor and memory; The processor is configured to execute computer programs or instructions stored in the memory, causing the communication device to implement the method described in any one of claims 1 to 22.

26. A computer-readable storage medium, characterized in that, The computer contains a computer program or instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 22.

27. A chip, characterized in that, The chip includes a processor coupled to a memory for executing a computer program or instructions stored in the memory, such that the chip implements the method described in any one of claims 1 to 22.

28. A computer program product, characterized in that, When the computer reads and executes the computer program product, the method described in any one of claims 1 to 22 is performed.

29. A communication system, characterized in that, include: A proxy management device and a source node intelligent device; the proxy management device is used to implement the method according to any one of claims 1 to 15; The source node intelligent device is used to implement the method described in any one of claims 16 to 22.

Images