Communication method and device

Abstract

The embodiment of the invention provides a communication method and device. The method comprises the steps that a first device obtains a target task; the first device obtains a first capability from a shared capability library according to the target task; wherein the shared capability library is used for storing capability, the capability in the shared capability library comprises first capability, and the shared capability library supports a plurality of first devices to share the capability in the shared capability library; the first device performs the target task using the first capability. Different first devices can acquire the first capability corresponding to the target task from the shared capability library when processing the similar target task, and execute the target task by using the first capability to obtain the execution result instead of processing the target task and generating the capability for executing the target task by each first device; according to the process, unnecessary homogenization operation can be reduced, the time spent in the task processing process is shortened, and the task processing efficiency of the first device is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0002] With the rapid development of communication and artificial intelligence (AI) technologies, AI agents can be configured on terminal devices to enhance their intelligence. Terminal devices can send tasks to the AI ​​agent, which then processes them, improving the accuracy of the results. Currently, even with similar tasks, different AI agents process their own tasks independently, resulting in numerous homogeneous operations and low efficiency. Summary of the Invention

[0003] This application provides a communication method and apparatus to improve the task processing efficiency of AIAgent.

[0004] In a first aspect, embodiments of this application provide a communication method, wherein the execution subject of the method is a first device or a module or chip in the first device, and the first device is used as an example for description. The method includes: the first device acquiring a target task; the first device acquiring a first capability from a shared capability library according to the target task; wherein the shared capability library is used to store capabilities, the capabilities in the shared capability library include the first capability, the shared capability library supports multiple first devices sharing the capabilities in the shared capability library; and the first device using the first capability to execute the target task.

[0005] In this method, when different first devices are processing similar target tasks, they can all obtain the first capability corresponding to the target task from the shared capability library and use the first capability to execute the target task and obtain the execution result, instead of each processing the target task and generating its own capability to execute the target task. The above process can reduce unnecessary homogenization operations, which is conducive to reducing the time spent in the task processing process and improving the task processing efficiency of the first device.

[0006] In one possible design, the first device acquires a first capability from a shared capability library based on the target task. This may include: the first device determining at least one subtask corresponding to the target task; and the first device acquiring a second capability corresponding to each of the at least one subtask from the shared capability library. The first capability includes the second capability corresponding to each of the at least one subtask. In this design, the first device can break down the target task into at least one subtask and acquire the second capability corresponding to each subtask from the shared capability library to achieve the purpose of acquiring the first capability. Therefore, the above process can achieve the purpose of acquiring the first capability.

[0007] In one possible design, the first device determining at least one subtask corresponding to the target task may include: the first device sending a first message to a second device, wherein the first message includes the target task and is used to request at least one subtask corresponding to the target task; and the first device receiving at least one subtask from the second device. In this design, the first device determining at least one subtask corresponding to the target task through the second device can improve the efficiency of obtaining at least one subtask. Furthermore, since the second device can provide large language model functionality, the at least one subtask determined by the second device is more accurate and reasonable.

[0008] In one possible design, the first message further includes information about a third capability, which is used to determine at least one subtask; the method may further include: the first device sending a second message to a capability library, wherein the second message includes a target task and is used to request information about the capability corresponding to the target task; the capability library includes a local capability library and / or a shared capability library corresponding to the first device; the local capability library corresponding to the first device is used to store capabilities, and the local capability library corresponding to the first device supports the first device itself to obtain the capabilities in the local capability library, but does not support other first devices to obtain the capabilities in the local capability library; the first device receives information about the third capability from the capability library.

[0009] In one possible design, the information for the third capability includes at least one of the following:

[0010] The identifier of a third ability; or,

[0011] The descriptive information of the third ability, used to describe the function of the third ability; or,

[0012] The sharing method of the third capability, which indicates how the third capability is presented; or,

[0013] The parameter information of the third capability is used to indicate the input parameters required to use the third capability and / or to indicate the output parameters of the third capability; or,

[0014] The environmental dependency information of the third capability is used to indicate the environmental information upon which the third capability depends; or...

[0015] The execution time of the third ability indicates the time required to execute the third ability; or,

[0016] The execution cost of a third capability, used to indicate the cost required to use a third capability; or,

[0017] The API for calling third-party capabilities is used to implement the functionality of third-party capabilities; or...

[0018] The source code of the third ability is used to implement the functionality of the third ability.

[0019] The source code licensing policy for third capabilities is used to indicate whether the source code of third capabilities allows modification / inheritance / derivation and / or whether other capabilities generated based on the source code of third capabilities need to be added to the shared capability library.

[0020] In one possible design, the second message also includes the first constraint condition corresponding to the target task; the third capability satisfies the first constraint condition.

[0021] In one possible design, the first constraint satisfies at least one of the following:

[0022] The first constraint is used to constrain the execution time of the target task; or,

[0023] The first constraint is used to constrain the execution cost of the target task; or,

[0024] The first constraint is used to constrain the execution result of the target task; or,

[0025] The first constraint is used to constrain the execution environment of the target task.

[0026] In one possible design, at least one subtask includes a first subtask; the first device retrieves a second capability corresponding to each of the at least one subtask from a shared capability library, which may include: the first device sending a third message to a second device, wherein the third message includes the first subtask and is used to request an identifier of the second capability corresponding to the first subtask; the first device receiving the identifier of the second capability corresponding to the first subtask from the second device; and the first device retrieving the second capability corresponding to the first subtask from the shared capability library based on the identifier of the second capability corresponding to the first subtask. With this design, the first device can retrieve the second capability from the shared capability library for executing the first subtask.

[0027] In one possible design, the third message may further include information about a fourth capability corresponding to the first subtask, the information about the fourth capability being used to determine the identifier of the second capability corresponding to the first subtask; the method may further include: the first device sending a fourth message to a capability library, the fourth message including the first subtask, the fourth message being used to request information about the capability corresponding to the first subtask; and the first device receiving information about the fourth capability from the capability library.

[0028] In one possible design, the fourth message may also include a second constraint corresponding to the first subtask, which is determined based on the first constraint corresponding to the target task; the fourth capability satisfies the second constraint.

[0029] In one possible design, the second constraint satisfies at least one of the following:

[0030] The second constraint is used to constrain the execution time of the first subtask, which is determined based on the execution time of the target task; or,

[0031] The second constraint is used to constrain the execution cost of the first subtask, which is determined based on the execution cost of the target task; or,

[0032] The second constraint is used to constrain the execution result of the first subtask, the result of which is determined based on the execution result of the target task; or,

[0033] The second constraint is used to constrain the execution environment of the first subtask.

[0034] In one possible design, the first device retrieves the second capability corresponding to the first subtask from a shared capability library based on the identifier of the second capability corresponding to the first subtask. This may include: the first device sending a fifth message to the shared capability library, wherein the fifth message includes the identifier of the second capability corresponding to the first subtask, and the fifth message is used to request the second capability corresponding to the first subtask; and the first device receiving the second capability corresponding to the first subtask from the shared capability library. In this design, the first device can retrieve the second capability for executing the first subtask from the shared capability library.

[0035] In one possible design, the first device retrieves the second capability corresponding to the first subtask from a shared capability library based on the identifier of the second capability corresponding to the first subtask. This may include: the first device retrieving the second capability corresponding to the first subtask from information of a fourth capability, where the information of the fourth capability comes from the shared capability library. In this design, the first device can retrieve the second capability used to execute the first subtask from the information of the fourth capability without having to access the shared capability library again, which improves the efficiency of retrieving the second capability.

[0036] In one possible design, the first device obtains the second capability corresponding to the first sub-task based on the identifier of the second capability corresponding to the first sub-task, which may include: the first device obtains the second capability corresponding to the first sub-task based on the identifier of the second capability corresponding to the first sub-task and authorization information, wherein the authorization information is used to instruct the first device to obtain the second capability corresponding to the first sub-task.

[0037] In one possible design, the above method may further include: the first device sending a sixth message to the third device, wherein the sixth message includes an identifier of a second capability corresponding to the first subtask, and the sixth message is used to request authorization information for the second capability corresponding to the first subtask; the first device receiving the authorization information for the second capability corresponding to the first subtask from the third device. In this design, the first device can quickly obtain the authorization information for the second capability corresponding to the first subtask, which helps to improve the efficiency of obtaining the authorization information for the second capability corresponding to the first subtask.

[0038] In one possible design, the above method may further include: a first device sending a seventh message to a shared capability library, wherein the seventh message includes a second capability corresponding to any subtask in at least one subtask, and the seventh message is used to instruct the second capability corresponding to any subtask to be added to the shared capability library. In this design, the first device can add the generated capability to the shared capability library, making it convenient for other first devices to obtain and use the capability from the shared capability library, avoiding unnecessary homogenization operations.

[0039] In one possible design, the above method may further include: a first device determining a fifth capability based on second capabilities corresponding to multiple subtasks in at least one subtask, wherein the fifth capability is used to implement a target task or a portion thereof; the first device sending a seventh message to a shared capability library, the seventh message including the fifth capability, wherein the seventh message instructs that the fifth capability be added to the shared capability library. In this design, the first device can add the generated capability to the shared capability library, facilitating other first devices to obtain and use the capability from the shared capability library, thus avoiding unnecessary homogenization operations.

[0040] In one possible design, the first device determines a fifth capability based on second capabilities corresponding to multiple subtasks within at least one subtask. This can include: the first device sending an eighth message to a second device, wherein the eighth message includes the second capabilities corresponding to the multiple subtasks within at least one subtask, and the eighth message is used to instruct the generation of a capability based on the capabilities corresponding to the multiple subtasks within at least one subtask; the first device receiving the fifth capability from the second device. In this design, generating the fifth capability by the second device, rather than by the first device, can reduce the power consumption of the first device. Furthermore, the fifth capability generated by the second device is more complete and reasonable.

[0041] In one possible design, the seventh message also includes at least one of the following:

[0042] The identifier of the first device; or,

[0043] The descriptive information of the fifth ability describes the function of the fifth ability; or,

[0044] The sharing method of the fifth ability, which indicates how the fifth ability is presented; or,

[0045] The parameter information of the fifth capability, which indicates the input parameters required to use the fifth capability and / or the output parameters of the fifth capability; or,

[0046] The fifth ability's environmental dependency information is used to indicate the environmental information upon which the fifth ability depends; or,

[0047] The execution time of the fifth ability indicates the time required to execute the fifth ability; or,

[0048] The execution cost of the fifth capability, used to indicate the cost required to use the fifth capability; or,

[0049] The API for calling the fifth ability; the API for calling the fifth ability is used to implement the functionality of the fifth ability; or,

[0050] The source code for the Fifth Ability; the source code for the Fifth Ability is used to implement the functionality of the Fifth Ability.

[0051] The source code license policy for Capability 5 indicates whether the source code of Capability 5 allows modification / inheritance / derivation and / or whether other capabilities generated based on the source code of Capability 5 need to be added to the shared capability library.

[0052] In one possible design, the first device sending a seventh message to the shared capability library may include: the first device sending a seventh message to the shared capability library upon successful verification of the fifth capability.

[0053] In one possible design, the verification of the fifth capability by the first device includes at least one of the following:

[0054] Verification of the execution time of the fifth ability; or,

[0055] Verification of the environment in which the fifth ability depends; or,

[0056] Verification of the code corresponding to the fifth ability.

[0057] Secondly, embodiments of this application provide a communication method. The execution subject of this method is a shared capability library or a module or chip within the shared capability library. Here, the shared capability library is used as the execution subject for example. The method includes: the shared capability library receiving a task from a first device; the shared capability library sending a first capability corresponding to the task to the first device, the first capability being used to execute the task, the shared capability library being used to store capabilities, the capabilities in the shared capability library including the first capability, and the shared capability library supporting multiple first devices sharing the capabilities in the shared capability library.

[0058] In this method, the shared capability library can provide the capability corresponding to the task for multiple first devices. Thus, when different first devices are processing similar tasks, they do not need to process the task and generate the capability for executing the target task on their own. This helps to reduce unnecessary homogenization operations, reduce the time spent in the task processing process, and improve the task processing efficiency of the first devices.

[0059] In one possible design, the shared capability library receives tasks from the first device, which may include: the shared capability library receiving a target task from the first device; the shared capability library sending a first capability corresponding to the task to the first device, which may include: the shared capability library sending the first capability corresponding to the target task to the first device. In this design, after obtaining the target task, the first device does not need to split the target task, but directly obtains the first capability corresponding to the target task from the shared capability library. This avoids the process of splitting the target task and generating executable code for each subtask, reduces unnecessary homogenization operations, helps to reduce the time spent on the above processing, and improves the efficiency of obtaining the execution result of the target task.

[0060] In one possible design, the shared capability library receives tasks from the first device, which may include: the shared capability library receiving at least one subtask corresponding to the target task from the first device; the shared capability library sending a first capability corresponding to the task to the first device may include: the shared capability library sending a second capability corresponding to each of the at least one subtask to the first device, the first capability including the second capability corresponding to each of the at least one subtask. In this design, the first device can split the target task into at least one subtask, and obtain the second capability corresponding to the subtask from the shared capability library to achieve the purpose of obtaining the first capability. Therefore, the above process can achieve the purpose of obtaining the first capability.

[0061] In one possible design, at least one subtask includes a first subtask; the shared capability library sends at least one second capability corresponding to each subtask to the first device, which may include: the shared capability library receiving a fifth message from the first device, wherein the fifth message includes an identifier of the second capability corresponding to the first subtask, and the fifth message is used to request the second capability corresponding to the first subtask; the shared capability library sends the second capability corresponding to the first subtask to the first device. In this design, the first device can obtain the second capability for performing the first subtask from the shared capability library.

[0062] In one possible design, the above method may further include: deducting the execution cost of the second capability corresponding to the first subtask from the account corresponding to the first device using the shared capability library.

[0063] In one possible design, the shared capability library receives a seventh message from the first device, wherein the seventh message includes a second capability corresponding to any one of the at least one subtasks, and the seventh message is used to instruct that the second capability corresponding to any one of the subtasks be added to the shared capability library; the shared capability library adds the second capability corresponding to any one of the at least one subtasks to the shared capability library. In this design, the first device can add the generated capability to the shared capability library, making it convenient for other first devices to obtain and use the capability from the shared capability library, avoiding unnecessary homogenization operations.

[0064] In one possible design, the above method may further include: the shared capability library distributing a reward corresponding to the second capability of any subtask in at least one subtask to the account corresponding to the first device.

[0065] In one possible design, the above method may further include: a shared capability library receiving a seventh message from a first device, wherein the seventh message includes a fifth capability, which is generated based on second capabilities corresponding to multiple subtasks in at least one subtask; the seventh message instructs that the fifth capability be added to the shared capability library; and the shared capability library adds the fifth capability to the shared capability library. In this design, the first device can add the generated capability to the shared capability library, facilitating other first devices to obtain and use the capability from the shared capability library, thus avoiding unnecessary homogenization operations.

[0066] In one possible design, the above method may also include: the shared capability library distributing the reward corresponding to the fifth capability to the account corresponding to the first device.

[0067] In one possible design, the above method may also include: optimizing the capabilities in the shared capability library.

[0068] In one possible design, capability optimization in the shared capability library includes at least one of the following: capability deletion, capability merging, capability replacement, and capability reconstruction. In this design, by optimizing the capabilities in the shared capability library, the quality of the capabilities in the shared capability library can be continuously improved, thereby increasing task execution efficiency.

[0069] Thirdly, 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.

[0070] In one possible design, the communication device includes a processor configured to support the communication device in performing corresponding functions performed by the first device or shared capability library 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.

[0071] In one possible design, 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.

[0072] In one possible design, 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 either the first or second aspect, and will not be repeated here.

[0073] Fourthly, embodiments of this application also provide a communication device, which includes modules / units for performing any of the methods provided in any of the first to second aspects described above. These modules / units can be implemented in hardware or by hardware executing corresponding software.

[0074] Fifthly, embodiments of this application provide a communication device, including a memory and a processor; wherein the processor is configured to execute a computer program or instructions stored in the memory, causing the communication device to implement any of the methods provided in any of the first to second aspects described above.

[0075] Sixthly, this application also provides a computer-readable storage medium, which includes a computer program that, when run on a communication device, causes the computer-readable storage medium to implement any of the methods provided in any of the first to second aspects.

[0076] In a seventh aspect, embodiments of this application also provide a computer program product that, when run on a communication device, causes the communication device to implement any of the methods provided in any of the first to second aspects described above.

[0077] Eighthly, a chip is provided, comprising a processor and potentially a memory, for implementing any of the methods provided in any of the first to second aspects. The chip may be composed of a chip or may include chips and other discrete devices.

[0078] A ninth aspect provides a communication system, comprising: a first device and a shared capability library; the first device is configured to implement the methods of the first aspect and any possible implementation thereof, and the shared capability library is configured to implement the methods of the second aspect and any possible implementation thereof.

[0079] In a tenth aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to implement any of the methods provided in any of the first to second aspects described above.

[0080] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0081] Figure 1This application provides a schematic diagram of the structure of a communication system according to an embodiment of the present application.

[0082] Figure 2 This application provides a schematic diagram of the structure of a communication system according to an embodiment of the present application.

[0083] Figure 3 A flowchart illustrating a communication method provided in an embodiment of this application;

[0084] Figure 4 A flowchart illustrating a method for acquiring a first capability provided in an embodiment of this application;

[0085] Figure 5 A flowchart illustrating a method for acquiring a first capability provided in an embodiment of this application;

[0086] Figure 6 A flowchart illustrating a method for obtaining at least one subtask, provided in an embodiment of this application;

[0087] Figure 7 A flowchart illustrating a method for obtaining information about a third capability, provided in an embodiment of this application;

[0088] Figure 8 A flowchart illustrating a method for obtaining a second capability corresponding to a first subtask, provided in an embodiment of this application;

[0089] Figure 9 A flowchart illustrating a method for obtaining information about a fourth capability, provided in an embodiment of this application;

[0090] Figure 10 A flowchart illustrating a method for obtaining authorization information of a second capability corresponding to a first subtask, provided in an embodiment of this application;

[0091] Figure 11 A flowchart illustrating a method for adding capabilities provided in an embodiment of this application;

[0092] Figure 12 A flowchart illustrating a method for determining a fifth capability provided in an embodiment of this application;

[0093] Figure 13 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0094] Figure 14 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0095] The technical solutions of the embodiments of this application will be clearly and completely 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 reference numerals in the specification, claims, and drawings of 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 used interchangeably 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 apparatus 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 apparatuses.

[0096] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0097] Large language models (LLMs) are deep learning models trained on large amounts of text data that can generate natural language text or understand the meaning of language text. LLMs can handle various natural language tasks, such as text classification, question answering, and dialogue, and are an important pathway to artificial intelligence.

[0098] Prompt information, also known as guidance information, is a piece of text used in large language models to guide the model in generating specific types of output. By designing and optimizing a set of prompts, a large language model can perform specific tasks.

[0099] Artificial intelligence agents, also known as intelligent agents or intelligent agents, are intelligent entities that can perceive the environment, make decisions, and perform actions. They are designed to efficiently execute and process complex tasks through natural language interaction using large language models.

[0100] The technical solutions disclosed in this application can be applied to 5G communication systems, such as 5G New Radio (NR) systems; they can also be applied to various application scenarios of 5G communication systems, such as enhanced mobile broadband (eMBB), ultra-reliable low latency communication (URLLC), and enhanced machine-type communication (eMTC). The technical solutions disclosed in this application can also be applied to various future communication systems, such as future communication systems and integrated air-space-sea-terrestrial communication systems. Furthermore, the technical solutions disclosed in this application can be applied to communication between base stations, communication between terminal devices, vehicle-to-everything (V2X) networks, the Internet of Things (IoT), the Industrial Internet, satellite communication, etc., for example, to device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communication systems.

[0101] Figure 1 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 1 As shown, the communication system 10 includes one or more network devices 20 and one or more terminal devices 30. The interface between the network devices and the terminal devices can be a Uu interface (or air interface), and data transmission between the network devices 20 and the terminal devices 30 can occur through the air interface. The terminal devices can access a data network (DN) through the network devices. The components of this communication system are described below.

[0102] (1) Terminal equipment

[0103] Terminal devices include devices that provide voice and / or data connectivity to users. For example, a terminal device is a device with wireless transceiver capabilities that can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted; it can also be deployed on water (such as on ships); and it can be deployed in the air (such as on airplanes, balloons, and satellites). Terminal devices can be tags, mobile phones, tablets, computers with wireless transceiver capabilities, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, vehicle-mounted terminals, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, wearable terminals, etc. The embodiments in this application do not limit the application scenarios. Terminal equipment may also be referred to as a terminal, user equipment (UE), access terminal, vehicle-mounted terminal, vehicle-mounted equipment, industrial control terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication equipment, UE agent, or UE device, etc. Terminal equipment can be fixed or mobile. It is understood that all or part of the functions of the terminal equipment in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The terminal equipment in this application can be a terminal for 5G or a terminal for future communication networks; this application does not limit this.

[0104] (2) Network equipment

[0105] Network equipment can include access network equipment and core network equipment.

[0106] Access network equipment is a device that provides wireless communication functions for terminal devices. Access network equipment includes, but is not limited to: future base stations (g node B, gNB) in 5G, evolved node B (eNB), radio network controller (RNC), node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home-evolved node B, or home node B, HNB), base band unit (BBU), transmitting and receiving point (TRP), transmitting point (TP), mobile switching center, etc.

[0107] Access network equipment and terminal equipment can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the access network equipment and terminal equipment.

[0108] Core network equipment includes some or all of the following network elements: unified data management (UDM) network element, unified data repository (UDR) network element, network exposure function (NEF) network element, application function (AF) network element, policy control function (PCF) network element, access and mobility management function (AMF) network element, tag management function (TMF) network element, session management function (SMF) network element, user plane function (UPF) network element, and network repository function (NRF) network element.

[0109] Access and Mobility Management (AMM) network elements are control plane network elements provided by the operator's network, responsible for access control and mobility management of terminal equipment accessing the operator's network. Functions include mobility state management, allocation of temporary user identities, authentication, and authorization. In 5G, AMM network elements can be AMF network elements. In future communication networks, AMM network elements may still be AMF network elements, or may have other names; this application does not impose any limitations.

[0110] User plane function network elements are gateways provided by the operator, serving as the gateway for communication between the operator's network and the DN (Digital Network Provider). User plane function network elements include user plane-related functions such as packet routing and transmission, packet inspection, service usage reporting, Quality of Service (QoS) processing, lawful interception, uplink packet inspection, and downlink packet storage. In 5G, user plane network elements can be UPF (User Plane Function) network elements. In future communication networks, user plane network elements may still be UPF network elements, or may have other names; this application does not impose any limitations.

[0111] exist Figure 1 In the network architecture shown, to improve the intelligence of terminal devices, intelligent agents can be set up for terminal devices. The intelligent agent can be located in the terminal device or in the network device. The intelligent agent located in the network device can provide relevant services to the terminal device, which is not limited here.

[0112] by Figure 1 The network architecture shown includes two terminal devices, with each terminal device's corresponding smart agent located on a network device. Figure 1 The network architecture shown includes terminal device 1 and terminal device 2. User 1 can use terminal device 1, and the smart proxy configured for terminal device 1 is smart proxy 1. User 2 can use terminal device 2, and the smart proxy configured for terminal device 2 is smart proxy 2.

[0113] User 1 inputs the target task into terminal device 1, namely "help me predict the future weather in Nanjing". Terminal device 1 sends the target task to intelligent agent 1. Intelligent agent 1 breaks down the target task into 3 sub-tasks, as follows:

[0114] 1. Retrieve a list of weather web pages;

[0115] 2. Retrieve the Nanjing weather webpage from the list of weather webpages;

[0116] 3. Retrieve Nanjing's weather information for the next 15 days from the Nanjing Weather website.

[0117] After obtaining the above three sub-tasks, Smart Agent 1 generates executable code corresponding to each of the three sub-tasks. By using the executable code corresponding to each of the three sub-tasks to execute the three sub-tasks in sequence, Smart Agent 1 can obtain the weather information for Nanjing for the next 15 days.

[0118] Similarly, User 2 inputs the target task into Terminal Device 2, namely "Help me predict the future weather in Shenzhen". Terminal Device 2 sends the target task to Smart Agent 2, which breaks down the target task into 3 sub-tasks, as follows:

[0119] 1. Retrieve a list of weather web pages;

[0120] 2. Retrieve the Shenzhen weather webpage from the list of weather webpages;

[0121] 3. Retrieve Shenzhen's weather information for the next 15 days from the Shenzhen Weather website.

[0122] After obtaining the above three sub-tasks, Smart Agent 2 generates executable code corresponding to each of the three sub-tasks. By executing the three sub-tasks sequentially using the executable code, Smart Agent 2 can obtain the weather information for Shenzhen for the next 15 days.

[0123] As can be seen from the above, when processing the target task, both intelligent agent 1 and intelligent agent 2 need to break down the target task into multiple subtasks and generate corresponding executable code for each subtask. The above processing takes a relatively long time.

[0124] Furthermore, since Smart Agent 1 and Smart Agent 2 have similar target tasks and generate executable code in similar ways, there is unnecessary homogenization, which will also lead to a longer processing time.

[0125] Based on this, embodiments of this application provide a communication method to solve the problem that intelligent agents need to spend a long time processing target tasks.

[0126] The communication method provided in the embodiments of this application is applicable to Figure 2 The communication system shown includes at least a first device and a shared capability library (SCL), wherein the first device can communicate with the shared capability library and also with terminal devices. Optionally, Figure 2The communication system shown may also include a local capability library (LCL) corresponding to the first device, a second device, and a third device. The communication connection relationships between the first device, the local capability library corresponding to the first device, the shared capability library, the second device, and the third device in this communication system can be referenced. Figure 2 The communication connection between the first device, the local capability library corresponding to the first device, the shared capability library, the second device, and the third device in the communication system can be a wired connection or a wireless connection, which is not limited here.

[0127] The following are Figure 2 The communication system shown is explained in detail below, including the first device, the local capability library corresponding to the first device, the shared capability library, the second device, and the third device:

[0128] 1) The first device is a device that provides intelligent agent functionality. The first device can be a virtual device or a physical device, and there is no limitation thereto. The first device can obtain the target task from the terminal device and return the result of the target task to the terminal device.

[0129] One first device can correspond to one terminal device, that is, one first device can receive a target task from a terminal device. In this case, the first device can be located in the terminal device, in the network device, or as an independent network element structure, without limitation.

[0130] One first device can correspond to multiple terminal devices, meaning that one first device can receive target tasks from multiple terminal devices. In this case, the first device can be located in a network device, or the first device can be an independent network structure; this is not limited here.

[0131] 2) The local capability library corresponding to the first device is used to store capabilities. One local capability library corresponds to one first device. One local capability library supports its own corresponding first device to obtain the capabilities in the local capability library, but does not support other first devices to obtain the capabilities in the local capability library.

[0132] For each first device, there may or may not exist a local capability library corresponding to each first device. If a local capability library corresponding to each first device exists, each first device may correspond to one local capability library or multiple local capability libraries, which is not limited here.

[0133] The local capability library corresponding to the first device can be located in the terminal device, the network device, or an independent structure; no limitation is made here.

[0134] The capabilities stored in the local capability library can be understood as source code used to implement a task, or as executable files used to implement a task, etc., without any specific definition here.

[0135] It should be understood that the capabilities in the local capability library corresponding to the first device can be generated and added by the first device, or generated by the local capability library by optimizing the capabilities in its own capability library, or can be the capabilities inherent in any network device in the communication network, such as computing capabilities, sensing capabilities, etc., without limitation here.

[0136] 3) The shared capability library is used to store capabilities, and the shared capability library supports multiple first devices to share the capabilities in the shared capability library.

[0137] The shared capability library can be located in terminal devices, network devices, or as an independent structure; no specific restrictions are imposed here.

[0138] The capabilities stored in the shared capability library can be understood as source code used to implement a task, or as executable files used to implement a task, etc., without being limited here.

[0139] It should be understood that the capabilities in the shared capability library can be generated and added by any first device, or generated by the shared capability library by optimizing the capabilities in its own capability library, or added by a capability provider (CP). The CP is used to generate and provide capabilities. The CP can be a third-party application program interface (API), etc., without limitation. It can also be a capability that any network device in the communication network itself has, without limitation.

[0140] 4) The second device is a device that provides large language model functionality. The second device can be a virtual device or a physical device, and there is no limitation on this. The first device can send a target task to the second device, and the second device can decompose the target task using the large language model to obtain at least one subtask, and send at least one subtask to the first device.

[0141] A second device can correspond to a first device, meaning a second device can receive a target task from a first device. In this case, if the first device is located in a terminal device, the second device can be located in that terminal device, a network device, or an independent network element. If the first device is located in a network device, the second device can be located in the network device or an independent network element. If the first device is an independent network element, the second device can be located in the network device or an independent network element.

[0142] One second device can correspond to multiple first devices, meaning one second device can receive target tasks from multiple first devices. In this case, if the first devices are located in a network device, the second device can be located in the network device or be an independent network element. If the first device is an independent network element, the second device can be located in the network device or be an independent network element.

[0143] 5) The third device is a device that can provide authorization information for capabilities. The third device can be a virtual device or a physical device, and there is no limitation on this.

[0144] The third device can receive an authorization request message sent by the first device, wherein the authorization request message is used to request authorization information for the capability of any task, and after receiving the authorization request message, the third device can send the authorization information for the capability of the task to the first device.

[0145] A third device can correspond to a first device, meaning a third device can receive authorization request messages from a first device. In this case, if the first device is located in a terminal device, the third device can be located in that terminal device, a network device, or an independent network element. If the first device is located in a network device, the third device can be located in the network device or an independent network element. If the first device is an independent network element, the third device can be located in the network device or an independent network element.

[0146] One third device can correspond to multiple first devices, meaning one third device can receive authorization request messages from multiple first devices. In this case, if the first devices are located in a network device, the third device can be located in the network device or be an independent network element. If the first devices are independent network elements, the third device can be located in the network device or be an independent network element.

[0147] It should be understood that the first device, the local capability library corresponding to the first device, the shared capability library, the second device, and the third device can be integrated into the same device, or they can be located in different devices, or they can be partially located in the same device, without any limitation here.

[0148] Combination Figure 2 The system architecture diagram shown in this application is an example. Figure 3 The illustrated method embodiments provide a detailed description of the technical solution of this application. It should be noted that... Figure 3 This is a schematic flowchart illustrating an embodiment of the method of this application, showing the detailed communication steps or operations of the method. However, these steps or operations are merely examples, and other operations may be performed in the embodiments of this application. Figure 3Variations of various operations within it. Furthermore, Figure 3 Each step in the process can be followed separately according to... Figure 3 The different orders presented may be executed, and it is possible that they are not intended to be executed. Figure 3 All operations within. Figure 3 The communication method shown is by Figure 2 The first device and the shared capability library interact and execute.

[0149] S301, the first device acquires the target mission.

[0150] For example, a user can input a target task on the terminal device. The target task can be described in the form of text, voice, image, etc., without limitation. For the sake of clarity in the following description, we will use text as the description of the target task as an example.

[0151] When the first device is located in a terminal device, the first device can directly obtain the target task from the terminal device; when the first device is located in a network device or is an independent network element structure, the terminal device can send the target task to the first device.

[0152] Optionally, the first device can also acquire the task constraints of the target task. The task constraints can be described in various ways, such as text, voice, or images, and are not limited here. For ease of explanation later, the following description will use text as an example to illustrate the task constraints of the target task.

[0153] For example, the first device can obtain the task constraints of the target task through any one of the following embodiments A1, A2, or A3.

[0154] In implementation method A1, the first device generates task constraints based on the target task.

[0155] In this embodiment of the application, after acquiring the target task, the first device can automatically generate the task constraints of the target task.

[0156] In implementation method A2, the first device obtains the task constraints of the target task from the task constraint configuration.

[0157] In one possible implementation, the first device stores a task constraint configuration, which may include task constraints corresponding to multiple tasks, wherein the multiple tasks in the task constraint configuration include a target task. After obtaining the target task, the first device can obtain the task constraints corresponding to the target task from the task constraint configuration.

[0158] In implementation method A3, the first device receives task constraints of a target task from a terminal device, wherein the task constraints of the target task are input by the user in the terminal device.

[0159] In this embodiment of the application, when the first device is located in a terminal device, the first device can directly obtain the task constraints of the target task from the terminal device; when the first device is located in a network device or is an independent network element structure, the terminal device can send the task constraints of the target task to the first device.

[0160] The following provides a detailed explanation of the task constraints of the target task. The task constraints of the target task must satisfy at least one of the following:

[0161] 1) Task constraints are used to constrain the execution time of the target task.

[0162] For example, task constraints may include a time limit or time range for the execution of the target task. For instance, a task constraint may include 30 seconds, indicating that the target task must be completed within 30 seconds; or, a task constraint may include 10 to 30 seconds, indicating that the target task must be completed within 10 to 30 seconds.

[0163] 2) Task constraints are used to constrain the execution cost of the target task.

[0164] For example, task constraints may include a cost ceiling or cost range for the execution cost of the target task. The execution cost can be in the form of points, currency, etc., and is not limited here. For instance, a task constraint may include 100 points, indicating that the target task must be completed within 100 points; or, a task constraint may include 100 to 200 points, indicating that the target task must be completed within 100 to 200 points.

[0165] 3) Task constraints are used to constrain the execution results of the target task.

[0166] For example, task constraints can include information about the format of the target task's execution result. For instance, task constraints could include displaying the target task's execution result in a chart, in text, or rounded down.

[0167] In addition, the task constraints of the target task can also constrain other aspects of the target task, which are not limited here.

[0168] It should be understood that the user can simultaneously input the target task and its constraints on the terminal device, and the first device simultaneously obtains the target task and its constraints from the terminal device. Alternatively, the user can first input the target task on the terminal device, and after the first device obtains the target task from the terminal device, the user can then input the task constraints on the terminal device, and the first device will then obtain the task constraints from the terminal device.

[0169] Furthermore, the embodiments of this application do not limit the input format of the target task and task constraints. For example, a user can input a descriptive text in a terminal device, and after obtaining the descriptive text, the first device parses the descriptive text to obtain the target task and the task constraints of the target task from the descriptive text.

[0170] For example, a user enters a descriptive text into a terminal device. The content of the descriptive text is "Help me predict the future weather in Nanjing. This needs to be completed within 30 seconds. The cost cannot exceed 100 points. The prediction result will be displayed in the form of charts and text." After obtaining the descriptive text, the first device parses the descriptive text and obtains the target task as "Help me predict the future weather in Nanjing." The corresponding task constraints are "It needs to be completed within 30 seconds. The cost cannot exceed 100 points. The prediction result will be displayed in the form of charts and text."

[0171] S302, the first device retrieves a first capability from the shared capability library according to the target task. The first capability can be used to execute the target task and obtain the execution result of the target task.

[0172] In the embodiments of this application, the first device may acquire the first capability through any one of the following embodiments B1 or B2.

[0173] Implementation method B1 includes Figure 4 The following steps are shown:

[0174] S401, the first device sends a ninth message to the shared capability library; correspondingly, the shared capability library receives the ninth message from the first device.

[0175] In this embodiment of the application, the ninth message includes a target task, and the ninth message is used to request the first capability corresponding to the target task, or the ninth message is used to indicate that the first capability corresponding to the target task is obtained.

[0176] Optionally, the ninth message may also include a first constraint, wherein the first constraint is determined based on the task constraints of the target task and / or the environmental information of the first device.

[0177] In one possible implementation, the environmental information of the first device includes software environment information and / or hardware environment information. The software environment information of the first device may include the operating system version number corresponding to the first device, and the hardware configuration information of the first device may include the central processing unit (CPU) model, network card model, etc. corresponding to the first device.

[0178] The first constraint is explained in detail below. The first constraint can satisfy at least one of the following:

[0179] 1) The first constraint is used to constrain the execution time of the target task.

[0180] In the embodiments of this application, the detailed description of the first constraint used to constrain the execution time of the target task can be found in the previous detailed description of the task constraint used to constrain the execution time of the target task, and will not be repeated here.

[0181] 2) The first constraint is used to constrain the execution cost of the target task.

[0182] In the embodiments of this application, the detailed description of the first constraint used to constrain the execution cost of the target task can be found in the foregoing detailed description of the task constraint used to constrain the execution cost of the target task, and will not be repeated here.

[0183] 3) The first constraint is used to constrain the execution result of the target task.

[0184] In the embodiments of this application, the detailed description of the first constraint used to constrain the execution result of the target task can be found in the foregoing detailed description of the task constraint used to constrain the execution result of the target task, and will not be repeated here.

[0185] 4) The first constraint is used to constrain the execution environment of the target task.

[0186] In this embodiment of the application, the first constraint may include environmental information of the first device, which is used to constrain the execution environment of the target task.

[0187] In addition, the first constraint may include other constraints, which are not limited here.

[0188] S402, the shared capability library determines the first capability corresponding to the target task.

[0189] In the embodiments of this application, the shared capability library may store at least one capability and information for each capability, or it may store at least one capability and the encoding vector corresponding to the information for each capability, or it may store at least one capability, information for each capability, and the encoding vector for the information for each capability, without limitation. The encoding vector corresponding to the capability information may be generated using an embedding model or other methods, without limitation.

[0190] In one possible implementation, the information about the capabilities in the shared capability library includes at least one of the following:

[0191] 1) Identification of abilities.

[0192] In the embodiments of this application, the capability identifier is used to distinguish different capabilities. The capability identifier can be the capability name, capability number, capability storage path, etc., and is not limited here. The capability identifier can be determined by a shared capability library for each capability, or it can be determined by the first device or CP providing the capability, and is not limited here.

[0193] 2) Description of abilities.

[0194] In the embodiments of this application, the capability description information is used to describe the function of the capability. The capability description information can be a piece of text, and is not limited thereto.

[0195] 3) Capability sharing methods.

[0196] In this embodiment, the capability sharing method is used to indicate the presentation method of the capability. The capability sharing method can be source code sharing or interface sharing, wherein the interface sharing method can include API sharing and Agent interface sharing.

[0197] If the capability is shared via source code sharing, it means that the source code of the capability is required to use it.

[0198] If the capability is shared via an interface, it means that there is no need to obtain the capability's source code; instead, the capability can be used by directly calling its API.

[0199] If the interface sharing method is API sharing, then the interface for calling the capability is the application interface.

[0200] If the interface sharing method is Agent interface sharing method, then the interface for calling the capability is Agent interface.

[0201] 4) Ability parameter information.

[0202] In the embodiments of this application, the capability parameter information is used to indicate the input parameters required to use the capability and / or to indicate the output parameters of the capability. The capability parameter information can be set in either the source code sharing method or the interface sharing method.

[0203] 5) Environmentally dependent information about capabilities.

[0204] In this embodiment, the capability's environment dependency information is used to indicate the environment information upon which the capability depends. The capability's environment dependency information includes the software environment information and / or the hardware configuration information upon which the capability depends. The software environment information may include the operating system version number upon which the capability depends, and the hardware configuration information may include the CPU model, network card model, etc. upon which the capability depends.

[0205] 6) Execution time of the capability.

[0206] In the embodiments of this application, the execution time of the capability is used to indicate the time required to execute the capability.

[0207] 7) The cost of implementing the capability.

[0208] In the embodiments of this application, the execution cost of a capability is used to indicate the cost required to use the capability. The execution cost of a capability may be in the form of points, currency, etc., and is not limited thereto.

[0209] 8) Capability call interface.

[0210] In this embodiment, the first device can implement the function of the capability by calling the capability's calling interface. Generally, the capability's calling interface can be a calling interface corresponding to a piece of callable code, and is not limited here.

[0211] In this embodiment of the application, when the capability is shared via an interface, the capability information includes the capability's calling interface.

[0212] When the interface sharing method is API sharing, the interface for calling the capability is the application interface.

[0213] When the interface sharing method is Agent interface sharing method, the interface for calling the capability is Agent interface.

[0214] 9) The source code of the capability.

[0215] In this embodiment of the application, the first device can implement the function of the capability by calling the source code of the capability. Generally, the source code of the capability can be a piece of executable code, which is not limited here.

[0216] In this embodiment of the application, when the capability is shared in the form of source code sharing, the capability information includes the capability's source code.

[0217] 10) Source code licensing policy for capabilities.

[0218] In this application embodiment, the capability's source code licensing policy is used to indicate whether the capability's source code allows modification / inheritance / derivation and / or whether other capabilities generated based on the capability's source code need to be added to the shared capability library. It should be understood that allowing inheritance / derivation of a capability's source code means that the source code of other capabilities can use the source code of that capability and add additional functional code based on that capability's source code.

[0219] In one possible implementation, if the source code licensing policy of a capability indicates that the source code of a capability cannot be modified / inherited / derived, then the source code of the capability can only be used, and cannot be modified / inherited / derived.

[0220] In one possible implementation, if the source code licensing policy of a capability indicates that other capabilities generated based on the source code of that capability need to be added to the shared capability library, then those other capabilities must be added to the shared capability library. If the source code licensing policy of a capability indicates that other capabilities generated based on the source code of that capability do not need to be added to the shared capability library, then those other capabilities may or may not be added to the shared capability library.

[0221] In this embodiment of the application, the shared capability library can determine the first capability corresponding to the target task through any one of the following implementation methods C1 or C2.

[0222] In implementation method C1, the shared capability library first calculates the similarity between the information of each capability in the shared capability library and the target task in the ninth message, and selects the capabilities with a similarity greater than a first similarity threshold as the first capability. The first capability may include one or more capabilities from the shared capability library.

[0223] In the above implementation method C1, the similarity between the information of each capability and the target task can be determined by the following method: the shared capability library first encodes the target task to obtain a first encoding vector; then, the shared capability library calculates the similarity between the encoding vector of the information of each capability and the first encoding vector, which is used as the similarity between the information of each capability and the target task.

[0224] The first capability can be quickly determined through the above implementation method C1, and the determined first capability can achieve the target task.

[0225] In implementation method C2, the shared capability library can calculate the similarity between the information of each capability in the capability library and the target task and the first constraint in the ninth message, and designate capabilities with a similarity greater than a first similarity threshold as first capabilities. The first capabilities may include one or more capabilities from the shared capability library.

[0226] In the above implementation method C2, the similarity between the information of each capability and the target task and the first constraint in the ninth message can be determined by the following method: the shared capability library first encodes the target task and the first constraint to obtain a second encoding vector; then, the shared capability library calculates the similarity between the encoding vector of the information of each capability and the second encoding vector, which is used as the similarity between the information of each capability and the target task and the first constraint in the ninth message.

[0227] The first capability can be accurately determined through the above implementation method C2, and the determined first capability can not only achieve the target task, but also satisfy the first constraint condition.

[0228] S403, the shared capability library sends the first capability to the first device.

[0229] In this embodiment, the shared capability library can also connect to accounts corresponding to multiple first devices, allowing for the addition or reduction of account balances within these accounts. It should be understood that the accounts corresponding to the first devices can be established, managed, and maintained by a third-party organization.

[0230] In one possible implementation, when the shared capability library sends the first capability to the first device, it can obtain the execution cost of the first capability from the information of the first capability and deduct the execution cost of the first capability from the account corresponding to the first device. The shared capability library can also add the deducted execution cost of the first capability to the account corresponding to the first device that provided the first capability.

[0231] Through the above-described implementation method B1, after acquiring the target task, the first device does not need to split the target task. Instead, it directly obtains the first capability corresponding to the target task from the shared capability library. This avoids the process of splitting the target task and generating capabilities for each sub-task, thus improving the efficiency of acquiring the first capability. Furthermore, when different first devices process similar target tasks, they can all obtain the first capability corresponding to the target task from the shared capability library, instead of processing the target task separately and generating capabilities for execution independently. This process reduces unnecessary homogenization operations, helps to reduce the time spent on task processing, and improves the task processing efficiency of the first device.

[0232] Before executing the above-described implementation method B1, the first device may first send a ninth message to its local capability library. This ninth message requests the first capability corresponding to the target task. If the local capability library can determine the first capability corresponding to the target task from its own resources, it can directly send the first capability to the first device. Afterward, the first device does not need to execute the above-described implementation method B1. If the local capability library cannot determine the first capability corresponding to the target task from its own resources, the first device executes the above-described implementation method B1. Since the first device is more efficient at obtaining capabilities from its local capability library, the above method can quickly obtain the first capability if the first capability corresponding to the target task exists in the local capability library.

[0233] It should be understood that the method by which the first device obtains the first capability from the local capability library can refer to the method by which the first device obtains the first capability from the shared capability library, and will not be elaborated here.

[0234] Implementation method B2 includes Figure 5 The following steps are shown:

[0235] S501, the first device determines at least one subtask corresponding to the target task.

[0236] This application provides two possible implementation methods for determining at least one subtask corresponding to a target task.

[0237] In a first possible implementation, the first device splits the target task into at least one sub-task.

[0238] The second possible implementation includes Figure 6 The following steps are shown:

[0239] S601, the first device sends a first message to the second device; correspondingly, the second device receives the first message from the first device.

[0240] In this embodiment of the application, the first message includes a target task, and the first message is used to request at least one subtask corresponding to the target task, or the first message is used to indicate that at least one subtask corresponding to the target task is obtained.

[0241] Optionally, the first message may also include a first constraint condition. A detailed description of the first constraint condition will not be repeated here.

[0242] Optionally, the first message may also include information about a third capability, wherein the information about the third capability may be provided by a local capability library and / or a shared capability library corresponding to the first device.

[0243] In one possible implementation, the information of the third capability includes at least one of the following:

[0244] 1) Identification of the third capability;

[0245] 2) Description of the third ability: The description of the third ability is used to describe the function of the third ability;

[0246] 3) The sharing method of the third capability: The sharing method of the third capability is used to indicate the presentation method of the third capability;

[0247] 4) Parameter information of the third capability, which is used to indicate the input parameters required to use the third capability and / or to indicate the output parameters of the third capability;

[0248] 5) Environmental dependency information of the third capability: The environmental dependency information of the third capability is used to indicate the environmental information on which the third capability depends;

[0249] 6) Execution time of the third capability: The execution time of the third capability is used to indicate the time required to execute the third capability;

[0250] 7) Execution cost of the third capability: The execution cost of the third capability is used to indicate the cost required to use the third capability;

[0251] 8) The calling interface for the third capability is used to implement the functionality of the third capability;

[0252] 9) The source code of the third ability, which is used to implement the functionality of the third ability;

[0253] 10) Source code licensing policy for third capabilities. The source code licensing policy for third capabilities is used to indicate whether the source code of third capabilities can be modified / inherited / derived and / or whether other capabilities generated based on the source code of third capabilities need to be added to the shared capability library.

[0254] It should be understood that a detailed description of the information regarding the aforementioned third capability can be found in the detailed description of the capabilities in the shared capability library mentioned earlier, and will not be repeated here.

[0255] This application provides a method for a first device to acquire information about a third capability, including, for example... Figure 7 The following steps are shown:

[0256] S701, the first device sends a second message to the capability library; correspondingly, the capability library receives the second message from the first device.

[0257] In this embodiment of the application, the second message includes a target task, and the second message is used to request information about the capabilities corresponding to the target task, or the second message is used to instruct the acquisition of information about the capabilities corresponding to the target task.

[0258] In this embodiment, the capability library includes a local capability library and / or a shared capability library corresponding to the first device. The local capability library corresponding to the first device can only connect to the account corresponding to that first device, and can increase or decrease the account balance in that account. The shared capability library can connect to multiple accounts corresponding to the first devices, and can increase or decrease the account balance in multiple accounts corresponding to the first devices.

[0259] S702, the capability library determines information about the third capability.

[0260] In this embodiment, the method for determining the third capability in S702 can refer to the method for determining the first capability in S402, and will not be described in detail here.

[0261] S703, the capability library sends information about the third capability to the first device; correspondingly, the first device receives information about the third capability from the capability library.

[0262] It should be understood that if the information of the third capability sent by the capability library to the first device includes the calling interface of the third capability or the source code of the third capability, the capability library may deduct the execution cost of the third capability from the account corresponding to the first device based on the execution cost of the third capability.

[0263] pass Figure 7 The method shown allows the first device to quickly determine the information of the third capability, which facilitates subsequent sub-task planning for the target task based on the information of the third capability.

[0264] In the above S601, the first device can generate the first message through any one of the following embodiments D1, D2, D3 or D4.

[0265] In implementation method D1, the first device can directly add the target task to the first message, or it can first process the target task with prompt words to obtain prompt information, and then add the prompt information to the first message. The prompt information generated by the first device each time it processes the target task with prompt words can be exactly the same or partially the same, which is not limited here.

[0266] For example, if the target task is "help me predict the future weather in Nanjing", the first device can directly add the target task to the first message, so the first message can directly include the information "help me predict the future weather in Nanjing"; or, the first device can first process the target task with prompt words to obtain prompt information such as "You are a weather forecast intelligent assistant, your target task is to predict the weather in Nanjing for the next month, please provide the sub-task plan for this target task", and then the first device adds the prompt information to the first message, so the first message can include the information "You are a weather forecast intelligent assistant, your task is to predict the weather in Nanjing for the next month, please provide the sub-task plan for this target task".

[0267] In implementation method D2, the first device can directly add the target task and the first constraint to the first message, or it can first process the target task and the first constraint with prompt words to obtain prompt information, and then add the prompt information to the first message.

[0268] For example, if the objective task is "help me predict the future weather in Nanjing", the first constraints include "must be completed within 30 seconds", "cannot consume more than 100 points", and "the prediction result is displayed in the form of charts and text". The first device can directly add the objective task and the first constraints to the first message. Therefore, the first message can include the following: "Objective task: help me predict the future weather in Nanjing; First constraints: must be completed within 30 seconds, cannot consume more than 100 points, and the prediction result is displayed in the form of charts and text".

[0269] Alternatively, the first device can first process the target task and the first constraint condition with prompt words to obtain prompt information such as "You are a weather forecast intelligent assistant. Your target task is to predict the weather in Nanjing for the next month. Your constraint condition is to complete it within 30 seconds, and the points consumed this time must not exceed 100. The prediction result must be displayed in the form of charts and text. Please provide a sub-task plan for this target task." The first device then adds the prompt information to the first message, which may include the above prompt information.

[0270] In implementation method D3, the first device can also directly add the target task and third capability information to the first message, or it can first process the target task and third capability information with prompt words to obtain prompt information, and then add the prompt information to the first message.

[0271] For example, if the target task is "help me predict the future weather in Nanjing", the information of the third capability includes the identifiers of three usable third capabilities: "web search capability", "web reading capability", and "file reading and writing capability". The first device can directly add the target task and the information of the third capability to the first message. Therefore, the first message may include the following: "Target task: help me predict the future weather in Nanjing; information of the third capability: web search capability, web reading capability, and file reading and writing capability".

[0272] Alternatively, the first device can first process the information of the target task and the third capability with prompt words to obtain prompt information such as "You are a weather forecast intelligent assistant. Your target task is to predict the weather in Nanjing for the next month. The capabilities you can access include web search, web reading, and file reading and writing. Please provide a sub-task plan for this target task." The first device then adds the prompt information to the first message, which may include the above prompt information.

[0273] In implementation method D4, the first device can directly add the target task, the first constraint, and the third capability information to the first message, or it can first process the target task, the first constraint, and the third capability information with prompt words to obtain prompt information, and then add the prompt information to the first message.

[0274] For example, the objective task is "Help me predict the future weather in Nanjing." The first constraint includes "must be completed within 30 seconds," "cannot consume more than 100 points," and "the prediction result is displayed in the form of charts and text." The third capability information includes the identifiers of three usable third capabilities: "web search capability," "web page reading capability," and "file read and write capability." The first device can directly add the objective task, the first constraint, and the third capability information to the first message. Therefore, the first message can include the following: "Objective task: Help me predict the future weather in Nanjing; First constraint: must be completed within 30 seconds, cannot consume more than 100 points, and the prediction result is displayed in the form of charts and text; Third capability information: web search capability, web page reading capability, and file read and write capability."

[0275] Alternatively, the first device can first process the information of the target task, the first constraint, and the third capability with prompt words to obtain prompt information such as "You are a weather forecast intelligent assistant. Your target task is to predict the weather in Nanjing for the next month. Your constraint is to complete the task within 30 seconds, and the points consumed must not exceed 100. The prediction results must be displayed in the form of charts and text. Please provide a sub-task plan for this target task. The capabilities you can call are web search capability, web page reading capability, and file reading and writing capability. Please provide a sub-task plan for this target task." The first device then adds the prompt information to the first message, which may include the above prompt information.

[0276] S602, the second device determines at least one subtask corresponding to the target task.

[0277] In the embodiments of this application, for four different implementations of generating the first message, the second device can determine at least one subtask corresponding to the target task through any one of the following implementations E1, E2, E3 or E4.

[0278] In implementation E1, if the first message includes a target task or a prompt message generated based on the target task, the second device can input the target task into the large language model after obtaining the target task in the first message, and the large language model can output at least one subtask.

[0279] For example, if the first message includes "You are a weather forecasting intelligent assistant, and your task is to predict the weather in Nanjing for the next month. Please provide a sub-task plan for this objective task," the second device can determine the following four sub-tasks:

[0280] 1) Get a list of weather web pages;

[0281] 2) Retrieve the Nanjing weather webpage from the list of weather webpages;

[0282] 3) Retrieve Nanjing's weather information for the next 15 days from the Nanjing Weather website;

[0283] 4) Based on the weather information for Nanjing in the next 15 days, predict the weather information for Nanjing in the next month.

[0284] It should be understood that the execution result obtained after at least one subtask is executed in sequence is equivalent to the execution result obtained after the target task is executed.

[0285] In the above implementation method E1, the large language model directly determines at least one subtask based on the target task, which can generate at least one subtask quickly and efficiently, thus improving the efficiency of subtask generation.

[0286] In implementation E2, when the first message includes a target task and a first constraint or a prompt message generated based on the target task and the first constraint, the second device, after obtaining the target task and the first constraint in the first message, can input the target task and the first constraint into a large language model, and the large language model can output at least one subtask and a second constraint corresponding to each subtask. The second constraint corresponding to each subtask is determined according to the first constraint corresponding to the target task.

[0287] In this embodiment of the application, at least one subtask includes a first subtask. The first subtask can be any of the at least one subtask. Taking the second constraint corresponding to the first subtask as an example, the second constraint corresponding to the first subtask is explained in detail below. The second constraint corresponding to the first subtask can satisfy at least one of the following:

[0288] 1) The second constraint is used to constrain the execution time of the first subtask.

[0289] In this embodiment of the application, the execution time of the first subtask is determined based on the execution time of the target task.

[0290] This application provides two possible implementation methods for determining the execution time of the first subtask.

[0291] In the first possible implementation, the execution time of the first subtask can be determined based on the execution time of the target task and the number of subtasks. That is, the execution time of the first subtask is equal to the ratio of the execution time of the target task to the number of subtasks.

[0292] For example, if the first constraint includes a maximum execution time of 30 seconds for the target task, and the second device splits the target task into three sub-tasks, then the maximum execution time for each sub-task is 10 seconds.

[0293] In the second possible implementation, the execution time of the first subtask can be determined based on the execution time of the target task and the complexity of the first subtask. The complexity of the first subtask can be determined by the large language model in the second device.

[0294] For example, if the first constraint includes a time limit of 30 seconds for the execution of the target task, the second device splits the target task into three subtasks: subtask 1, subtask 2, and subtask 3. Subtask 1 and subtask 2 have higher complexity, while subtask 3 has lower complexity. Therefore, the time limit for the execution of subtask 1 is 12 seconds, the time limit for the execution of subtask 2 is 12 seconds, and the time limit for the execution of subtask 1 is 6 seconds.

[0295] 2) The second constraint is used to constrain the execution cost of the first subtask.

[0296] In this embodiment of the application, the execution cost of the first subtask is determined based on the execution cost of the target task.

[0297] This application provides two possible implementation methods for determining the execution cost of the first subtask.

[0298] In the first possible implementation, the execution cost of the first subtask can be determined based on the execution cost of the target task and the number of subtasks. That is, the execution cost of the first subtask is equal to the ratio of the execution cost of the target task to the number of subtasks.

[0299] In the second possible implementation, the execution cost of the first subtask can be determined based on the execution cost of the target task and the complexity of the first subtask. The complexity of the first subtask can be determined by the large language model in the second device.

[0300] 3) The second constraint is used to constrain the execution result of the first subtask.

[0301] In this embodiment of the application, the execution result of the first subtask is determined based on the execution result of the target task.

[0302] When the first subtask is the last subtask corresponding to the target task, the form information of the execution result of the first subtask is the same as the form information of the execution structure of the target task.

[0303] 4) The second constraint is used to constrain the execution environment of the first subtask.

[0304] In this embodiment of the application, the execution environment of the target task can be used as the execution environment of the first subtask.

[0305] For example, if the first message includes the message "You are a weather forecasting intelligent assistant. Your goal is to predict the weather in Nanjing for the next month. Your constraints are that you must complete the task within 30 seconds, and the points consumed must not exceed 100. The prediction results must be presented in the form of charts and text. Please provide a sub-task plan for this goal," the second device can determine the following 7 sub-tasks:

[0306] 1) Obtain a list of weather web pages; the corresponding second constraint is that it must be completed within 2 seconds and the points consumed must not exceed 10.

[0307] 2) Read the Nanjing weather webpage from the list of weather webpages; the corresponding second constraint is that it must be completed within 2 seconds and the points consumed must not exceed 15.

[0308] 3) Retrieve the weather information for Nanjing for the next 15 days from the Nanjing Weather website; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0309] 4) Based on the weather information of Nanjing for the next 15 days, predict the weather information of Nanjing for the next month; the corresponding second constraint is that it must be completed within 10 seconds and the points consumed must not exceed 30.

[0310] 5) Plot the weather information for Nanjing for the next month as a curve; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0311] 6) Summarize the weather information for Nanjing for the next month in text; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0312] 7) Write the curve chart and text summary of Nanjing's weather information for the next month into a file and save it; the corresponding second constraint is that it must be completed within 1 second and the points consumed must not exceed 5.

[0313] In the above implementation method E2, the large language model determines at least one subtask based on the target task and the first constraint condition, and each of the determined at least one subtask has a corresponding second constraint condition, which facilitates the subsequent determination of the capability corresponding to each subtask based on the second constraint condition corresponding to each subtask.

[0314] In implementation method E3, when the first message includes information about the target task and the third capability, or a prompt message generated based on the information about the target task and the third capability, the second device, after obtaining the information about the target task and the third capability from the first message, can input the information about the target task and the third capability into a large language model, and the large language model can output at least one subtask. Specifically, the large language model performs subtask planning on the target task with reference to the information about the third capability to obtain at least one subtask, and some or all of the subtasks in the at least one subtask can be executed through the third capability.

[0315] For example, if the first message includes "You are a weather forecasting intelligent assistant, and your goal is to predict the weather in Nanjing for the next month. You have access to web search, web page reading, and file read / write capabilities. Please provide a subtask plan for this goal," the second device can determine the following four subtasks:

[0316] 1) Get a list of weather web pages;

[0317] 2) Retrieve the Nanjing weather webpage from the list of weather webpages;

[0318] 3) Retrieve Nanjing's weather information for the next 15 days from the Nanjing Weather website;

[0319] 4) Based on the weather information for Nanjing in the next 15 days, predict the weather information for Nanjing in the next month.

[0320] Of the four sub-tasks determined by the second device, the sub-task of "obtaining a list of weather web pages" can be executed through the web search capability in the third capability, the sub-task of "reading Nanjing weather web pages from the list of weather web pages" can be executed through the web page reading capability in the third capability, and the sub-task of "reading Nanjing's weather information for the next 15 days from Nanjing weather web pages" can be executed through the file read and write capability in the third capability.

[0321] In the above implementation method E3, the large language model refers to the information of the third capability to perform subtask planning on the target task to obtain at least one subtask, which makes it convenient to directly use the third capability to execute the subtask in the future. This can avoid retrieving the capability corresponding to the subtask from the capability library or generating capability for each subtask, which is beneficial to improving the efficiency of executing subtasks.

[0322] In implementation E4, when the first message includes information about the target task, the first constraint, and the third capability, or a prompt message generated based on the information about the target task, the first constraint, and the third capability, the second device, after obtaining the information about the target task, the first constraint, and the third capability from the first message, can input the information about the target task, the first constraint, and the third capability into a large language model. The large language model then outputs at least one subtask and a second constraint corresponding to each subtask. The at least one subtask is obtained by the large language model through subtask planning of the target task with reference to the information about the third capability. The second constraint corresponding to each subtask is determined based on the first constraint corresponding to the target task.

[0323] For example, if the first message includes the message "You are a weather forecasting intelligent assistant. Your goal is to predict the weather in Nanjing for the next month. Your constraints are that you must complete the task within 30 seconds, and the points consumed must not exceed 100. The prediction results must be displayed in the form of charts and text. You can access web search, web page reading, and file reading and writing capabilities. Please provide a subtask plan for this goal," the second device can determine the following 7 subtasks:

[0324] 1) Obtain a list of weather web pages; the corresponding second constraint is that it must be completed within 2 seconds and the points consumed must not exceed 10.

[0325] 2) Read the Nanjing weather webpage from the list of weather webpages; the corresponding second constraint is that it must be completed within 2 seconds and the points consumed must not exceed 15.

[0326] 3) Retrieve the weather information for Nanjing for the next 15 days from the Nanjing Weather website; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0327] 4) Based on the weather information of Nanjing for the next 15 days, predict the weather information of Nanjing for the next month; the corresponding second constraint is that it must be completed within 10 seconds and the points consumed must not exceed 30.

[0328] 5) Plot the weather information for Nanjing for the next month as a curve; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0329] 6) Summarize the weather information for Nanjing for the next month in text; the corresponding second constraint is that it must be completed within 5 seconds and the points consumed must not exceed 20.

[0330] 7) Write the curve chart and text summary of Nanjing's weather information for the next month into a file and save it; the corresponding second constraint is that it must be completed within 1 second and the points consumed must not exceed 5.

[0331] In the above implementation method E4, the large language model determines at least one subtask based on the target task, the first constraint, and the third capability information, so that the third capability can be directly used to execute the subtask in the future. Each of the determined subtasks has a corresponding second constraint, so that the capability corresponding to each subtask can be determined in the future based on the second constraint corresponding to each subtask.

[0332] Optionally, after determining at least one subtask corresponding to the target task, the second device can also obtain the second capability corresponding to at least one subtask by accessing the capability library.

[0333] It should be understood that at least one subtask contains one or more subtasks whose corresponding second capabilities come from the shared capability library, which will not be elaborated on later.

[0334] S603, the second device sends at least one subtask to the first device; correspondingly, the first device receives at least one subtask from the second device.

[0335] Optionally, if the second device acquires at least one subtask and the second capability corresponding to each subtask, the second device may send the at least one subtask and the second capability corresponding to each subtask to the first device. Correspondingly, the first device receives the at least one subtask and the second capability corresponding to each subtask from the second device. Afterward, the first device does not need to execute S502 and subsequent steps. In the above method, the second device can acquire at least one subtask and the second capability corresponding to each subtask and send them to the first device, which helps improve the efficiency of acquiring the second capability.

[0336] exist Figure 6 In the above method, the efficiency of obtaining at least one subtask corresponding to the target task can be improved by determining the at least one subtask through the second device, and the at least one subtask determined by the large language model in the second device is more accurate and reasonable.

[0337] Through the steps in S501, after the first device determines at least one subtask corresponding to the target task, the first device can first determine whether there is a third capability that can be used to execute the subtask based on the information of the third capability. If it exists, the third capability is used directly to execute the subtask; if it does not exist, the capability corresponding to the subtask is obtained from the local capability library and / or shared capability library of the first device.

[0338] For ease of description, the following explanation will use the example of the first device obtaining the capability corresponding to the subtask from the shared capability library. Obtaining the capability corresponding to the subtask from the local capability library of the first device can be referred to the example of obtaining the capability corresponding to the subtask from the shared capability library, and will not be repeated hereafter.

[0339] S502, the first device obtains at least one second capability corresponding to each subtask from the shared capability library.

[0340] In the embodiments of this application, the first capability includes at least one second capability corresponding to each subtask. It can be understood that the execution result obtained by executing a subtask using the second capability corresponding to at least one subtask is equivalent to the execution result obtained by executing the target task using the first capability.

[0341] In the above S502, the first device can be via, as follows: Figure 8 The steps shown illustrate how to obtain the second capability corresponding to at least one subtask. The following explanation uses the first subtask among the at least one subtasks as an example to illustrate how to obtain the second capability corresponding to the first subtask, where the first subtask is any one of the at least one subtasks.

[0342] S801, the first device sends a third message to the second device; correspondingly, the second device receives the third message from the first device.

[0343] In this embodiment of the application, the third message includes a first subtask, and the third message is used to request the identifier of the second capability corresponding to the first subtask, or the third message is used to indicate obtaining the identifier of the second capability corresponding to the first subtask.

[0344] Optionally, the third message may also include a second constraint corresponding to the first subtask. A detailed description of the second constraint will not be repeated here.

[0345] Optionally, the third message may also include information indicating one or more of the following: a subtask executed before the first subtask, the result of a subtask executed before the first subtask, or the target task. This information may be used to identify the second capability corresponding to the first subtask.

[0346] Optionally, the third message may also include information about a fourth capability corresponding to the first subtask. This fourth capability information is used to determine the identifier of the second capability corresponding to the first subtask. The fourth capability information may be provided by the local capability library and / or shared capability library corresponding to the first device. A description of the fourth capability information can be found in the description of the third capability information, and will not be repeated here.

[0347] For ease of description, the following explanation will use the example of the fourth capability information coming from the shared capability library. Obtaining the fourth capability information from the local capability library corresponding to the first device can be referred to as obtaining the fourth capability information from the shared capability library, and will not be repeated hereafter.

[0348] This application provides a method for a first device to acquire information about a fourth capability, including, for example... Figure 9 The following steps are shown:

[0349] S901, the first device sends a fourth message to the shared capability library; correspondingly, the shared capability library receives the fourth message from the first device.

[0350] In this embodiment of the application, the fourth message includes a first subtask, and the fourth message is used to request information about the capability corresponding to the first subtask, or the fourth message is used to indicate the acquisition of information about the capability corresponding to the first subtask.

[0351] S902, the shared capability library determines information about the fourth capability.

[0352] In this embodiment of the application, the method for determining the information of the fourth capability in S902 can refer to the method for determining the information of the third capability in S702, and will not be described in detail here.

[0353] S903, the shared capability library sends information about the fourth capability to the first device; correspondingly, the first device receives information about the fourth capability from the shared capability library.

[0354] It should be understood that if the information of the fourth capability sent by the shared capability library to the first device includes the calling interface of the fourth capability or the source code of the fourth capability, the shared capability library may deduct the execution cost of the fourth capability from the account corresponding to the first device based on the execution cost of the fourth capability.

[0355] pass Figure 9 The method shown allows the first device to quickly determine the information of the fourth capability, which facilitates the subsequent determination of the second capability corresponding to the first subtask based on the information of the fourth capability.

[0356] In one possible implementation, the first device... Figure 9 The method shown, after obtaining the information of the fourth capability, can retrieve the identifier of the second capability corresponding to the first subtask from the information of the fourth capability, and retrieve the second capability corresponding to the first subtask from the shared capability library based on the identifier of the second capability corresponding to the first subtask, without needing to go through... Figure 8 The methods in S802 to S805 are used to obtain the second capability corresponding to the first subtask. The second capability corresponding to the first subtask can be determined quickly and accurately using these methods.

[0357] In S801 above, the third message generated by the first device can include four possible implementations. The way the first device generates the third message can refer to the way the first device generates the first message, and will not be described in detail here.

[0358] S802, the second device determines the identifier of the second capability corresponding to the first subtask.

[0359] In the embodiments of this application, the second device can determine the identifier of the second capability at least through any one of the following embodiments F1, F2, F3, F4 or F5.

[0360] In implementation F1, if the third message includes the first subtask, the second device can input the first subtask into the large language model, and the large language model can output the identifier of the second capability.

[0361] Generally, after acquiring the first subtask, a large language model can search for capabilities in the capability library based on the first subtask, and then determine the identifier of the second capability corresponding to the first subtask.

[0362] In implementation F2, when the third message includes a first subtask and a second constraint corresponding to the first subtask, the second device can input the first subtask and the second constraint into the large language model, and the large language model can output the identifier of the second capability.

[0363] Generally, after obtaining the first subtask and the second constraint, the large language model can search for capabilities in the capability library based on the first subtask and the second constraint, and then determine the identifier of the second capability corresponding to the first subtask. The determined second capability corresponding to the first subtask satisfies the second constraint.

[0364] In implementation F3, when the third message includes information about the first subtask and the fourth capability, the second device can input the information about the first subtask and the fourth capability into the large language model, and the large language model can output the identifier of the second capability.

[0365] Generally, after obtaining information about the first subtask and the fourth capability, a large language model can look up information about the fourth capability based on the first subtask and determine the identifier of the second capability corresponding to the first subtask from the information about the fourth capability.

[0366] In implementation F4, when the third message includes information about the first subtask, the second constraint corresponding to the first subtask, and the fourth capability, the second device can input the information about the first subtask, the second constraint corresponding to the first subtask, and the fourth capability into the large language model, and the large language model can output the identifier of the second capability.

[0367] Generally, after obtaining information about the first subtask, the second constraint, and the fourth capability, the large language model can look up the information about the fourth capability based on the first subtask and the second constraint, determine the identifier of the second capability corresponding to the first subtask from the information of the fourth capability, and the determined second capability corresponding to the first subtask satisfies the second constraint.

[0368] In implementation F5, if the third message includes information about the first subtask, the second constraint, the fourth capability, the target task, the subtask preceding the first subtask, and the execution result of the subtask preceding the first subtask, the second device can input the above information in the third message into the large language model, and the large language model can output the identifier of the second capability.

[0369] Generally, after obtaining information about the first subtask, the second constraint, the fourth capability, the target task, the subtasks preceding the first subtask, and the execution results of the subtasks preceding the first subtask, the large language model can search for information about the fourth capability based on the execution results of the first subtask, the second constraint, the target task, the subtasks preceding the first subtask, and the subtasks preceding the first subtask. From the information about the fourth capability, it can determine the identifier of the second capability corresponding to the first subtask, and the determined second capability corresponding to the first subtask satisfies the second constraint.

[0370] If the large language model cannot determine the identifier of the second capability corresponding to the first subtask through the above five implementation methods, the large language model can also generate the second capability corresponding to the first subtask and send the second capability corresponding to the first subtask to the first device for the first device to use the second capability to execute the first subtask. For ease of description in the following text, the following explanation will assume that the large language model can determine the identifier of the second capability corresponding to the first subtask.

[0371] S803, the second device sends the identifier of the second capability corresponding to the first subtask to the first device; correspondingly, the first device receives the identifier of the second capability corresponding to the first subtask from the second device.

[0372] In this embodiment of the application, after the first device obtains the identifier of the second capability corresponding to the first subtask through the steps in S803 above, it can obtain the second capability corresponding to the first subtask through any of the following implementation methods G1 or G2.

[0373] In implementation method G1, the first device obtains the second capability corresponding to the first sub-task from the information of the fourth capability based on the identifier of the second capability corresponding to the first sub-task.

[0374] In this embodiment of the application, if the information of the fourth capability includes the calling interface of the fourth capability or the source code of the fourth capability, and the first device determines that the information of the fourth capability includes the identifier of the second capability corresponding to the first subtask, then the first device can directly use the calling interface of the fourth capability or the source code of the fourth capability in the information of the fourth capability as the second capability corresponding to the first subtask.

[0375] Through the above-described implementation method G1, the first device can obtain the second capability for performing the first subtask from the information of the fourth capability without having to access the capability library again, which helps to improve the efficiency of obtaining the second capability.

[0376] Implementation method G2 includes the following steps as shown in S804 and S805:

[0377] S804, the first device sends a fifth message to the shared capability library; correspondingly, the shared capability library receives the fifth message from the first device.

[0378] In this embodiment of the application, the fifth message may include an identifier of the second capability corresponding to the first subtask. The fifth message is used to request the second capability corresponding to the first subtask, or the fifth message is used to indicate that the second capability corresponding to the first subtask is obtained.

[0379] Optionally, the fifth message may also include the identifier of the first device.

[0380] Optionally, the fifth message may also include authorization information for the second capability corresponding to the first subtask, wherein the authorization information for the second capability corresponding to the first subtask is used to instruct the first device to obtain the second capability corresponding to the first subtask. The authorization information may be in the form of a key, token, etc., and is not limited thereto.

[0381] In this embodiment of the application, the first device can be used as follows: Figure 10 The following steps are shown to obtain the authorization information for the second capability corresponding to the first subtask.

[0382] S1001, the first device sends a sixth message to the third device; correspondingly, the third device receives the sixth message from the first device.

[0383] In this embodiment of the application, the sixth message may include the identifier of the second capability corresponding to the first subtask. The sixth message is used to request authorization information of the second capability corresponding to the first subtask, or the sixth message is used to indicate obtaining authorization information of the second capability corresponding to the first subtask.

[0384] It should be understood that after the first device obtains the identifier of the second capability corresponding to the first subtask through S803, it can execute the command. Figure 10 The steps shown are to obtain the authorization information for the second capability corresponding to the first subtask.

[0385] Optionally, the sixth message may also include the identifier of the first device.

[0386] In this embodiment of the application, the third device is a device for providing authorization information of capabilities.

[0387] The third device can be a CP (Capability Provider), which can store the capabilities it provides, capability information, capability authorization information, the scope of authorization, and the scope of permissions, etc., without limitation here. The scope of authorization includes the identifier of the first device that can use the capability; the scope of permissions includes whether the source code of the capability can be obtained, and / or whether the source code of the capability can be modified / inherited / derived, etc.

[0388] The third device can be an authentication authorization center (AAC). The AAC can provide authorization information for capabilities through a shared capability library or by providing it itself. When the AAC provides the authorization information, it can store the capability's authorization information, authorization scope, and permission scope, etc., without further limitation. The capability's authorization information, authorization scope, and permission scope in the AAC can come from the CP (Content Provider) or from the shared capability library.

[0389] S1002, the third device determines whether to send authorization information for the second capability corresponding to the first sub-task to the first device based on the identifier of the second capability corresponding to the first sub-task.

[0390] In the embodiments of this application, depending on whether the third device is a CP or an AAC, the third device can adopt different implementation methods to determine whether to send the authorization information of the second capability corresponding to the first subtask to the first device.

[0391] When the third device is a CP, the third device can determine whether to send authorization information of the second capability corresponding to the first subtask to the first device through any of the following implementation methods K1 or K2.

[0392] In implementation method K1, after obtaining the identifier of the second capability corresponding to the first subtask, the CP determines to send the authorization information of the second capability corresponding to the first subtask to the first device.

[0393] In the above-described implementation K1, any first device can obtain the authorization information of the second capability corresponding to the first subtask from the CP, which is beneficial for the widespread use and sharing of capabilities.

[0394] In implementation method K2, the CP can first determine the authorization scope of the second capability corresponding to the first sub-task based on the identifier of the second capability corresponding to the first sub-task. If the identifier of the first device is within the authorization scope of the second capability corresponding to the first sub-task, then the CP determines to send the authorization information of the second capability corresponding to the first sub-task to the first device.

[0395] In the above-described implementation K2, the CP determines whether to send authorization information for the second capability corresponding to the first sub-task to the first device based on whether the first device is within the authorization scope of the second capability corresponding to the first sub-task, which can effectively ensure the reasonable issuance of authorization information.

[0396] After obtaining the authorization information of the second capability corresponding to the first subtask through implementation method K1 or implementation method K2, the CP can also determine the scope of permission of the second capability corresponding to the first subtask based on the identifier of the second capability corresponding to the first subtask. If the identifier of the first device is within the scope of permission of the second capability corresponding to the first subtask, it means that the first device can obtain the source code of the second capability corresponding to the first subtask, and / or the first device can modify / inherit / derive the source code of the second capability corresponding to the first subtask, and use the above information as the permission information of the second capability corresponding to the first subtask.

[0397] When the third device is AAC, the third device can determine whether to send authorization information of the second capability corresponding to the first subtask to the first device through any of the following implementations L1, L2 or L3.

[0398] In implementation L1, after obtaining the identifier of the second capability corresponding to the first subtask, AAC determines to send the authorization information of the second capability corresponding to the first subtask to the first device.

[0399] In the above-described implementation L1, the authorization information of the second capability corresponding to the first subtask sent by the AAC to the first device can come from the AAC itself. That is, the AAC can obtain the authorization information of the second capability corresponding to the first subtask from its own stored capability authorization information. Alternatively, the authorization information of the second capability corresponding to the first subtask sent by the AAC to the first device can come from a shared capability library. That is, the AAC sends the identifier of the second capability corresponding to the first subtask to the shared capability library, and the shared capability library can obtain the authorization information of the second capability corresponding to the first subtask from the shared capability library based on the identifier of the second capability corresponding to the first subtask, and then send the authorization information of the second capability corresponding to the first subtask to the AAC.

[0400] In the above implementation L1, any first device can obtain the authorization information of the second capability corresponding to the first subtask from the AAC, which is beneficial to the widespread use and sharing of capabilities.

[0401] In implementation L2, the AAC can first determine the authorization scope of the second capability corresponding to the first sub-task based on the identifier of the second capability corresponding to the first sub-task. If the identifier of the first device is within the authorization scope of the second capability corresponding to the first sub-task, then it is determined to send the authorization information of the second capability corresponding to the first sub-task to the first device.

[0402] In the above implementation L2, the authorization information of the second capability corresponding to the first subtask sent by AAC to the first device can come from AAC or from the shared capability library, which will not be elaborated here.

[0403] In the above implementation L2, AAC determines whether to send authorization information of the second capability corresponding to the first sub-task to the first device based on whether the first device is within the authorization scope of the second capability corresponding to the first sub-task, which can effectively ensure the reasonable issuance of authorization information.

[0404] In implementation L3, the AAC can send the identifier of the second capability corresponding to the first subtask and the identifier of the first device to the shared capability library. The shared capability library determines the authorization scope of the second capability corresponding to the first subtask based on the identifier of the second capability corresponding to the first subtask. If the identifier of the first device is within the authorization scope of the second capability corresponding to the first subtask, the shared capability library determines to send the authorization information of the second capability corresponding to the first subtask to the first device, and sends the authorization information of the second capability corresponding to the first subtask to the AAC, which then sends it to the first device.

[0405] In the above implementation L3, the authorization information of the second capability corresponding to the first subtask sent by AAC to the first device can come from the shared capability library.

[0406] In the above implementation method L3, the shared capability library determines whether to send the authorization information of the second capability corresponding to the first sub-task to the first device based on whether the first device is within the authorization scope of the second capability corresponding to the first sub-task, which can effectively ensure the reasonable distribution of authorization information.

[0407] After obtaining the authorization information of the second capability corresponding to the first subtask through implementation method L1, L2, or L3, the AAC can also determine the permission information of the second capability corresponding to the first subtask. The method by which the AAC determines the permission information of the second capability corresponding to the first subtask can be referred to the method by which the CP determines the permission information of the second capability corresponding to the first subtask, and will not be elaborated here. S1003, if the third device determines to send the authorization information of the second capability corresponding to the first subtask to the first device, the third device sends the authorization information of the second capability corresponding to the first subtask to the first device.

[0408] pass Figure 10 The method described above allows the first device to quickly obtain authorization information for the second capability corresponding to the first subtask, which helps to improve the efficiency of obtaining authorization information for the second capability corresponding to the first subtask.

[0409] S805, the shared capability library sends the second capability corresponding to the first subtask to the first device according to the identifier of the second capability corresponding to the first subtask.

[0410] In this embodiment of the application, the shared capability library can determine the second capability corresponding to the first subtask through any one of the following implementation methods N1, N2 or N3.

[0411] In implementation N1, if the fifth message includes an identifier of the second capability corresponding to the first subtask, and if the shared capability library does not need to review the authorization information, the shared capability library can obtain the second capability corresponding to the first subtask based on the identifier and send the second capability corresponding to the first subtask to the first device; if the shared capability library needs to review the authorization information, since the fifth message does not include the authorization information of the second capability corresponding to the first subtask, the shared capability library refuses to send the second capability corresponding to the first subtask to the first device.

[0412] In implementation N2, if the fifth message includes the identifier and authorization information of the second capability corresponding to the first subtask, the shared capability library confirms that the fifth message includes the authorization information of the second capability corresponding to the first subtask, the shared capability library obtains the second capability corresponding to the first subtask according to the identifier, and sends the second capability corresponding to the first subtask to the first device.

[0413] Optionally, before executing implementation method N1 or implementation method N2, the shared capability library may verify the authorization information of the second capability corresponding to the first subtask. If the authorization information is determined to be valid, the shared capability library then executes implementation method N1 or implementation method N2; if the authorization information is determined to be invalid, the shared capability library refuses to send the second capability corresponding to the first subtask to the first device.

[0414] In implementation N3, when the fifth message includes the identifier of the second capability corresponding to the first subtask and the identifier of the first device, the shared capability library determines the authorization scope of the second capability corresponding to the first subtask based on the identifier of the second capability corresponding to the first subtask. If the identifier of the first device is within the authorization scope of the second capability corresponding to the first subtask, the shared capability library can obtain the second capability corresponding to the first subtask based on the identifier and send the second capability corresponding to the first subtask to the first device.

[0415] Furthermore, if the fifth message includes permission information for the second capability corresponding to the first subtask, the second capability corresponding to the first subtask ultimately determined by the shared capability library must satisfy the content of the aforementioned permission information.

[0416] For example, if the permission information for the second capability corresponding to the first subtask includes the ability to access and modify the source code of the second capability corresponding to the first subtask, but not to inherit or derive from the source code of the second capability corresponding to the first subtask, then the permission mechanism for the source code of the second capability corresponding to the first subtask sent by the shared capability library to the first device is: allow use, allow modification, disallow inheritance and derivation. It should be understood that the permission mechanism for the source code of the second capability corresponding to the first subtask is a mechanism set within the source code of the second capability corresponding to the first subtask.

[0417] In one possible implementation, when the shared capability library sends the second capability corresponding to the first subtask to the first device, it can also obtain the execution cost of the second capability corresponding to the first subtask from the information of the second capability corresponding to the first subtask, and deduct the execution cost of the second capability corresponding to the first subtask from the account corresponding to the first device. The shared capability library can also add the deducted execution cost of the second capability corresponding to the first subtask to the account corresponding to the first device that provided the second capability corresponding to the first subtask.

[0418] Through the above-described implementation G2, the first device can obtain a second capability from the shared capability library for performing the first subtask.

[0419] Through the above-described implementation method B2, when the first device cannot directly obtain the first capability corresponding to the target task, the first device can divide the target task into at least one sub-task, and obtain the second capability corresponding to the sub-task to achieve the purpose of obtaining the first capability. Therefore, the above process can achieve the purpose of obtaining the first capability. S303, the first device uses the first capability to execute the target task.

[0420] When the first capability is an interface-sharing method, the first device calls the calling interface of the first capability in order to perform the target task using the first capability. The calling interface of the first capability can be provided by a shared capability library or CP.

[0421] When the first capability is a source code sharing method, after the first device obtains the source code of the first capability, it executes the target task by using the source code of the first capability.

[0422] pass Figure 3 The method shown allows different first devices to obtain the first capability corresponding to the target task from the shared capability library when processing similar target tasks, and to use the first capability to execute the target task and obtain the execution result, instead of each processing the target task and generating its own capability to execute the target task. This process can reduce unnecessary homogenization operations, which helps to reduce the time spent in the task processing process and improve the task processing efficiency of the first device.

[0423] pass Figure 3 After the method shown uses the first capability to perform the target task, the first device can... Figure 3 The capabilities generated in the method shown are added to the shared capability library and / or the local capability library corresponding to the first device. The following explanation uses the example of the first device adding the generated capabilities to the shared capability library. Figure 11 The following steps are shown.

[0424] Optionally, Figure 11 The method includes S1101.

[0425] S1101, the first device determines a fifth capability based on the second capabilities corresponding to the multiple sub-tasks in at least one sub-task. The fifth capability is used to achieve the target task or a portion thereof.

[0426] In this application embodiment, the first device can determine the fifth capability through any one of the following implementations P1 or P2.

[0427] In implementation method P1, the first device can generate a fifth capability based on the capabilities corresponding to multiple subtasks in at least one subtask. The generated fifth capability can realize multiple subtasks.

[0428] Through the above-described implementation method P1, the first device can quickly generate the fifth capability, which is beneficial to improving the efficiency of generating new capabilities.

[0429] Implementation method P2 includes, for example: Figure 12 The following steps are shown:

[0430] S1201, the first device sends an eighth message to the second device; correspondingly, the second device receives the eighth message from the first device.

[0431] In this embodiment of the application, the eighth message may include second capabilities corresponding to multiple subtasks in at least one subtask, and the eighth message is used to instruct the generation of a capability based on the capabilities corresponding to multiple subtasks in at least one subtask.

[0432] S1202, the second device sends the fifth capability to the first device; correspondingly, the first device receives the fifth capability from the second device.

[0433] In this embodiment of the application, after the second device obtains the second capabilities corresponding to the multiple subtasks in the eighth message, it inputs the second capabilities corresponding to the multiple subtasks into the large language model, and the large language model outputs the fifth capability and sends the fifth capability to the first device.

[0434] In the above-described implementation P2, the fifth capability is generated by the large language model in the second device, rather than by the first device, which reduces the power consumption of the first device. Furthermore, the fifth capability generated by the large language model is more complete and reasonable.

[0435] S1102, the first device sends the seventh message to the shared capability library.

[0436] In this application embodiment, the seventh message may include any one of the following implementations Q1 or Q2.

[0437] In implementation Q1, the seventh message includes a second capability corresponding to any one of the subtasks in at least one subtask. The seventh message is used to indicate that the second capability corresponding to any one of the subtasks be added to the shared capability library.

[0438] Optionally, if the seventh message includes the second capability corresponding to the first subtask, the seventh message may also include at least one of the following:

[0439] 1) Identification of the first device;

[0440] 2) Description information of the second capability corresponding to the first subtask. The description information of the second capability corresponding to the first subtask is used to describe the function of the second capability corresponding to the first subtask.

[0441] 3) The sharing method of the second capability corresponding to the first subtask. The sharing method of the second capability corresponding to the first subtask is used to indicate the presentation method of the second capability corresponding to the first subtask.

[0442] 4) Parameter information of the second capability corresponding to the first subtask. The parameter information of the second capability corresponding to the first subtask is used to indicate the input parameters required to use the second capability corresponding to the first subtask and / or to indicate the output parameters of the second capability.

[0443] 5) Environmental dependency information of the second capability corresponding to the first subtask. The environmental dependency information of the second capability corresponding to the first subtask is used to indicate the environmental information on which the second capability corresponding to the first subtask depends.

[0444] 6) Execution time of the second capability corresponding to the first subtask. The execution time of the second capability corresponding to the first subtask is used to indicate the time required to execute the second capability corresponding to the first subtask.

[0445] 7) The execution cost of the second capability corresponding to the first subtask. The execution cost of the second capability corresponding to the first subtask is used to indicate the cost required to use the second capability corresponding to the first subtask.

[0446] 8) The calling interface for the second capability corresponding to the first subtask is used to implement the function of the second capability corresponding to the first subtask;

[0447] 9) The source code of the second capability corresponding to the first subtask. The source code of the second capability corresponding to the first subtask is used to implement the function of the second capability corresponding to the first subtask.

[0448] 10) Source code licensing policy for the second capability corresponding to the first subtask. The source code licensing policy for the second capability corresponding to the first subtask is used to indicate whether the source code of the second capability corresponding to the first subtask is allowed to be modified / inherited / derived and / or whether other capabilities generated based on the source code of the second capability corresponding to the first subtask need to be added to the shared capability library.

[0449] It should be understood that the information of the second ability corresponding to the first subtask can be set by the user. For example, the user can set the execution cost of the second ability corresponding to the first subtask to 100 points. The information of the second ability corresponding to the first subtask can also be obtained from the ability library.

[0450] It should be understood that a detailed description of the information regarding the second ability corresponding to the first subtask mentioned above can be found in the detailed description of the information regarding the third ability mentioned earlier, and will not be repeated here.

[0451] Optionally, the seventh message may also include an encoded vector of the information of the second capability corresponding to the first subtask, wherein the encoded vector of the information of the second capability corresponding to the first subtask may be generated by the first device or by the large language model in the second device, and is not limited here.

[0452] In implementation Q2, the seventh message includes the fifth capability, and the seventh message is used to indicate that the fifth capability is added to the shared capability library.

[0453] Optionally, the seventh message may also include at least one of the following:

[0454] 1) Identification of the first device;

[0455] 2) Description of the fifth ability: The description of the fifth ability is used to describe the function of the fifth ability;

[0456] 3) The sharing method of the fifth ability, which indicates how the fifth ability is presented;

[0457] 4) Parameter information of the fifth capability, which is used to indicate the input parameters required to use the fifth capability and / or to indicate the output parameters of the fifth capability;

[0458] 5) Environmental dependency information of the fifth ability: The environmental dependency information of the fifth ability is used to indicate the environmental information on which the fifth ability depends;

[0459] 6) Execution time of the fifth ability: The execution time of the fifth ability is used to indicate the time required to execute the fifth ability;

[0460] 7) The execution cost of the fifth capability, which indicates the cost required to use the fifth capability;

[0461] 8) The calling interface of the fifth ability is used to implement the functions of the fifth ability;

[0462] 9) The source code of the Fifth Ability, which is used to implement the functionality of the Fifth Ability;

[0463] 10) Fifth Ability Source Code Licensing Policy: The Fifth Ability Source Code Licensing Policy is used to indicate whether the Fifth Ability Source Code allows modification / inheritance / derivation and / or whether other capabilities generated based on the Fifth Ability Source Code need to be added to the shared capability library.

[0464] It should be understood that the information of the aforementioned fifth capability can be set by the user, or it can be generated by the first or second device when generating the fifth capability, and there is no limitation here.

[0465] Furthermore, since the fifth capability is generated based on the capabilities corresponding to multiple subtasks within at least one subtask, the source code licensing policy for the fifth capability is also based on the source code licensing policies for the capabilities corresponding to each of the multiple subtasks. For example, if the two subtasks used to generate the fifth capability correspond to capabilities 1 and 2 respectively, and the source code licensing policy for capability 1 indicates that the source code for capability 1 cannot be modified, while the source code licensing policy for capability 2 indicates that the source code for capability 2 can be modified, then the source code licensing policy for the fifth capability includes the statement that the source code for the fifth capability cannot be modified.

[0466] It should be understood that a detailed description of the information regarding the fifth ability mentioned above can be found in the detailed description of the information regarding the third ability mentioned above, and will not be repeated here.

[0467] Optionally, the seventh message may also include an encoded vector of the fifth capability information, wherein the encoded vector of the fifth capability information may be generated by the first device or by the large language model in the second device, without limitation.

[0468] Optionally, before executing S1102, the first device can verify the second or fifth capability corresponding to the first subtask. After the verification of the second or fifth capability corresponding to the first subtask is successful, the first device generates and sends a seventh message based on the second or fifth capability corresponding to the first subtask. Alternatively, the first device can send the second or fifth capability corresponding to the first subtask to the second device, which verifies the second or fifth capability corresponding to the first subtask. After the second device verifies the second or fifth capability corresponding to the first subtask successfully, it sends a verification success message to the first device. Upon receiving the verification success message, the first device generates and sends a seventh message based on the second or fifth capability corresponding to the first subtask.

[0469] The following describes how the first device verifies the fifth capability. The verification of the second capability corresponding to the first sub-task by the first device can be referenced in the verification of the fifth capability by the first device, and will not be repeated here. The verification of the second or fifth capability corresponding to the first sub-task by the second device can also be referenced in the verification of the second or fifth capability corresponding to the first sub-task by the first device, and will not be repeated here.

[0470] In one possible implementation, the verification of the fifth capability may include at least one of the following:

[0471] 1) Verification of the execution time of the fifth capability by the first device.

[0472] In this embodiment of the application, the first device can determine whether the execution time of the fifth capability is less than a first threshold. If the execution time of the fifth capability is less than the first threshold, the verification is successful; otherwise, the verification fails.

[0473] 2) Verification of the environment in which the first device depends on the fifth capability.

[0474] In this embodiment of the application, the first device can determine whether the number of dependent environments of the fifth capability is less than a second threshold. If the number of dependent environments of the fifth capability is less than the second threshold, the verification is successful; otherwise, the verification fails.

[0475] The first device can also determine whether the dependent environment of the fifth capability includes a preset environment. If the dependent environment of the fifth capability includes a preset environment, the verification fails; otherwise, the verification passes. The preset environment can be a pre-defined type of operating system, CPU, network card, etc., which is not limited here.

[0476] 3) The first device verifies the code corresponding to the fifth capability.

[0477] In this embodiment of the application, the first device can determine whether the number of lines of code corresponding to the fifth capability is less than the third threshold. If the number of lines of code corresponding to the fifth capability is less than the third threshold, the verification passes; otherwise, the verification fails.

[0478] The first device can also determine whether there is private data in the code corresponding to the fifth capability. If private data is found in the code corresponding to the fifth capability, the verification fails; otherwise, the verification passes. The private data may include, but is not limited to, user privacy information.

[0479] The first device can also determine whether there are high-risk interfaces in the code corresponding to the fifth capability. If there are high-risk interfaces in the code corresponding to the fifth capability, the verification fails; otherwise, the verification passes. High-risk interfaces may include, but are not limited to, high-risk system interfaces and user interfaces.

[0480] S1103, the shared capability library adds the second or fifth capability corresponding to any subtask in at least one subtask to the shared capability library.

[0481] In this embodiment of the application, before the first device executes S1103, if the seventh message includes the fifth capability, the shared capability library can perform a similarity check on the fifth capability.

[0482] In one possible implementation, the shared capability library can calculate the similarity between the fifth capability and the capabilities in the shared capability library. If there is no similarity greater than the second similarity threshold, the shared capability library can add the fifth capability to the shared capability library. If there is a similarity greater than the second similarity threshold, the shared capability library can perform capability processing on the fifth capability.

[0483] Capability processing includes any of the following:

[0484] 1) Remove abilities similar to the fifth ability from the shared ability library and add the fifth ability to the shared ability library;

[0485] 2) The shared capability library marks the fifth capability and capabilities similar to the fifth capability, and adds the fifth capability to the shared capability library;

[0486] 3) The shared capability library refuses to add the fifth capability.

[0487] Optionally, after successfully storing the fifth capability in the shared capability library, a reward corresponding to the fifth capability can be issued to the account of the first device. The amount of the reward for the fifth capability issued by the shared capability library can be determined by the shared capability library or by the first device, which will not be elaborated upon here.

[0488] Furthermore, the shared capability library can generate identifiers for fifth capabilities and include the identifier, description, sharing method, parameter information, environment dependencies, execution time, execution cost, API, source code, and source code licensing policy as information about the fifth capability. The shared capability library can also store information about fifth capabilities.

[0489] It should be understood that the identifier of the fifth capability can be generated by the shared capability library or generated by the first device and sent to the shared capability library, without limitation here.

[0490] In addition, the shared capability library can encode the information of the fifth capability to obtain the encoding vector of the information of the fifth capability, and the shared capability library can also store the encoding vector of the information of the fifth capability.

[0491] It should be understood that, in the case where the seventh message includes a second capability corresponding to any one of the at least one subtasks, the processing of the second capability corresponding to any one of the at least one subtasks in the shared capability library can refer to the processing of the fifth capability as described above, and will not be repeated here.

[0492] Optionally, Figure 11 The method may also include S1104.

[0493] S1104, the shared capability library sends a response message to the first device; correspondingly, the first device receives the response message from the shared capability library.

[0494] In this embodiment of the application, the response message is used to indicate that the second or fifth capability corresponding to any one of the subtasks in at least one subtask has been successfully added to the shared capability library.

[0495] Optionally, the response message may also include the subscription address corresponding to the fifth capability. The first device can obtain the number of times the fifth capability has been used, the identifier of the first device using the fifth capability, whether the source code of the fifth capability has been modified / inherited / derived, and the identifiers of other capabilities derived from the source code of the fifth capability by accessing the subscription address corresponding to the fifth capability. This is not limited here.

[0496] Optionally, the shared capability library can also receive subscription request messages from the first device. These subscription request messages may include an identifier of the fifth capability and at least one of the following: a request for the number of times the fifth capability has been used, a request for the identifier of the first device using the fifth capability, a request for whether the source code of the fifth capability has been modified / inherited / derived, and a request for identifiers of other capabilities derived from the source code of the fifth capability. The shared capability library sends a subscription response message to the first device. This response message may include a subscription address corresponding to the fifth capability. The first device can obtain at least one of the following by accessing the subscription address: the number of times the fifth capability has been used, the identifier of the first device using the fifth capability, whether the source code of the fifth capability has been modified / inherited / derived, and identifiers of other capabilities derived from the source code of the fifth capability.

[0497] Optionally, the shared capability library can also receive capability modification messages from the first device, wherein the capability modification message includes the identifier of the fifth capability and modification information. The modification information may include modifications to at least one of the following: the description information of the fifth capability, the sharing method of the fifth capability, the parameter information of the fifth capability, the environment dependency information of the fifth capability, the execution time of the fifth capability, the execution cost of the fifth capability, the calling interface of the fifth capability, the source code of the fifth capability, and the source code licensing policy of the fifth capability. The shared capability library modifies the fifth capability or its information according to the modification information in the capability modification message.

[0498] Optionally, the shared capability library can also receive a capability deregistration message from the first device, wherein the capability deregistration message includes an identifier of the fifth capability and is used to deregister the fifth capability. After receiving the capability deregistration message, the shared capability library deletes the fifth capability and its information from the shared capability library.

[0499] It should be understood that the subscription request message, capability modification message, and capability cancellation message for the second capability corresponding to any subtask can be referenced from the subscription request message, capability modification message, and capability cancellation message for the fifth capability, and will not be elaborated here.

[0500] pass Figure 11The method described above allows the first device to add the generated capabilities to a shared capability library, making it easier for other first devices to obtain and use the capabilities from the shared capability library, thus avoiding unnecessary homogenization operations.

[0501] In this embodiment, the shared capability library can also periodically or non-periodically optimize the capabilities within it. The shared capability library can also periodically or non-periodically send its capabilities to a second device, where a large language model optimizes them. For ease of description, the following detailed explanation uses the shared capability library optimization as an example. The large language model optimization in the second device can refer to the shared capability library optimization, and will not be elaborated upon here.

[0502] In one possible implementation, the capability optimization triggering condition corresponding to non-periodic capability optimization in the shared capability library may include at least one of the following: the remaining storage space of the shared capability library is less than the fourth threshold, or the number of capabilities in the shared capability library is greater than the fifth threshold, or the sum of the lines of code corresponding to each capability in the shared capability library is greater than the sixth threshold, etc., without limitation.

[0503] Capability optimization in a shared capability library includes at least one of the following: capability deletion, capability merging, capability replacement, and capability reconstruction. The following is a detailed explanation of capability optimization:

[0504] 1) Capability deletion

[0505] For any capability in any shared capability library, if the time since the capability was added to the shared capability library exceeds the seventh threshold, or the number of times the capability has been used is less than the eighth threshold, or the probability of an error when executing the capability is greater than the ninth threshold, then the shared capability library can delete the capability.

[0506] 2) Capability merging

[0507] For any two capabilities in any shared capability library, if the functional similarity between the two capabilities is greater than the ninth threshold, or the dependency environment similarity between the two capabilities is greater than the tenth threshold, or the two capabilities were added by the same first device, then the two capabilities can be merged.

[0508] 3) Capability replacement

[0509] For any two capabilities in any shared capability library, if the functional similarity between the two capabilities is greater than the ninth threshold, or the dependency environment similarity between the two capabilities is greater than the tenth threshold, or the two capabilities were added by the same first device, then one capability can be used to replace the other capability.

[0510] 4) Capability Restructuring

[0511] For any capability in any shared capability library, if there is a logical error in the source code corresponding to the capability, or if there is a branch in the source code corresponding to the capability that takes longer than the eleventh threshold, then the source code of the capability can be rewritten.

[0512] For any capability in any shared capability library, if there is a part of the source code corresponding to that capability that can be replaced by other capabilities, then that part of the code can be replaced by the replaceable capability.

[0513] It should be understood that if the fifth capability is deleted, merged, replaced, or reconstructed, the first device will obtain information about the deletion, merging, replacement, or reconstruction of the fifth capability through the subscription address, provided that the first device obtains the subscription address.

[0514] In the above method, by optimizing the capabilities in the shared capability library, the quality of the capabilities in the shared capability library can be continuously improved, and the execution efficiency of the capabilities can be guaranteed.

[0515] In the embodiments provided above, the methods provided by the embodiments of this application have been described from the perspective of interaction between various devices. To implement the functions of the methods provided in the embodiments of this application above, the first device may include a hardware structure and / or a software module, implementing the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a particular function is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

[0516] The module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0517] The following, combined with Figures 13 to 14 This application provides a detailed description of the communication device provided in its embodiments. It should be understood that the descriptions of the device embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail here will be referred to the method embodiments above, and for the sake of brevity, will not be repeated here.

[0518] Similar to the above concept, such as Figure 13As shown, this application embodiment also provides a communication device 1300 for implementing the functions of the first device or shared capability library in the above method. For example, the communication device can be a software module or a chip system. In this application embodiment, the chip system can be composed of chips or may include chips and other discrete devices. The communication device 1300 may include: a communication unit 1301 and a processing unit 1302.

[0519] In this embodiment, the communication device 1300 includes a communication unit and a processing unit, which are respectively used to perform the sending and receiving steps of the first device or the shared capability library in the method embodiments described above. The communication unit and the processing unit can be integrated into one unit or two independent units. In one implementation, the communication device 1300 can perform the following functions:

[0520] Communication unit 1301 is used to acquire target tasks.

[0521] The processing unit 1302 is used to obtain a first capability from a shared capability library according to the target task; wherein, the shared capability library is used to store capabilities, the capabilities in the shared capability library include the first capability, and the shared capability library supports multiple first devices to share the capabilities in the shared capability library.

[0522] The processing unit 1302 is also used to perform the target task using the first capability.

[0523] In one possible design, the processing unit 1302 is specifically used to: determine at least one subtask corresponding to the target task; the communication unit 1301 is specifically used to: obtain at least one second capability corresponding to each subtask from the shared capability library, wherein the first capability includes at least one second capability corresponding to each subtask.

[0524] In one possible design, the processing unit 1302 is specifically configured to: send a first message to the second device, the first message including a target task, the first message being used to request at least one subtask corresponding to the target task; and receive at least one subtask from the second device.

[0525] In one possible design, the first message also includes information about a third capability, which is used to determine at least one subtask.

[0526] The communication unit 1301 is further configured to: send a second message to the capability library, the second message including a target task, the second message being used to request information on the capability corresponding to the target task; the capability library including a local capability library and / or a shared capability library corresponding to the first device; the local capability library corresponding to the first device being used to store capabilities, the local capability library corresponding to the first device supporting the first device in obtaining capabilities from the local capability library;

[0527] The communication unit 1301 is also used to: receive information about third capabilities from the capability library.

[0528] In one possible design, the second message also includes the first constraint condition corresponding to the target task; the third capability satisfies the first constraint condition.

[0529] In one possible design, at least one subtask includes a first subtask; the communication unit 1301 is specifically configured to: send a third message to the second device, the third message including the first subtask, the third message being used to request an identifier of a second capability corresponding to the first subtask; receive an identifier of a second capability corresponding to the first subtask from the second device; and obtain the second capability corresponding to the first subtask from the shared capability library based on the identifier of the second capability corresponding to the first subtask.

[0530] In one possible design, the third message also includes information about the fourth capability corresponding to the first subtask, the information about the fourth capability being used to determine the identifier of the second capability corresponding to the first subtask; the communication unit 1301 is further configured to: send a fourth message to the capability library, wherein the fourth message includes the first subtask, the fourth message being used to request information about the capability corresponding to the first subtask; and receive information about the fourth capability from the capability library.

[0531] In one possible design, the fourth message also includes a second constraint corresponding to the first subtask, which is determined based on the first constraint corresponding to the target task; the fourth capability satisfies the second constraint.

[0532] In one possible design, the communication unit 1301 is specifically used to: send a fifth message to the shared capability library, wherein the fifth message includes an identifier of the second capability corresponding to the first subtask, and the fifth message is used to request the second capability corresponding to the first subtask; and receive the second capability corresponding to the first subtask from the shared capability library.

[0533] In one possible design, the communication unit 1301 is specifically used to: obtain the second capability corresponding to the first subtask from the information of the fourth capability based on the identifier of the second capability corresponding to the first subtask, wherein the information of the fourth capability comes from the shared capability library.

[0534] In one possible design, the communication unit 1301 is specifically used to: obtain the second capability corresponding to the first sub-task from the shared capability library according to the identifier and authorization information of the second capability corresponding to the first sub-task, wherein the authorization information is used to instruct the first device to obtain the second capability corresponding to the first sub-task.

[0535] In one possible design, the communication unit 1301 is further configured to: send a sixth message to a third device, wherein the sixth message includes an identifier of a second capability corresponding to the first subtask, and the sixth message is used to request authorization information for the second capability corresponding to the first subtask; and receive authorization information for the second capability corresponding to the first subtask from the third device.

[0536] In one possible design, the communication unit 1301 is further configured to: send a seventh message to the shared capability library, the seventh message including a second capability corresponding to any one of the at least one subtasks, the seventh message being used to instruct the second capability corresponding to any one of the subtasks to be added to the shared capability library.

[0537] In one possible design, the communication unit 1301 is further configured to: determine a fifth capability based on the second capabilities corresponding to the multiple subtasks in at least one subtask, wherein the fifth capability is used to implement the target task or a part thereof; and send a seventh message to a shared capability library, the seventh message including the fifth capability, the seventh message being used to instruct the fifth capability to be added to the shared capability library.

[0538] In one possible design, the communication unit 1301 is specifically configured to: send an eighth message to the second device, the eighth message including second capabilities corresponding to multiple subtasks in at least one subtask, the eighth message being used to instruct the generation of a capability based on the capabilities corresponding to multiple subtasks in at least one subtask; and receive a fifth capability from the second device.

[0539] In one implementation, the communication device 1300 can perform the following functions:

[0540] Communication unit 1301 is used to receive tasks from the first device;

[0541] The communication unit 1301 is also used to send a first capability corresponding to the task to the first device, wherein the first capability is used to execute the task.

[0542] In one possible design, the communication unit 1301 is specifically used to: receive a target task from the first device; and send a first capability corresponding to the target task to the first device.

[0543] In one possible design, the communication unit 1301 is specifically used to: receive at least one subtask corresponding to the target task from the first device; and send at least one second capability corresponding to each subtask to the first device, wherein the first capability includes the second capability corresponding to each of the at least one subtask.

[0544] In one possible design, at least one subtask includes a first subtask; the communication unit 1301 is specifically configured to: receive a fifth message from the first device, wherein the fifth message includes an identifier of a second capability corresponding to the first subtask, and the fifth message is used to request the second capability corresponding to the first subtask; and send the second capability corresponding to the first subtask to the first device.

[0545] In one possible design, the processing unit 1302 is used to deduct the execution cost of the second capability corresponding to the first subtask from the account corresponding to the first device.

[0546] In one possible design, the communication unit 1301 is further configured to: receive a seventh message from the first device, wherein the seventh message includes a second capability corresponding to any one of the at least one subtasks, and the seventh message is used to instruct the second capability corresponding to any one of the subtasks to be added to the shared capability library; the processing unit 1302 is further configured to: add the second capability corresponding to any one of the at least one subtasks to the shared capability library.

[0547] In one possible design, the processing unit 1302 is further configured to: issue a reward corresponding to the second capability of any subtask in at least one subtask to the account corresponding to the first device.

[0548] In one possible design, the communication unit 1301 is further configured to: receive a seventh message from the first device, wherein the seventh message includes a fifth capability, the fifth capability being generated based on the second capabilities corresponding to the plurality of subtasks in at least one subtask, and the seventh message being used to instruct the fifth capability to be added to the shared capability library; the processing unit 1302 is further configured to: add the fifth capability to the shared capability library.

[0549] In one possible design, the processing unit 1302 is also used to: issue the reward corresponding to the fifth capability to the account corresponding to the first device.

[0550] In one possible design, the processing unit 1302 is also used to optimize the capabilities in the shared capability library.

[0551] The above are just examples. The communication unit and processing unit in the communication device 1300 can also perform other functions. For a more detailed description, please refer to the relevant descriptions in the method embodiments shown above. They will not be repeated here.

[0552] The methods provided in the embodiments of this application above are described from the perspective of a communication device as the executing entity. To implement the functions of the methods provided in the embodiments of this application above, the communication device may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0553] For example, when implemented in hardware, the hardware implementation of this communication device can refer to... Figure 14 And its related descriptions.

[0554] See Figure 14 The communication device may include: one or more processors 1402; a memory 1403; and one or more computer programs 1404. These components can be connected via one or more communication buses 1401. The one or more computer programs 1404 are stored in the memory 1403 and configured to be executed by the one or more processors 1402. The one or more computer programs 1404 include instructions that can be used to perform the methods in any of the above embodiments. The one or more processors 1402 can perform the functions of the communication unit 1301 and the processing unit 1302.

[0555] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a communication device, cause the communication device to implement the communication method described in the above embodiments.

[0556] This application also provides a computer program product that, when run on a computer, causes the computer to execute the communication method described in the above embodiments.

[0557] In this application, the communication device, computer-readable storage medium, computer program product or chip provided in the embodiments are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0558] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0559] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0560] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0561] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0562] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0563] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: The method is applied to a first device, and comprises: obtaining a target task; obtaining a first capability from a shared capability library according to the target task, wherein the shared capability library is used to store capabilities, the capabilities in the shared capability library include the first capability, and the shared capability library supports multiple first devices sharing the capabilities in the shared capability library; performing the target task by using the first capability.

2. The method of claim 1, wherein, The step of obtaining the first capability from the shared capability library according to the target task comprises: determining at least one subtask corresponding to the target task; obtaining a second capability corresponding to each of the at least one subtask from the shared capability library, wherein the first capability includes the second capability corresponding to each of the at least one subtask.

3. The method of claim 2, wherein, The step of determining the at least one subtask corresponding to the target task comprises: sending a first message to a second device, wherein the first message includes the target task, and the first message is used to request the at least one subtask corresponding to the target task; receiving the at least one subtask from the second device.

4. The method of claim 3, wherein, The first message further includes information of a third capability, wherein the information of the third capability is used to determine the at least one subtask. The method further comprises: sending a second message to a capability library, wherein the second message includes the target task, and the second message is used to request information of a capability corresponding to the target task; the capability library includes a local capability library corresponding to the first device and / or the shared capability library; the local capability library corresponding to the first device is used to store capabilities, and the local capability library corresponding to the first device supports the first device to obtain the capabilities in the local capability library; receiving the information of the third capability from the capability library.

5. The method of any one of claims 3-4, wherein, The second message further includes a first constraint condition corresponding to the target task; and the third capability satisfies the first constraint condition.

6. The method of any one of claims 2-5, wherein, The at least one subtask includes a first subtask. The step of obtaining the second capability corresponding to each of the at least one subtask from the shared capability library comprises: sending a third message to a second device, wherein the third message includes the first subtask, and the third message is used to request an identifier of a second capability corresponding to the first subtask; receiving the identifier of the second capability corresponding to the first subtask from the second device; obtaining the second capability corresponding to the first subtask from the shared capability library according to the identifier of the second capability corresponding to the first subtask.

7. The method of claim 6, wherein, The third message further includes information of a fourth capability corresponding to the first subtask, wherein the information of the fourth capability is used to determine the identifier of the second capability corresponding to the first subtask. The method further comprises: sending a fourth message to the capability library, wherein the fourth message includes the first subtask, and the fourth message is used to request information of a capability corresponding to the first subtask; receiving the information of the fourth capability from the capability library.

8. The method of claim 7, wherein, The fourth message further includes a second constraint condition corresponding to the first subtask, wherein the second constraint condition is determined according to the first constraint condition corresponding to the target task; and the fourth capability satisfies the second constraint condition.

9. The method of any one of claims 6-8, wherein, The method further comprises: sending a sixth message to a third device, the sixth message comprising an identifier of the second capability corresponding to the first subtask, the sixth message being used to request authorization information of the second capability corresponding to the first subtask; receiving the authorization information of the second capability corresponding to the first subtask from the third device.

10. The method of any one of claims 7-8, wherein, The method further comprises: sending a seventh message to the shared capability library, the seventh message comprising the second capability corresponding to any subtask of the at least one subtask, the seventh message being used to indicate that the second capability corresponding to the any subtask is added to the shared capability library.

11. The method of any one of claims 6-10, wherein, The method further comprises: determining a fifth capability according to the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the fifth capability being used to implement the target task or to implement a part of the target task; 12. The method of claim 11, wherein, sending a seventh message to the shared capability library, the seventh message comprising the fifth capability, the seventh message being used to indicate that the fifth capability is added to the shared capability library. The method further comprises: sending an eighth message to the second device, the eighth message comprising the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the eighth message being used to indicate that one capability is generated according to the capabilities corresponding to the plurality of subtasks of the at least one subtask; 13. The method of any one of claims 2-12, wherein, receiving the fifth capability from the second device. The method further comprises:

14. The method of any one of claims 2-12, wherein, sending a sixth message to a third device, the sixth message comprising an identifier of the second capability corresponding to the first subtask, the sixth message being used to request authorization information of the second capability corresponding to the first subtask; receiving the authorization information of the second capability corresponding to the first subtask from the third device. The method further comprises:

15. The method of claim 14, wherein, sending a seventh message to the shared capability library, the seventh message comprising the second capability corresponding to any subtask of the at least one subtask, the seventh message being used to indicate that the second capability corresponding to the any subtask is added to the shared capability library. The method further comprises: determining a fifth capability according to the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the fifth capability being used to implement the target task or to implement a part of the target task; 16. A method of communication, comprising: sending a seventh message to the shared capability library, the seventh message comprising the fifth capability, the seventh message being used to indicate that the fifth capability is added to the shared capability library. The method further comprises: sending an eighth message to the second device, the eighth message comprising the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the eighth message being used to indicate that one capability is generated according to the capabilities corresponding to the plurality of subtasks of the at least one subtask; receiving the fifth capability from the second device. The method further comprises: sending a sixth message to a third device, the sixth message comprising an identifier of the second capability corresponding to the first subtask, the sixth message being used to request authorization information of the second capability corresponding to the first subtask; receiving the authorization information of the second capability corresponding to the first subtask from the third device. The method further comprises: sending a seventh message to the shared capability library, the seventh message comprising the second capability corresponding to any subtask of the at least one subtask, the seventh message being used to indicate that the second capability corresponding to the any subtask is added to the shared capability library. The method further comprises: determining a fifth capability according to the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the fifth capability being used to implement the target task or to implement a part of the target task; sending a seventh message to the shared capability library, the seventh message comprising the fifth capability, the seventh message being used to indicate that the fifth capability is added to the shared capability library. The method further comprises: sending an eighth message to the second device, the eighth message comprising the second capabilities corresponding to the plurality of subtasks of the at least one subtask, the eighth message being used to indicate that one capability is generated according to the capabilities corresponding to the plurality of subtasks of the at least one subtask; receiving the fifth capability from the second device.

17. The method of claim 16, wherein, The receiving the task from the first device comprises: receiving a target task from the first device; The sending the first capability corresponding to the task to the first device comprises: sending a first capability corresponding to the target task to the first device.

18. The method of claim 16, wherein, The receiving the task from the first device comprises: receiving at least one subtask corresponding to a target task from the first device; The sending the first capability corresponding to the task to the first device comprises: sending second capabilities corresponding to the at least one subtask respectively to the first device, wherein the first capability comprises the second capabilities corresponding to the at least one subtask respectively.

19. The method of claim 17, wherein, The at least one subtask comprises a first subtask; The sending the second capability corresponding to the at least one subtask to the first device comprises: receiving a fifth message from the first device, wherein the fifth message comprises an identification of the second capability corresponding to the first subtask, and the fifth message is used to request the second capability corresponding to the first subtask; sending the second capability corresponding to the first subtask to the first device.

20. The method of claim 19, wherein, The method further comprises: deducting an execution cost of the second capability corresponding to the first subtask from an account corresponding to the first device.

21. The method of any one of claims 18-20, wherein, The method further comprises: receiving a seventh message from the first device, wherein the seventh message comprises a second capability corresponding to any one of the at least one subtask, and the seventh message is used to indicate that the second capability corresponding to the any one of the at least one subtask is added to the shared capability library; adding the second capability corresponding to the any one of the at least one subtask to the shared capability library.

22. The method of claim 21, wherein, The method further comprises: issuing a reward corresponding to the second capability corresponding to the any one of the at least one subtask to an account corresponding to the first device.

23. The method of any one of claims 18-20, wherein, The method further comprises: receiving a seventh message from the first device, wherein the seventh message comprises a fifth capability, and the fifth capability is generated according to second capabilities corresponding to a plurality of subtasks of the at least one subtask, and the seventh message is used to indicate that the fifth capability is added to the shared capability library; adding the fifth capability to the shared capability library.

24. The method of claim 23, wherein, The method further comprises: issuing a reward corresponding to the fifth capability to an account corresponding to the first device.

25. The method of any one of claims 16-24, wherein, The method further comprises: performing capability optimization on the capabilities in the shared capability library.

26. A communications device, characterized by comprises a processor and a memory; The processor is configured to execute computer programs or instructions stored in the memory, so that the communication device implements the method according to any one of claims 1-15, or implements the method according to any one of claims 16-25.

27. A computer-readable storage medium, characterized in that, The computer program or instruction is stored in the computer readable storage medium, and when the computer program or instruction is executed on the computer, the computer readable storage medium implements the method according to any one of claims 1-15, or implements the method according to any one of claims 16-25.

28. A chip, characterized by The chip comprises a processor coupled with a memory, for executing computer programs or instructions stored in the memory, so that the chip implements the method of any one of claims 1-15, or implements the method of any one of claims 16-25.

29. A communications device, characterized by The communication device comprises a module for executing the method of any one of claims 1-15, or the communication device comprises a module for executing the method of any one of claims 16-25.

30. A computer program product, characterised in that, When the computer reads and executes the computer program product, the computer implements the method of any one of claims 1-15, or implements the method of any one of claims 16-25.

Images