CN-121996417-A - Task execution method and device and related equipment

CN121996417ACN 121996417 ACN121996417 ACN 121996417ACN-121996417-A

Abstract

The application provides a task execution method, a task execution device and related equipment, which relate to the technical field of artificial intelligence and wireless communication, wherein the task execution method comprises the steps of obtaining a target request, wherein the target request is used for requesting to execute a target task; the method comprises the steps of splitting a target task to obtain a plurality of subtasks, obtaining target information matched with the subtasks in a preset database, packaging the subtasks and the target information into target information blocks, generating execution path information according to the target information blocks, wherein the execution path information is used for representing an operation step sequence for executing the subtasks, and executing the operation step sequence based on the execution path information. Thus, the accuracy of the execution of the target task can be improved, namely, the execution effect of the target task is enhanced.

Inventors

QIAO JUN
WANG YUXUAN
Li Shentie
GENG BO
JIANG YONG

Assignees

中国移动通信集团安徽有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20260116

Claims (10)

1. A method of performing a task, comprising: acquiring a target request, wherein the target request is used for requesting to execute a target task; splitting the target task to obtain a plurality of subtasks; acquiring target information matched with the subtasks from a preset database, and packaging the subtasks and the target information into a target information block; Generating execution path information according to the target information block, wherein the execution path information is used for representing an operation step sequence for executing the subtasks; And executing the operation step sequence based on the execution path information.
2. The method of claim 1, wherein splitting the target task to obtain a plurality of subtasks comprises: Splitting the target task through a first agent to obtain a plurality of subtasks; The obtaining the target information matched with the subtask in the preset database, and packaging the subtask and the target information into a target information block, includes: Acquiring target information matched with the subtasks from the preset database through a second agent, and packaging the subtasks and the target information into target information blocks through the second agent; the generating the execution path information according to the target information block includes: Inputting the target information block into a third agent to generate the execution path information; Wherein the first agent is connected with the third agent through the second agent.
3. The method of claim 2, wherein after the performing the sequence of operational steps based on the execution path information, the method further comprises: The method comprises the steps of obtaining target evaluation parameters, wherein the target evaluation parameters comprise at least one of a first evaluation parameter, a second evaluation parameter and a third evaluation parameter, the first evaluation parameter is used for evaluating the accuracy of the first agent on the splitting of the target task, the second evaluation parameter is used for evaluating the matching degree of the subtasks and the target information, and the third evaluation parameter is used for evaluating the execution effect corresponding to the subtasks after the execution path information is executed; Optimizing a first rewarding function corresponding to the first agent according to the first evaluation parameter, optimizing a second rewarding function corresponding to the second agent according to the second evaluation parameter, and/or optimizing a third rewarding function corresponding to the third agent according to the third evaluation parameter.
4. The method of claim 3, wherein the target evaluation parameters include the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter, wherein optimizing the first rewards function corresponding to the first agent according to the first evaluation parameter, optimizing the second rewards function corresponding to the second agent according to the second evaluation parameter, and/or optimizing the third rewards function corresponding to the third agent according to the third evaluation parameter, comprises: acquiring a fourth evaluation parameter, wherein the fourth evaluation parameter is used for evaluating the overall completion quality of the target task when the target task is completed; Optimizing the first bonus function according to the fourth evaluation parameter and the first evaluation parameter, optimizing the second bonus function according to the fourth evaluation parameter and the second evaluation parameter, and/or optimizing the third bonus function according to the fourth evaluation parameter and the third evaluation parameter.
5. The method of claim 3, wherein the target evaluation parameters include the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter, wherein optimizing the first rewards function corresponding to the first agent according to the first evaluation parameter, optimizing the second rewards function corresponding to the second agent according to the second evaluation parameter, and/or optimizing the third rewards function corresponding to the third agent according to the third evaluation parameter, comprises: Acquiring contribution degrees corresponding to the first agent, the second agent and the third agent in the process of completing the target task; optimizing the first rewarding function according to the contribution degree corresponding to the first agent and the first evaluation parameter, optimizing the second rewarding function according to the contribution degree corresponding to the second agent and the second evaluation parameter, and/or optimizing the third rewarding function according to the contribution degree corresponding to the third agent and the third evaluation parameter.
6. The method according to any one of claims 1 to 5, wherein the obtaining, in a preset database, target information matched with the subtask includes: obtaining a target vector corresponding to the subtask; Obtaining a plurality of embedded vectors matched with the target vector from the preset database through a vectorization retrieval technology; And determining storage information corresponding to at least part of the embedded vectors in the plurality of embedded vectors as the target information, wherein the storage information is stored in the preset database.
7. A task execution device, characterized by comprising: the first acquisition module is used for acquiring a target request, wherein the target request is used for requesting to execute a target task; The splitting module is used for splitting the target task to obtain a plurality of subtasks; the packaging module is used for acquiring target information matched with the subtasks in a preset database and packaging the subtasks and the target information into a target information block; The generation module is used for generating execution path information according to the target information block, wherein the execution path information is used for representing a sequence of operation steps for executing the subtasks; and the execution module is used for executing the operation step sequence based on the execution path information.
8. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, characterized in that the processor is arranged to read the program in the memory to carry out the steps of the task execution method according to any one of claims 1 to 6.
9. A readable storage medium storing a program, wherein the program when executed by a processor implements the steps of the task execution method according to any one of claims 1 to 6.
10. A computer program product comprising computer instructions which, when executed by a processor, implement the steps of the task execution method of any one of claims 1 to 6.

Description

Task execution method and device and related equipment Technical Field The embodiment of the application relates to the technical field of artificial intelligence and wireless communication, in particular to a task execution method, a task execution device and related equipment. Background With the continuous development of electronic technology, electronic devices occupy more and more important positions in people's lives, and electronic devices can be used for performing many tasks, for example, the electronic devices can be used for outputting activity schemes, outputting survey reports, and the like. However, in the actual use process, when the task to be executed is complex, the electronic device has a low understanding degree of the task to be executed, which easily results in poor accuracy of executing the task. Disclosure of Invention The embodiment of the application provides a task execution method, a task execution device and related equipment, which are used for solving the problem of poor accuracy of task execution. To solve the above problems, the present application is achieved as follows: in a first aspect, an embodiment of the present application provides a task execution method, including: acquiring a target request, wherein the target request is used for requesting to execute a target task; splitting the target task to obtain a plurality of subtasks; acquiring target information matched with the subtasks from a preset database, and packaging the subtasks and the target information into a target information block; Generating execution path information according to the target information block, wherein the execution path information is used for representing an operation step sequence for executing the subtasks; And executing the operation step sequence based on the execution path information. In a second aspect, an embodiment of the present application provides a task execution device, including: the first acquisition module is used for acquiring a target request, wherein the target request is used for requesting to execute a target task; The splitting module is used for splitting the target task to obtain a plurality of subtasks; the packaging module is used for acquiring target information matched with the subtasks in a preset database and packaging the subtasks and the target information into a target information block; The generation module is used for generating execution path information according to the target information block, wherein the execution path information is used for representing a sequence of operation steps for executing the subtasks; and the execution module is used for executing the operation step sequence based on the execution path information. In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a program stored in the memory and capable of running on the processor, where the processor is configured to read the program in the memory to implement the steps in the method according to the foregoing first aspect. In a fourth aspect, embodiments of the present application also provide a readable storage medium storing a program which, when executed by a processor, implements the steps of the method as described in the foregoing first aspect. In a fifth aspect, embodiments of the present application also provide a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method as described in the first aspect above. In the embodiment of the application, the more complex target task can be split into a plurality of subtasks, so that the overlong task and the excessively complex task are avoided, the understanding degree of the electronic equipment on the task is lower, the understanding degree of the electronic equipment on each subtask can be improved, meanwhile, the target information matched with the subtask is acquired in the preset database, the target information can be understood as the expansion information of the subtask, the understanding degree of the electronic equipment on the target information block can be further improved by packaging the subtask and the target information into the target information block, the accuracy of the execution path information generated based on the target information block is further improved, and after the operation step sequence is executed based on the execution path information, the executing accuracy of the target task is further improved, namely the executing effect of the target task is enhanced. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be