Search

CN-121996514-A - Task execution method, device, equipment and storage medium

CN121996514ACN 121996514 ACN121996514 ACN 121996514ACN-121996514-A

Abstract

The application discloses a task execution method, a device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of displaying input query information, wherein the query information is used for generating a query task, the query task is a task for outputting a query result corresponding to the query information, displaying at least two decomposition tasks generated based on the query information in a time line mode, wherein the at least two decomposition tasks are used for completing the query task, displaying state information corresponding to the at least two decomposition tasks respectively, the state information corresponding to the decomposition tasks is used for indicating the execution state of the decomposition tasks, and displaying the query result corresponding to the query information after the query task is executed. According to the application, at least two decomposition tasks are displayed in a time line mode by adopting a vertical linear list layout, so that the vertical screen space of the terminal equipment is fully utilized, and the difficulty of interactive operation is reduced.

Inventors

  • HUANG BIN
  • Ju Xincheng
  • ZHAO YANG

Assignees

  • 腾讯科技（深圳）有限公司

Dates

Publication Date
20260508
Application Date
20260127

Claims (20)

  1. 1.A method of task execution, the method comprising: displaying input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; displaying at least two decomposition tasks generated based on the query information in a time line form, wherein the at least two decomposition tasks are used for completing the query task; Displaying state information corresponding to the at least two decomposition tasks respectively, wherein the state information corresponding to the decomposition tasks is used for indicating the execution state of the decomposition tasks; And after the query task is executed, displaying a query result corresponding to the query information.
  2. 2. The method of claim 1, wherein displaying, in a timeline, at least two decomposition tasks generated based on the query information comprises: And displaying at least two decomposition task information in sequence based on the execution sequence of the at least two decomposition tasks, wherein each decomposition task information is used for indicating one decomposition task.
  3. 3. The method according to claim 2, wherein the method further comprises: displaying task node icons corresponding to the at least two pieces of decomposed task information respectively and connecting lines for connecting the task node icons; The task node icons are used for marking the decomposing tasks, and the connecting lines are used for indicating the execution sequence of the at least two decomposing tasks.
  4. 4. A method according to claim 3, wherein the task node icons have different display styles for indicating different execution states of the break-up task.
  5. 5. The method according to any one of claims 2 to 4, wherein displaying at least two decomposed task information in a sequential order based on an execution order of the at least two decomposed tasks includes: Displaying the at least two decomposition task information in a sequential arrangement based on the execution order and the hierarchical structure of the at least two decomposition tasks; the hierarchical structure is used for defining father-son relations among the decomposition tasks, the decomposition task information corresponding to the decomposition tasks belonging to the same hierarchy is displayed in an aligned mode, the decomposition task information corresponding to the decomposition tasks belonging to different hierarchies is displayed in a staggered mode, and the decomposition task information corresponding to at least one decomposition task serving as a child task of the father task is displayed below the decomposition task information corresponding to the decomposition task serving as the father task.
  6. 6. The method of claim 5, wherein as a breakdown of the parent task, a corresponding expand stow control is displayed, the method further comprising: In response to a first operation for the expansion and retraction control, displaying the decomposition task information respectively corresponding to at least one decomposition task as a child task of the parent task below the decomposition task information respectively corresponding to at least one decomposition task as a child task of the parent task when the decomposition task information respectively corresponding to at least one decomposition task as a child task of the parent task is in a hidden state, or And under the condition that the decomposition task information corresponding to the at least one decomposition task serving as the child task of the parent task is in a display state, canceling to display the decomposition task information corresponding to the at least one decomposition task serving as the child task of the parent task under the decomposition task information corresponding to the decomposition task of the parent task in response to the second operation of the expansion and retraction control.
  7. 7. The method according to any one of claims 1 to 6, wherein the status information corresponding to the decomposed task includes at least one of a task node icon and a status text label; the task node icon is used for marking the decomposing task, and the display style of the task node icon is used for indicating the execution state of the decomposing task; The state text label is used for indicating the execution state of the decomposition task in a text form.
  8. 8. The method of claim 7, wherein the color of the task node icon matches the execution state indicated by the state literal tag; When the task node icon corresponding to the decomposition task is in a first color, the state text label corresponding to the decomposition task is used for indicating that the execution state of the decomposition task is completed; When the task node icon corresponding to the decomposition task is in the second color, the state text label corresponding to the decomposition task is used for indicating that the execution state of the decomposition task is executing; And when the task node icon corresponding to the decomposition task is in the third color, the state text label corresponding to the decomposition task is used for indicating that the execution state of the decomposition task is not started.
  9. 9. The method of claim 7 or 8, wherein the status information corresponding to the decomposed task further includes progress information indicating progress of execution of the decomposed task.
  10. 10. A method of task execution, the method comprising: The method comprises the steps of obtaining input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; executing each decomposition task in the decomposition task list through the AI model to obtain execution results corresponding to the at least two decomposition tasks respectively; and generating a query result corresponding to the query information according to the execution results respectively corresponding to the at least two decomposition tasks through the AI model.
  11. 11. The method of claim 10, wherein the generating, by the AI model, a resolved task list corresponding to the query information from the query information comprises: Generating new query information according to the query information and a historical query record through the AI model, wherein the historical query record is a query record positioned before the query information in the current query process; Obtaining an analysis result of the new query information according to the new query information through the AI model, wherein the analysis result is used for indicating whether the new query information depends on search data to generate a query result corresponding to the query information; And under the condition that the analysis result is used for indicating the new query information to depend on the search data to generate a query result corresponding to the query information, generating a decomposition task list corresponding to the query information according to the new query information through the AI model.
  12. 12. The method of claim 11, wherein the method further comprises: And under the condition that the analysis result is used for indicating the new query information to generate the query result corresponding to the query information independent of the search data, generating the query result corresponding to the query information according to the new query information through the AI model.
  13. 13. The method according to any of claims 10 to 12, wherein the list of resolved tasks comprises at least one of: the at least two decomposition tasks respectively correspond to the identification information; names corresponding to the at least two decomposition tasks respectively; descriptive text corresponding to the at least two decomposition tasks respectively; The at least two decomposition tasks are respectively called intelligent agents when executed; The at least two decomposition tasks respectively call input parameters of the intelligent agent; And the at least two decomposition tasks are respectively corresponding to the execution sequence.
  14. 14. A method according to any one of claims 10 to 13, wherein the task decomposition list includes at least one decomposition task list with hierarchy corresponding to each other, and a hierarchy in the task decomposition list is used to define parent-child relationships between the decomposition tasks; The generating, by the AI model, a decomposition task list corresponding to the query information according to the query information includes: Generating a first-level decomposition task list corresponding to the query information according to the query information through the AI model; In the process of executing the decomposing task serving as the parent task, generating a decomposing task list corresponding to the subtask of the parent task according to the decomposing task serving as the parent task through the AI model.
  15. 15. The method of claim 14, wherein the generating, by the AI model, a query result corresponding to the query information according to the execution results respectively corresponding to the at least two decomposition tasks comprises: generating a summary result corresponding to the at least two decomposition tasks according to the execution results respectively corresponding to the at least two decomposition tasks through the AI model; Generating an anti-thinking result of the at least two decomposition tasks according to the summarized results corresponding to the at least two decomposition tasks through the AI model, wherein the anti-thinking result is used for indicating the decomposition task to be re-executed in the at least two decomposition tasks; Generating new execution results respectively corresponding to the at least two decomposition tasks according to the thinking-back results of the at least two decomposition tasks through the AI model; And generating a query result corresponding to the query information according to the new execution results respectively corresponding to the at least two decomposition tasks through the AI model.
  16. 16. The method according to any one of claims 10 to 15, further comprising: Constructing a directed acyclic graph corresponding to the query information according to a decomposition task list corresponding to the query information, wherein the directed acyclic graph is used for indicating the dependency relationship between the at least two decomposition tasks, each task node in the directed acyclic graph is used for indicating one decomposition task, and a directed edge in the directed acyclic graph is used for indicating the existence of the dependency relationship between the two decomposition tasks connected with the directed edge; Traversing each task node in the directed acyclic graph, and adding the decomposition task corresponding to the task node to a ready queue after at least one decomposition task corresponding to the front-end dependent node corresponding to the task node is executed, wherein the decomposition task corresponding to the front-end dependent node is the front-end task of the decomposition task corresponding to the task node; Invoking an agent to synchronously execute at least one decomposition task in the ready queue.
  17. 17. The method according to any one of claims 10 to 16, further comprising: Generating task state information corresponding to the at least two decomposition tasks respectively, wherein the task state information of the decomposition tasks comprises at least one item of creation time of the decomposition tasks, execution state of the decomposition tasks and identification information corresponding to sub-tasks of the decomposition tasks; and updating task state information corresponding to the at least two decomposition tasks respectively in the process of executing the at least two decomposition tasks.
  18. 18. A task execution device, the device comprising: The input display module is used for displaying input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; The task display module is used for displaying at least two decomposition tasks generated based on the query information in a time line form, wherein the at least two decomposition tasks are used for completing the query task; The state display module is used for displaying state information corresponding to the at least two decomposition tasks respectively, and the state information corresponding to the decomposition tasks is used for indicating the execution state of the decomposition tasks; And the result display module is used for displaying the query result corresponding to the query information after the execution of the query task is completed.
  19. 19. A task execution device, the device comprising: the input acquisition module is used for acquiring input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; The task generation module is used for generating a decomposition task list corresponding to the query information according to the query information through the AI model, wherein the decomposition task list comprises at least two decomposition tasks, and the at least two decomposition tasks are used for completing the query task; the task execution module is used for executing each decomposition task in the decomposition task list through the AI model to obtain execution results corresponding to the at least two decomposition tasks respectively; And the result generation module is used for generating a query result corresponding to the query information according to the execution results respectively corresponding to the at least two decomposition tasks through the AI model.
  20. 20. A computer device comprising a processor and a memory in which a computer program is stored, the computer program being loaded and executed by the processor to implement the task execution method of any one of claims 1 to 9 or to implement the task execution method of any one of claims 10 to 17.

Description

Task execution method, device, equipment and storage medium Technical Field The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for executing tasks. Background The user may initiate a query in an AI (ARTIFICIAL INTELLIGENCE ) application to obtain an answer. In the related art, a client typically adopts a form of a mind map to display an execution process of a query task, disassembles the query task, and continuously disassembles a plurality of sub-tasks obtained by disassembling the query task to form a network structure with query task nodes as starting points, and radially expands the sub-task nodes to the periphery, wherein each node represents a dependency relationship through a connection line, and the client supports interactive operations such as scaling, translation and the like for the mind map. However, the above method requires a large display space to expand the display task node, so that the device screen may not completely present the execution flow of the query task. Disclosure of Invention The embodiment of the application provides a task execution method, a device, equipment and a storage medium. The technical scheme provided by the embodiment of the application is as follows: according to an aspect of an embodiment of the present application, there is provided a task execution method, including: displaying input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; displaying at least two decomposition tasks generated based on the query information in a time line form, wherein the at least two decomposition tasks are used for completing the query task; Displaying state information corresponding to the at least two decomposition tasks respectively, wherein the state information corresponding to the decomposition tasks is used for indicating the execution state of the decomposition tasks; And after the query task is executed, displaying a query result corresponding to the query information. According to an aspect of an embodiment of the present application, there is provided a task execution method, including: Acquiring input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; Generating a decomposition task list corresponding to the query information according to the query information through the AI model, wherein the decomposition task list comprises at least two decomposition tasks, and the at least two decomposition tasks are used for completing the query task; executing each decomposition task in the decomposition task list through the AI model to obtain execution results corresponding to the at least two decomposition tasks respectively; and generating a query result corresponding to the query information according to the execution results respectively corresponding to the at least two decomposition tasks through the AI model. According to an aspect of an embodiment of the present application, there is provided a task performing device including: The input display module is used for displaying input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; The task display module is used for displaying at least two decomposition tasks generated based on the query information in a time line form, wherein the at least two decomposition tasks are used for completing the query task; The state display module is used for displaying state information corresponding to the at least two decomposition tasks respectively, and the state information corresponding to the decomposition tasks is used for indicating the execution state of the decomposition tasks; And the result display module is used for displaying the query result corresponding to the query information after the execution of the query task is completed. According to an aspect of an embodiment of the present application, there is provided a task performing device including: the input acquisition module is used for acquiring input query information, wherein the query information is used for generating a query task, and the query task is a task for outputting a query result corresponding to the query information; The task generation module is used for generating a decomposition task list corresponding to the query information according to the query information through the AI model, wherein the decomposition task list comprises at least two decomposition tasks, and the at least two decomposition tasks are used for completing the query task; the task execution module is used for executing each decomposition task in the decomposition task list through the AI mode