Task execution method and device, equipment and storage medium
By displaying the task execution workflow and real-time task screen in the chat interface, the problem of lack of transparency in the execution of complex tasks by artificial intelligence models is solved, thereby improving the user experience and interactive functions.
Patent Information
- Application Number
- CN202511757215.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-26
- Publication Date
- 2026-03-03
AI Technical Summary
In existing technologies, artificial intelligence models lack transparency when performing complex tasks, making it impossible for users to perceive the task execution process in real time, which affects the user experience.
After receiving the task description information in the chat interface, the task execution workflow is displayed, and the task nodes are executed sequentially through the task execution agent, with the task execution screen displayed in real time to increase transparency.
By showcasing the task execution process, the transparency of task execution and user experience are improved, and the interactive functions of the artificial intelligence model are enriched.
Smart Images
Figure CN121599740A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, and in particular to a task execution method, apparatus, device, and storage medium. Background Technology
[0002] With the continuous development of computer technology, artificial intelligence models have played a very important role in various fields. For example, in the field of e-commerce, artificial intelligence models can assist users in shopping.
[0003] Therefore, how to enrich the interactive functions of using artificial intelligence models to perform complex tasks for users is a technical problem that urgently needs to be solved. Summary of the Invention
[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a task execution method, apparatus, device and storage medium.
[0005] In a first aspect, embodiments of this disclosure provide a task execution method, the method comprising: In response to task description information entered in the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface; wherein, the task execution workflow includes multiple task nodes with execution order relationship generated according to the task description information, each task node is configured with at least one task execution agent, and the at least one task execution agent is determined according to the task type corresponding to the task node; In response to the task execution operation triggered by the task execution workflow, the task execution agent corresponding to each task node in the task execution workflow is called in sequence to execute the task, and the task execution screen is displayed synchronously in the task live broadcast area of the session interface; wherein, the task execution screen is used to present the process of the task execution agent simulating the user's task execution.
[0006] In one optional implementation, the method further includes: During the process of calling the task execution agent corresponding to the first task node in the task execution workflow to execute the task, the task execution process content corresponding to the first task node is displayed in the information area of the session interface; wherein, the task execution process content includes the execution steps of the task execution agent corresponding to the first task node.
[0007] In one optional implementation, the method further includes: During the process of calling the task execution agent corresponding to the first task node to execute the task, the task execution details information corresponding to the first task node is displayed on the content interface; wherein, the task execution details information includes the execution result information corresponding to each execution step of the task execution agent corresponding to the first task node.
[0008] In one optional implementation, the method further includes: During the process of calling the task execution agent corresponding to the first task node to execute the task, task execution prompt information is displayed on the task execution screen shown in the task live broadcast area; wherein, the task execution prompt information is used to indicate the task execution process currently presented on the task execution screen.
[0009] In one optional implementation, the method further includes: During the execution of a task, task progress information is displayed in the information area of the session interface; wherein, the task progress information is used to reflect the progress of task execution.
[0010] In one optional implementation, the method further includes: In response to a workflow-triggered modification operation performed on the task, a workflow modification interface is displayed; After receiving the modified content input on the workflow modification interface, the modified task execution workflow is updated and displayed in the information area; wherein, the modified task execution workflow is generated based on the modified content, the task execution workflow, and the task description information.
[0011] In one optional implementation, the method further includes: During the execution of a task by the task execution agent corresponding to the second task node in the task execution workflow, if a preset interruption event is detected, the task execution is paused and an interruption message is displayed. In response to an object access operation for the interruption information, an object access interface is displayed, and the preset interruption event is processed based on the object access interface; In response to the completion message of the preset interruption event, the task execution agent corresponding to the second task node is invoked to continue executing the task.
[0012] In one optional implementation, the method further includes: In response to the task execution completion message of the task execution agent corresponding to the third task node in the task execution workflow, a task execution log corresponding to the third task node is generated; In response to the viewing operation of the task execution log corresponding to the third task node, the log content in the task execution log is displayed on the content interface.
[0013] Secondly, embodiments of this disclosure also provide a task execution apparatus, the apparatus comprising: The first display module is used to respond to the task description information input in the session interface and display the task execution workflow corresponding to the task description information in the information area of the session interface; wherein, the task execution workflow includes multiple task nodes with execution order relationship generated according to the task description information, each task node is configured with at least one task execution agent, and the at least one task execution agent is determined according to the task type corresponding to the task node; The task execution module is used to respond to the task execution operation triggered by the task execution workflow, sequentially call the task execution agent corresponding to each task node in the task execution workflow to execute the task, and display the task execution screen in the task live broadcast area of the session interface; wherein, the task execution screen is used to present the process of the task execution agent simulating the user's task execution.
[0014] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising: A processor; a memory for storing executable instructions of the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement the task execution method provided in the embodiments of this disclosure.
[0015] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program for performing the task execution method provided in embodiments of this disclosure.
[0016] Fifthly, this disclosure provides a computer program product comprising a computer program / instruction that, when executed by a processor, implements the method described above.
[0017] The technical solution provided in this disclosure has at least the following advantages compared with the prior art: In the task execution method provided in this embodiment, after receiving input task description information in the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface. The task execution workflow includes multiple task nodes with an execution order, and each task node is configured with a task execution agent determined according to its task type. When a task execution operation triggered by the task execution workflow is received, the task execution agents corresponding to each task node are sequentially invoked to execute the task, and the task execution screen is displayed in the task live broadcast area of the session interface to present the process of the task execution agent simulating the user's task execution. This embodiment can generate multiple task nodes based on the task description information input by the user, configure task execution agents for each task node according to its task type, execute tasks by invoking each task execution agent, and display the task execution screen on the session interface. Therefore, this embodiment can not only use task execution agents to execute complex tasks for users, but also display the task execution screen to users during the task execution process, increasing the transparency of task execution and enriching the interactive functions of using artificial intelligence models to execute complex tasks for users. Attached Figure Description
[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.
[0019] Figure 1 A flowchart of a task execution method provided in this embodiment of the disclosure; Figure 2 A schematic diagram of a page provided for an embodiment of this disclosure; Figure 3 Another schematic diagram of a page provided for an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of a task execution device provided in an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation
[0020] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0021] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.
[0022] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.
[0023] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.
[0024] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".
[0025] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
[0026] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained. In related technologies, the use of artificial intelligence models to execute complex tasks is usually implemented in a black box manner. Users can only see the final result of the task execution and cannot perceive the task execution process in real time. The low transparency of the task execution process makes it impossible for users to understand how the final result is obtained, thus affecting the user experience.
[0027] To address this, this disclosure provides a task execution method. After receiving input task description information in a session interface, the method displays the corresponding task execution workflow in the information area of the session interface. The task execution workflow includes multiple task nodes with an execution order, and each task node is configured with a task execution agent determined according to its task type. When a task execution operation triggered by this task execution workflow is received, the task execution agents corresponding to each task node are sequentially invoked to execute the task, and the task execution screen is displayed in the task live streaming area of the session interface, presenting the process of the task execution agent simulating the user's task execution. This disclosure can generate multiple task nodes based on the user-input task description information, configure task execution agents for each task node according to its task type, execute tasks by invoking each task execution agent, and display the task execution screen on the session interface. Therefore, this disclosure not only utilizes task execution agents to execute complex tasks for users but also displays the task execution screen to users during the task execution process, increasing the transparency of task execution and enriching the interactive functionality of using artificial intelligence models to execute complex tasks for users.
[0028] For ease of understanding, embodiments of this disclosure provide a task execution method, which can be executed by a task execution device, wherein the device can be implemented in software and / or hardware, and is generally integrated into an electronic device. Reference Figure 1 The flowchart below illustrates a task execution method provided in this embodiment of the present disclosure, wherein the method includes: S101: In response to the task description information entered in the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface.
[0029] The task execution workflow includes multiple task nodes with an execution order relationship generated based on the task description information. Each task node is configured with at least one task execution agent, which is determined based on the task type corresponding to the task node.
[0030] In this embodiment of the disclosure, the task description information includes the task content described in natural language, and the session interface is used to receive the task description information input by the user.
[0031] In one optional implementation, after receiving the task description information input by the user through the session interface, the large language model generates a task execution workflow based on the task description information. This task execution workflow is used to plan the execution process of the task corresponding to the task description information. Specifically, the large language model parses the input task description information to determine the task elements and generates a task execution workflow based on the task elements, where task elements refer to key task information.
[0032] In this embodiment of the disclosure, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface. For example... Figure 2 The diagram shown is a schematic of a page provided in an embodiment of this disclosure, wherein the session interface 200 includes an information area 201 and a task live streaming area 202.
[0033] In one optional implementation, after receiving the task description information input by the user through the input box on the session interface 200, the task execution workflow corresponding to the task description information is displayed in the information area 201 of the session interface. The task execution workflow may include multiple task nodes generated based on the task description information, and these task nodes have an execution order relationship. For example... Figure 2 The task nodes ①-⑤ shown have an execution order relationship. Each task node displays its corresponding task execution content. For example, the task execution content corresponding to task node ① is "Task Planning - Defining Query Target and Path". The task execution content corresponding to each task node in the task execution workflow is generated by the large language model based on the task description information.
[0034] In this embodiment, different task execution agents are used to handle different types of tasks. After generating the task execution workflow, a task execution agent can be determined based on the task type corresponding to each task node in the workflow, and this agent can be configured as the corresponding task node to execute the task of that node. Specifically, the task execution agent can proxy the execution of the task of the corresponding task node. For example, the task execution agent can include an agent for performing information query tasks, an agent for performing object selection tasks, an agent for performing convenient operation tasks, and an agent for performing extended tasks. This embodiment supports dynamic expansion of the task execution agent.
[0035] In one optional implementation, each task node in the task execution workflow can be configured with one or more task execution agents, which can be determined according to the task type of the task node.
[0036] S102: In response to the task execution operation triggered for the task execution workflow, the task execution agent corresponding to each task node in the task execution workflow is called in sequence to execute the task, and the task execution screen is displayed in the task live broadcast area of the session interface.
[0037] The task execution screen is used to present the process of the task execution agent simulating the user performing a task.
[0038] In this embodiment of the disclosure, after receiving a task execution operation triggered by a task execution workflow for the information area of the session interface, the task execution agent configured for each task node in the task execution workflow is called in sequence to execute the task. During the execution of the task, the task execution screen is displayed synchronously in the task live broadcast area of the session interface.
[0039] like Figure 2 The task execution screen is displayed in the task live streaming area 202 shown, which is used to present the process of the task execution agent simulating the user to perform the task.
[0040] In one optional implementation, before receiving a task execution operation triggered by the task execution workflow in the information area of the session interface, the user can also trigger a modification operation for the task execution workflow. After receiving the modification operation for the task execution workflow, a workflow modification interface is displayed, and after receiving the modified content entered in the workflow modification interface, the modified task execution workflow is updated and displayed in the information area. Subsequently, the user can trigger a task execution operation for the modified task execution workflow. Specifically, the modified task execution workflow is generated based on the entered modified content, the original task execution workflow, and the entered task description information.
[0041] In another optional implementation, during task execution, task progress information can be displayed in the information area of the session interface to reflect the progress of task execution, so that users can be informed of the task execution progress of the task execution workflow in a timely manner. Optionally, the task execution progress information of task nodes in the task execution workflow can be displayed in the information area, such as a progress of 20%, which indicates that the overall task execution workflow is 20% complete.
[0042] In another alternative implementation, task nodes in different states can be displayed in an information area to reflect the task execution progress of task nodes in the task execution workflow.
[0043] like Figure 2 The information area 201 shown displays task nodes in different states. Task node ① is in the completed state, task node ② is in the executing state, and task nodes ③-⑤ are all in the inactive state. The different states of the task nodes reflect the progress of task execution in the task execution workflow.
[0044] To achieve transparency in the task execution process, this embodiment of the disclosure can also display the task execution flow content corresponding to the task node in the information area of the session interface during the execution of a task by calling the task execution agent of any task node (hereinafter referred to as the first task node) in the task execution workflow. The task execution flow content includes the execution steps of the task execution agent corresponding to the task node.
[0045] like Figure 2 The information area 201 shown displays the task execution process content 203 corresponding to the task node that is currently executing, so that users can understand the task execution process in a timely manner and improve the transparency of task execution.
[0046] Based on this, the embodiments of this disclosure can also synchronously display the task execution details information corresponding to the first task node on the content interface during the process of calling the task execution agent corresponding to the first task node to execute the task. The task execution details information includes the execution result information corresponding to each execution step of the task execution agent corresponding to the first task node.
[0047] like Figure 2 The content interface 204 and the session interface 200 are independent of each other. During the task execution process in the task execution workflow, the content interface 204 is used to synchronously display the task execution details 205 corresponding to the task node that is currently executing. By synchronously displaying the task execution details, the transparency of the task execution process can be further improved, thereby increasing the user's trust in the task execution results.
[0048] Building upon this, the content interface 204 can also simultaneously display task progress information 207 corresponding to the task execution workflow within the information area 201 to reflect the progress of task execution. Clicking on any task node in the task progress information 207 will trigger the display of the corresponding task execution details on the content interface 204.
[0049] In another optional implementation, during the process of calling the task execution agent corresponding to the first task node to execute the task, task execution prompts can be displayed synchronously on the upper layer of the task execution screen displayed in the task live broadcast area to inform the user of the task execution process currently presented on the task execution screen.
[0050] like Figure 2 The task execution screen displayed in the task live streaming area 202 shown has an overlay area 206 on top. Task execution prompts are displayed in the overlay area 206 to inform the user of the current task execution process and help the user understand the current execution content of the task.
[0051] In this embodiment of the disclosure, after all tasks corresponding to each task node in the task execution workflow in the information area of the session interface have been completed, the task execution result is obtained and displayed on the session interface.
[0052] In the task execution method provided in this embodiment, after receiving input task description information in the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface. The task execution workflow includes multiple task nodes with an execution order relationship, and each task node is configured with a task execution agent determined according to its task type. When a task execution operation triggered by the task execution workflow is received, the task execution agents corresponding to each task node are sequentially invoked to execute the task, and the task execution screen is displayed in the task live streaming area of the session interface to present the process of the task execution agent simulating the user's task execution.
[0053] This embodiment of the disclosure can generate multiple task nodes based on the task description information input by the user, configure task execution agents for each task node according to its task type, execute tasks by calling each task execution agent, and display the task execution screen on the session interface. Therefore, this embodiment of the disclosure can not only use task execution agents to execute complex tasks for users, but also display the task execution screen to users during the task execution process, increasing the transparency of task execution and enriching the interactive functions of using artificial intelligence models to execute complex tasks for users.
[0054] Since the execution of a task by calling a task execution agent may involve execution steps involving user personal information such as permission verification and login verification, this embodiment of the present disclosure can also suspend the execution of the task and allow the user to take over the handling when the above-mentioned interruption event is detected during the execution of the task.
[0055] Specifically, during the execution of a task by the task execution agent corresponding to any task node (hereinafter referred to as the second task node) in the task execution workflow displayed in the information area of the call session interface, if a preset interruption event is detected, the task execution is paused and interruption information is displayed. The interruption information describes the detected interruption event. Specifically, the interruption event can be an event requiring user intervention during the execution of the task by the task execution agent, such as login events, payment events, or events involving user personal information input, or events involving user personal decisions, such as user preference information adjustment events.
[0056] like Figure 3 As shown, this is another page diagram provided in an embodiment of the present disclosure. In the information area 201 of the session interface 200, a task execution workflow is displayed. During the task execution process of the task execution agent corresponding to task node ③, a login event is detected, the task execution is paused, and an interruption message 302 is displayed.
[0057] Upon receiving an object access operation triggered by an interruption message, the object access interface is displayed, and the detected interruption event is processed based on this interface. In response to the completion message for the interruption event, the task execution agent corresponding to the second task node is invoked to continue task execution.
[0058] like Figure 3 As shown, upon receiving a selection of the "I will complete" option, the object access interface 305 is displayed. Alternatively, a takeover control 304 and a pause control are displayed in the task live streaming area 202 of the session interface 200. The user can trigger the takeover control 304 to display the object access interface 305. The task execution can be paused by triggering the pause control. For easier user operation, the task live streaming area 202 can be enlarged to the object access interface 305. The object access interface is a user-controlled interface, such as a user-controlled browser interface. The user can handle interruption events on the object access interface 305 by inputting information or triggering interactive operations.
[0059] Upon completion of the interruption event processing message, the task execution agent corresponding to the second task node can be automatically invoked to continue executing the task, or the user can trigger the "Restore Agent Mode" control 306 on the object access interface 305 to invoke the task execution agent corresponding to the second task node to continue executing the task, and the object access interface 305 will restore the task live broadcast area 202 of the display session interface 200.
[0060] In practical applications, after the task execution agent corresponding to each task node in the task execution workflow completes its task execution, a task execution log for that task node is generated to record the task execution process and results of that task execution agent. In this embodiment of the disclosure, after the task execution agent corresponding to any task node completes its task execution, a viewing operation of the task execution log for that task node can be triggered.
[0061] like Figure 3 The task node ① in information area 201 shown is in the task completion state. Users can click the log viewing control 307 to trigger the display of the task execution log content in task node ① on the content interface 204, replaying the task execution process. Additionally, users can export the log content, etc.
[0062] The task execution method provided in this disclosure can generate multiple task nodes based on task description information input by the user, configure task execution agents for each task node according to its task type, execute tasks by calling each task execution agent, and display the task execution screen on the session interface. Therefore, this disclosure not only enables the use of task execution agents to execute complex tasks for users, but also displays the task execution screen to users during the execution process, increasing the transparency of task execution and enriching the interactive functions of using artificial intelligence models to execute complex tasks for users.
[0063] In addition, the embodiments of this disclosure can also handle interruption events involving user personal information during task execution through manual takeover, thereby improving the flexibility and controllability of task execution and enhancing the user experience.
[0064] To implement the above embodiments, this disclosure also proposes a task execution device. Figure 4 This is a schematic diagram of a task execution device provided in an embodiment of the present disclosure. The device can be implemented by software and / or hardware and is generally integrated into an electronic device. Figure 4 As shown, the device includes: The first display module 401 is used to display the task execution workflow corresponding to the task description information in the information area of the session interface in response to the task description information input in the session interface; wherein, the task execution workflow includes multiple task nodes with execution order relationship generated according to the task description information, each task node is configured with at least one task execution agent, and the at least one task execution agent is determined according to the task type corresponding to the task node; The task execution module 402 is used to respond to the task execution operation triggered by the task execution workflow, sequentially call the task execution agent corresponding to each task node in the task execution workflow to execute the task, and display the task execution screen in the task live broadcast area of the session interface; wherein, the task execution screen is used to present the process of the task execution agent simulating the user's task execution.
[0065] In one optional embodiment, the apparatus further includes: The second display module is used to display the task execution process content corresponding to the first task node in the information area of the session interface during the process of calling the task execution agent corresponding to the first task node in the task execution workflow to execute the task; wherein, the task execution process content includes the execution steps of the task execution agent corresponding to the first task node.
[0066] In one optional embodiment, the apparatus further includes: The third display module is used to display the task execution details information corresponding to the first task node on the content interface during the process of calling the task execution agent corresponding to the first task node to execute the task; wherein, the task execution details information includes the execution result information corresponding to each execution step of the task execution agent corresponding to the first task node.
[0067] In one optional embodiment, the apparatus further includes: The fourth display module is used to display task execution prompt information on the task execution screen displayed in the task live broadcast area during the process of calling the task execution agent corresponding to the first task node to execute the task; wherein, the task execution prompt information is used to indicate the task execution process currently presented on the task execution screen.
[0068] In one optional embodiment, the apparatus further includes: The fifth display module is used to display task progress information in the information area of the session interface during task execution; wherein the task progress information is used to reflect the progress of task execution.
[0069] In one optional embodiment, the apparatus further includes: The first interface display module is used to display the workflow modification interface in response to the modification operation triggered by the workflow for the task. The update display module is used to receive the modified content entered on the workflow modification interface and then update and display the modified task execution workflow in the information area; wherein, the modified task execution workflow is generated based on the modified content, the task execution workflow, and the task description information.
[0070] In one optional embodiment, the apparatus further includes: The interrupt module is used to pause task execution and display interrupt information if a preset interruption event is detected during the execution of a task by the task execution agent corresponding to the second task node in the task execution workflow. The second interface display module is used to respond to the object access operation for the interruption information, display the object access interface, and process the preset interruption event based on the object access interface. The calling module is used to respond to the processing completion message of the preset interruption event and call the task execution agent corresponding to the second task node to continue executing the task.
[0071] In one optional embodiment, the apparatus further includes: The log generation module is used to generate a task execution log corresponding to the third task node in response to a task execution completion message from the task execution agent corresponding to the third task node in the task execution workflow. The sixth display module is used to respond to the viewing operation of the task execution log corresponding to the third task node and display the log content in the task execution log in the content interface.
[0072] In the task execution device provided in this embodiment, after receiving input task description information at the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface. The task execution workflow includes multiple task nodes with an execution order relationship, and each task node is configured with a task execution agent determined according to its task type. When a task execution operation triggered by the task execution workflow is received, the task execution agents corresponding to each task node are sequentially invoked to execute the task, and the task execution screen is displayed in the task live streaming area of the session interface to present the process of the task execution agent simulating the user's task execution.
[0073] This embodiment of the disclosure can generate multiple task nodes based on the task description information input by the user, configure task execution agents for each task node according to its task type, execute tasks by calling each task execution agent, and display the task execution screen on the session interface. Therefore, the task execution device provided by this embodiment of the disclosure can not only use task execution agents to execute complex tasks for users, but also display task execution screens to users during the task execution process, increasing the transparency of task execution and enriching the interactive functions of using artificial intelligence models to execute complex tasks for users.
[0074] In addition to the methods and apparatus described above, this disclosure also provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to implement the task execution method described in this disclosure.
[0075] This disclosure also provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, they implement the task execution method described in this disclosure.
[0076] In addition, this disclosure also provides an electronic device, see [link to relevant documentation]. Figure 5 As shown, it may include: The electronic device includes a processor 501, a memory 502, an input device 503, and an output device 504. The number of processors 501 in the electronic device can be one or more. Figure 5Taking a processor as an example. In some embodiments of this disclosure, the processor 501, memory 502, input device 503, and output device 504 can be connected via a bus or other means, wherein, Figure 5 Taking the example of a connection between China and Israel via a bus.
[0077] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The input device 503 can be used to receive input digital or character information, and to generate signal inputs related to user settings and function control of the electronic device.
[0078] Specifically in this embodiment, the processor 501 loads the executable files corresponding to the processes of one or more applications into the memory 502 according to the following instructions, and the processor 501 runs the applications stored in the memory 502 to realize the various functions of the above-mentioned electronic device.
[0079] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0080] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A task execution method, characterized in that, The method includes: In response to task description information entered in the session interface, the task execution workflow corresponding to the task description information is displayed in the information area of the session interface; wherein, the task execution workflow includes multiple task nodes with execution order relationship generated according to the task description information, each task node is configured with at least one task execution agent, and the at least one task execution agent is determined according to the task type corresponding to the task node; In response to the task execution operation triggered by the task execution workflow, the task execution agent corresponding to each task node in the task execution workflow is called in sequence to execute the task, and the task execution screen is displayed synchronously in the task live broadcast area of the session interface; wherein, the task execution screen is used to present the process of the task execution agent simulating the user's task execution.
2. The task execution method according to claim 1, characterized in that, The method further includes: During the process of calling the task execution agent corresponding to the first task node in the task execution workflow to execute the task, the task execution process content corresponding to the first task node is displayed in the information area of the session interface; wherein, the task execution process content includes the execution steps of the task execution agent corresponding to the first task node.
3. The task execution method according to claim 2, characterized in that, The method further includes: During the process of calling the task execution agent corresponding to the first task node to execute the task, the task execution details information corresponding to the first task node is displayed on the content interface; wherein, the task execution details information includes the execution result information corresponding to each execution step of the task execution agent corresponding to the first task node.
4. The task execution method according to claim 2 or 3, characterized in that, The method further includes: During the process of calling the task execution agent corresponding to the first task node to execute the task, task execution prompt information is displayed on the task execution screen shown in the task live broadcast area; wherein, the task execution prompt information is used to indicate the task execution process currently presented on the task execution screen.
5. The task execution method according to claim 1, characterized in that, The method further includes: During the execution of a task, task progress information is displayed in the information area of the session interface; wherein, the task progress information is used to reflect the progress of task execution.
6. The task execution method according to claim 1, characterized in that, The method further includes: In response to a workflow-triggered modification operation performed on the task, a workflow modification interface is displayed; After receiving the modified content input on the workflow modification interface, the modified task execution workflow is updated and displayed in the information area; wherein, the modified task execution workflow is generated based on the modified content, the task execution workflow, and the task description information.
7. The task execution method according to claim 1, characterized in that, The method further includes: During the execution of a task by the task execution agent corresponding to the second task node in the task execution workflow, if a preset interruption event is detected, the task execution is paused and an interruption message is displayed. In response to an object access operation for the interruption information, an object access interface is displayed, and the preset interruption event is processed based on the object access interface; In response to the completion message of the preset interruption event, the task execution agent corresponding to the second task node is invoked to continue executing the task.
8. The task execution method according to claim 1, characterized in that, The method further includes: In response to the task execution completion message of the task execution agent corresponding to the third task node in the task execution workflow, a task execution log corresponding to the third task node is generated; In response to the viewing operation of the task execution log corresponding to the third task node, the log content in the task execution log is displayed on the content interface.
9. A task execution device, characterized in that, The device includes: The first display module is used to respond to the task description information input in the session interface and display the task execution workflow corresponding to the task description information in the information area of the session interface; wherein, the task execution workflow includes multiple task nodes with execution order relationship generated according to the task description information, each task node is configured with at least one task execution agent, and the at least one task execution agent is determined according to the task type corresponding to the task node; The task execution module is used to respond to the task execution operation triggered by the task execution workflow, sequentially call the task execution agent corresponding to each task node in the task execution workflow to execute the task, and display the task execution screen in the task live broadcast area of the session interface; wherein, the task execution screen is used to present the process of the task execution agent simulating the user's task execution.
10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method as described in any one of claims 1-8.
11. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method as described in any one of claims 1-8.
12. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method as described in any one of claims 1-8.