Task display method and device based on intelligent agent, computer equipment and storage medium

Abstract

The invention provides an agent-based task display method and device, computer equipment and a storage medium, and belongs to the field of artificial intelligence. The embodiment of the invention provides a scheme capable of performing foreground display on the action executed by the intelligent agent, an original black box execution mode is broken, a user can perform operations such as modification on any item in the workflow list based on the displayed workflow list so as to effectively guide the intelligent agent to accurately execute the task, and the user experience is improved. Therefore, the task execution process can generate the expected effect within the control range of the user, the accuracy of the task result is greatly improved, and the man-machine interaction efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and in particular to a task display method, apparatus, computer device, and storage medium based on intelligent agents. Background Technology

[0002] With the development of AI (Artificial Intelligence) technology, AI is increasingly being applied to various aspects of daily life. However, the current AI execution process is generally black-box, meaning that when users use AI to perform a task, they can only output questions or instructions to the AI, while the AI's processing runs in the background, directly providing answers or operation results to the user. Users cannot intervene in the AI's execution process. If the output answer or operation result does not meet expectations, the user needs to repeatedly input, which wastes both time and effort, and actually reduces the efficiency of human-computer interaction. Therefore, there is an urgent need for a task display method based on intelligent agents that can improve the efficiency of human-computer interaction. Summary of the Invention

[0003] This disclosure provides a task display method, apparatus, computer device, and storage medium based on intelligent agents, which can improve the efficiency of human-computer interaction. The technical solution of this disclosure is as follows:

[0004] According to one aspect of the embodiments of this disclosure, a task display method based on an intelligent agent is provided, including:

[0005] In response to the task's requirement information, a workflow list for the task is displayed. The workflow list includes multiple subtasks arranged in execution order. These multiple subtasks are generated by an agent based on the task's requirement information. The agent is used to automate the execution of the task based on a large model.

[0006] The agent is shown to execute the task based on the workflow list, and the execution progress of the subtask is displayed during the execution of any subtask among the plurality of subtasks;

[0007] In response to an adjustment operation on the task or any subtask, the task is executed based on the adjusted task or subtask.

[0008] According to another aspect of the embodiments of this disclosure, a task display device based on an intelligent agent is provided, comprising:

[0009] The list display unit is configured to display a workflow list of the task in response to the task's requirement information. The workflow list includes multiple subtasks arranged in execution order. The multiple subtasks are generated by an agent based on the task's requirement information. The agent is used to automate the execution of the task based on a large model.

[0010] The task display unit is configured to display the task executed by the agent based on the workflow list, and to display the execution progress of the subtask during the execution of any subtask among the plurality of subtasks;

[0011] The task display unit is further configured to execute the task based on the adjusted task or subtask in response to an adjustment operation on the task or any subtask.

[0012] In some embodiments, the task display unit is configured to highlight subtasks that are currently in execution among the plurality of subtasks in the workflow list.

[0013] In some embodiments, the task display unit is configured to display the agent executing the task based on the workflow list, which includes: if any subtask is completed, displaying the subtask in the workflow list as being in a completed state.

[0014] In some embodiments, the task display unit is configured to display the steps being executed in any of the plurality of subtasks during the execution of the subtask; and to display the subtask result of the subtask if the subtask is completed.

[0015] In some embodiments, the task display unit is further configured to display setting options for each subtask, the setting options being used to configure whether the execution of the subtask is visible;

[0016] In response to the settings option of the first subtask being set to invisible, the execution progress of the first subtask will not be displayed during its execution.

[0017] The task display unit is also configured to display the execution progress of the second subtask during its execution, in response to the setting option of the second subtask being set to visible.

[0018] In some embodiments, the task display unit is further configured to display an interaction reference option, which is used to set whether to reference the user's historical interaction data when displaying the task;

[0019] The task display unit is configured to display the execution progress of the third subtask during the execution of the third subtask in response to the interaction reference option being set to reference historical interaction data. The third subtask is a subtask among the plurality of subtasks in which the user has performed interactive operations based on the historical interaction data.

[0020] In some embodiments, the task display unit is further configured to perform at least one of the following: display at least one evaluation data of the subtask result of the subtask; if the number of subtask results of the subtask is multiple, display comparison data between the subtask results based on the evaluation data of each subtask result.

[0021] In some embodiments, the task display unit is further configured to re-execute the subtask in response to a modification operation on the subtask result of the subtask, so as to obtain a new subtask result.

[0022] In some embodiments, the task display unit is further configured to execute the task based on the modified workflow list in response to a modification operation on the workflow list.

[0023] In some embodiments, the task display unit is further configured to, in response to a confirmation operation on the workflow list, execute the task based on the workflow list through the agent; display a countdown, and, in response to the end of the countdown, execute the task based on the workflow list through the agent.

[0024] In some embodiments, the task display unit is further configured to display requirement information for at least one candidate task; in response to a selection operation of the requirement information for any candidate task, the requirement information of the selected candidate task is output as the requirement information for the task.

[0025] According to another aspect of the embodiments of the present disclosure, a computer device is provided, the computer device comprising:

[0026] One or more processors;

[0027] Memory used to store the executable program code of the processor;

[0028] The processor is configured to execute the program code to implement the aforementioned agent-based task display method.

[0029] According to another aspect of the present disclosure, a computer-readable storage medium is provided that, when program code in the computer-readable storage medium is executed by a processor of a computer device, enables the computer device to perform the above-described agent-based task display method.

[0030] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the above-described agent-based task display method.

[0031] This disclosure provides a solution that displays the actions performed by an intelligent agent in the foreground, breaking away from the original black-box execution method. This allows users to modify any item in the displayed workflow list, effectively guiding the intelligent agent to accurately execute tasks. As a result, the task execution process is within the user's control, producing the expected results, greatly improving the accuracy of task results and enhancing human-computer interaction efficiency.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0034] Figure 1 This is a schematic diagram illustrating the implementation environment of an agent-based task display method according to an exemplary embodiment.

[0035] Figure 2 This is a flowchart illustrating an agent-based task display method according to an exemplary embodiment.

[0036] Figure 3 This is a flowchart illustrating another agent-based task display method according to an exemplary embodiment.

[0037] Figure 4 This is a schematic diagram illustrating an agent-based task page according to an exemplary embodiment.

[0038] Figure 5 This is a schematic diagram illustrating an agent-based task session page according to an exemplary embodiment.

[0039] Figure 6 This is a schematic diagram illustrating an agent-based task session page according to an exemplary embodiment.

[0040] Figure 7 This is a schematic diagram illustrating an agent-based task session page according to an exemplary embodiment.

[0041] Figure 8 This is a block diagram illustrating an agent-based task display device according to an exemplary embodiment.

[0042] Figure 9 This is a block diagram illustrating a terminal according to an exemplary embodiment. Detailed Implementation

[0043] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0044] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0045] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0046] Figure 1 This is a schematic diagram illustrating an implementation environment for an agent-based task display method according to an exemplary embodiment. See also Figure 1 The implementation environment specifically includes: terminal 101 and server 102. Terminal 101 and server 102 can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0047] Terminal 101 is at least one of the following devices: smartphone, smartwatch, desktop computer, laptop, MP3 player, MP4 player, and laptop computer. Terminal 101 runs an application that supports intelligent agent services. Users can log in to this application through Terminal 101 to access the services provided by the application. For example, users can perform corresponding tasks through this application on Terminal 101, where the application can refer to any application that embeds intelligent agent services.

[0048] Terminal 101 generally refers to one of a plurality of terminals; this embodiment uses terminal 101 as an example. Those skilled in the art will understand that the number of terminals can be more or less. For example, there may be several terminals, or dozens or hundreds of terminals, or even more. This disclosure does not limit the number of terminals or the type of device.

[0049] Server 102 can be at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Server 102 provides background services for applications supporting agent-based task display. Server 102 can connect to terminal 101 via a wireless or wired network. Server 102 can provide the terminal with live stream forwarding and live stream-related database services, and of course, other types of video services. In some embodiments, the number of servers may be more or fewer, and this disclosure does not limit this. Of course, server 102 may also include other functional servers to provide more comprehensive and diversified services.

[0050] Figure 2 This is a flowchart illustrating an agent-based task display method according to an exemplary embodiment. See also: Figure 2 Using a computer device as the executing entity, this method includes the following steps:

[0051] In step 201, in response to the task's requirement information, the computer device displays a workflow list for the task. The workflow list includes multiple subtasks arranged in execution order. These subtasks are generated by an agent based on the task's requirement information. The agent is used to automate the execution of the task based on a large model.

[0052] Here, "task" refers to any task that can be performed by an intelligent agent. For example, a text-to-image task, that is, a task that generates images or videos based on text, or an image processing task, that is, a task that further optimizes an input image, etc. This disclosure does not limit the scope of the task. Correspondingly, the intelligent agent used to perform the task can vary depending on the task. Different intelligent agents of the application can be invoked to perform different tasks. An intelligent agent refers to an AI model, which is a model trained to perform the above-mentioned tasks, and can also be called a large model or a large language model, etc.

[0053] Among them, the intelligent agent can call a large model to automatically execute tasks. The intelligent agent can call the corresponding large model based on different tasks, and use the task requirements information as the input parameters for calling the large model, and then perform analysis and processing through the large model.

[0054] The above tasks can be triggered through the task page, which provides a task entry point. Users can input or select task requirements by interacting with the task entry point, and then trigger the execution of the task based on the requirements.

[0055] For a task, after the computer device obtains the task's requirements information, it can generate a workflow list based on this information through an intelligent agent. This workflow list includes the various steps of the task, which are multiple subtasks. Each step has a certain execution order, meaning that the multiple subtasks also have a certain execution order. When the computer device displays the task's workflow list, it will arrange the subtasks according to the execution order, so that the user can intuitively observe the task content of the subtasks included in the workflow list and intuitively understand the execution order of each subtask, thus achieving a clear understanding of what to execute and when to execute.

[0056] In step 202, the computer device displays the intelligent agent executing tasks based on the workflow list, and displays the execution progress of any subtask during the execution of multiple subtasks.

[0057] During task execution, the progress of subtasks can be displayed according to their actual execution status. For example, it can show that a subtask has been completed or that a subtask is being executed. The execution result of the subtask can also be displayed.

[0058] In step 203, in response to the adjustment operation on the task or any subtask, the computer device executes the task based on the adjusted task or subtask.

[0059] By displaying the execution progress, users can intuitively perceive the task execution and thus perform timely operations such as pausing, modifying, and restarting to control the task execution. If the content of the task or subtask is adjusted, it can continue to be executed according to the workflow list based on the adjusted task or subtask, or be re-executed based on the workflow list to output the task results.

[0060] This disclosure provides a solution that displays the actions performed by an intelligent agent in the foreground, breaking away from the original black-box execution method. This allows users to modify any item in the displayed workflow list, effectively guiding the intelligent agent to accurately execute tasks. As a result, the task execution process is within the user's control, producing the expected results, greatly improving the accuracy of task results and enhancing human-computer interaction efficiency.

[0061] Figure 3 This is a flowchart illustrating an agent-based task display method according to an exemplary embodiment. See also: Figure 3 Taking a computer device as the executing entity as an example, the method includes the following steps:

[0062] In step 301, in response to the task's requirement information, the computer device displays a workflow list for the task, which includes multiple subtasks arranged in execution order, and the multiple subtasks are generated by the agent based on the task's requirement information.

[0063] Computer devices can provide the above-mentioned task execution functions through a task page, where users can trigger interaction with the intelligent agent by entering their requirements. See also Figure 4 ,Should Figure 4 The image shows a task page, which includes input boxes. Users can interact with the agent by entering their requirements, thereby controlling the agent to perform corresponding tasks. In some embodiments, the task page can also provide requirements information for candidate tasks for reference or reuse. That is, the computer device displays requirements information for at least one candidate task. In response to selecting any candidate task's requirements information, the selected candidate task's requirements information is output as the task's requirements information. This candidate task's requirements information can be requirements information for tasks created by the user in the past, or requirements information for some general tasks, thus providing a reference for the user's input. Users can refer to the sentence structure for input, thereby lowering the barrier to entry for the agent and improving input accuracy. Alternatively, users can directly select existing requirements information through a selection operation, eliminating the need for manual input and improving human-computer interaction efficiency.

[0064] After obtaining the task requirements, the computer device can generate multiple subtasks based on these requirements using an intelligent agent. These subtasks correspond to various steps of the task, and these steps can be executed by the same intelligent agent or by calling different intelligent agents. This embodiment does not limit this. When the computer device displays the task's workflow list, it can display the multiple subtasks from top to bottom according to their execution order, such as... Figure 5 As shown. When displaying subtasks, the task name and content of each subtask can be shown. For example, for the "Text-to-Image" task, it can include five subtasks such as creative analysis, script writing, image material preparation, video packaging, and video generation. Corresponding to each subtask, the task content is also displayed. For example, for creative analysis, it displays "Search for ** materials based on ***" and "Analyze the video for you," explaining that the subtask includes two stages: first, searching for reference materials (i.e., video materials) for the user, and then analyzing the searched materials for the user, etc. Of course, the task content can also include operation instructions. For example, when the user needs to select an image, it can display "Click the control to add an image," thereby guiding the user to perform similar operations according to the operation instructions.

[0065] In some embodiments, the task page also provides session creation controls, such as Figure 5 The “New Session” control in the document allows for the quick creation of new sessions, which are pages for interacting with the agent. When a new session is started, existing sessions can be temporarily stored or processed in parallel with the new session. This disclosure does not limit this aspect.

[0066] In step 302, the computer device displays a countdown, and in response to the countdown ending, the agent executes the task based on the workflow list.

[0067] In this embodiment, the computer device may provide a default function, such as displaying a countdown timer to provide the user with an opportunity to make modifications. Once the countdown ends, the computer device automatically executes the task based on the generated workflow list through an intelligent agent. In some embodiments, the computer device may also provide a confirmation execution control, allowing the user to trigger the intelligent agent to execute the task based on the confirmation operation of the control. Thus, by confirming the workflow list, the task can be executed by the intelligent agent based on the workflow list without waiting for a countdown.

[0068] See Figure 5 The task page also includes a pause / modify control 501 and a confirm / execute control 502. The pause / modify control 501 is used to pause task execution and modify the content of the task or subtask. The confirm / execute control 502 is used to start the task execution process. In response to a trigger operation on the pause / modify control 501, task execution can be paused, and upon receiving a modification operation on a subtask in the workflow list, the task will be executed based on the modified workflow list. After modification, the task can be restarted to continue execution.

[0069] In step 303, the computer device highlights the subtasks that are currently in the execution state among multiple subtasks in the workflow list.

[0070] To allow users to intuitively understand the currently executing task, computer devices can highlight tasks that are in the execution state. This highlighting can include methods such as highlighting, changing the font size, and dynamic display; this embodiment does not limit the specific method used. Changing the font size can involve increasing the font size of subtasks that are currently executing or decreasing the font size of subtasks that are not currently executing; alternatively, it can involve keeping the font color of subtasks that are currently executing unchanged while lightening the font color of subtasks that are not currently executing. This embodiment does not limit the use of any of the above-mentioned highlighting methods.

[0071] In step 304, the computer device displays the steps being executed in any of the multiple subtasks during the execution of the subtask.

[0072] It should be noted that if the subtask involves multiple steps, an incremental approach can be used to gradually display the steps based on the agent's processing progress. This allows users to feel involved in the agent's processing and to intuitively understand the task's progress.

[0073] To further highlight subtasks that are currently executing and their progress, you can expand the page to display more execution details. See also Figure 6 ,Should Figure 6 The page on the left is the task page, displaying a workflow list. Task A is highlighted in the workflow list and is currently in execution. The right side uses an extended page to show the execution process of Task A. For example, if Task A is currently performing a search, a prompt can be displayed to inform the user that the search process in Task A is in progress. This avoids the user being anxious and confused, providing a stable and continuous visual progress and enhancing the user's sense of security.

[0074] In some embodiments, the computer device may also provide an option to display the execution of a subtask. For example, the computer device may display setting options for each subtask, which are used to configure whether the execution of the subtask is visible. In response to the setting option of a first subtask being set to invisible, the execution progress of the first subtask is not displayed during its execution. In response to the setting option of a second subtask being set to visible, the execution progress of the second subtask is displayed during its execution. Visibility and invisibility refer to whether the subtask is displayed on the computer device's interface. By providing settings for visible and invisible subtasks, overly complex page displays can be avoided, achieving better transparency. Users can choose which subtasks to display and which to hide based on the processing stage they are interested in, thereby greatly improving display and interaction efficiency.

[0075] In step 305, if the subtask is completed, the computer device displays the subtask result.

[0076] Once any subtask is completed, the computer device can display the subtask result to the user, which is the execution result of the subtask. See [link to relevant documentation]. Figure 7For example, taking the above-mentioned text-to-image task as an example, creative analysis includes two stages: material search and material analysis. During the material search process, the system can first display "Searching for materials for you based on ***", and when the system finds the corresponding materials, it can display "The following materials have been found for you based on ***", with the found materials displayed below. Then, in the material analysis stage, it can display "Analyzing the video for you", and show the video analysis results. These results can display the video logic obtained from the video analysis, and show representative images from the video for each stage of the video logic. This embodiment does not limit this aspect.

[0077] In some embodiments, the computer device provides a modification function during the execution of subtasks. Users can modify the execution conditions of the subtask process to re-execute or continue the subtask based on the modified execution conditions, thereby adjusting the execution of the entire task. The subtask execution conditions refer to certain limiting conditions when executing a subtask. For example, for a subtask used for searching, the limiting conditions could be the search time range, the search data source, etc. In some embodiments, during the execution of subtasks, users can also modify the subtask results of the subtask process to re-execute or continue the subtask based on the modified subtask results, thereby adjusting the execution of the entire task. The subtask result refers to the output result of the subtask and the output result at any stage of the subtask. Because there are data dependencies between different stages within a subtask, and also between different subtasks, adjustments to these results can affect task execution, thereby improving the accuracy of the task execution results. Moreover, since this adjustment is made during task execution, i.e. before the task is completed, subsequent subtasks of this subtask may not have been executed yet. In a black-box execution method, if the execution result is unsatisfactory, it can only be re-executed. Compared to a black-box method, the method provided by this disclosure embodiment greatly reduces the amount of data processed, thereby improving processing efficiency.

[0078] In some embodiments, the above modifications can be triggered based on operations on the content to be modified. For example, for the results of a subtask, when a hover operation of the cursor on the subtask result is detected, it can be determined that the user wants to modify the subtask result, and a search can be triggered to display the subtask results found again.

[0079] In some embodiments, the computer device may also display at least one evaluation data point of the subtask result of the subtask, so as to provide data reference for the user on whether to modify the subtask result. For example, for searched materials, it may provide the exposure conversion rate, click-through rate, click-to-conversion rate and completion rate of the materials, so as to optimize the execution process.

[0080] In some embodiments, if there are multiple subtask results, the computer device can also display comparative data between the subtask results based on the evaluation data of each subtask result. This comparative data can reflect the comparison of each subtask result across different dimensions, allowing users to select subtask results based on their preferred dimensions. This significantly improves the intelligence of the interaction. Furthermore, because intervention functions are provided in this process, the accuracy of results at each stage can be guaranteed, avoiding repeated execution due to unsatisfactory output, thus greatly improving the efficiency of human-computer interaction.

[0081] It should be noted that the above modifications to the workflow list of the task and the modifications to the subtasks can be performed at any time during task execution, and this disclosure does not limit this.

[0082] In some embodiments, the computer device can also provide the user's historical operations to determine which subtasks' execution progress to display. The user's past operations can reflect the processing stage the user is interested in. Correspondingly, the computer device can display an interactive reference option, which is used to set whether to reference the user's historical interaction data when displaying tasks. In response to the interactive reference option being set to reference historical interaction data, during the execution of the third subtask, the execution progress of the third subtask is displayed. The third subtask is the subtask among the plurality of subtasks for which the user has previously performed interactive operations based on the historical interaction data. For example, if the user has previously performed an intervention operation on the video creative analysis subtask, modifying the analyzed information, then based on this operation, the computer device can, when the interactive reference function is active, only display the third subtask, i.e., the execution progress of the video creative analysis subtask. This avoids overly complex page display and achieves better transparency. The user can choose which subtasks to display and which not to display based on the processing stage they are interested in, thereby greatly improving display and interaction efficiency.

[0083] In step 306, if any subtask in the workflow list is completed, the computer device displays that the subtask is in the completed state in the workflow list.

[0084] For subtasks that have been completed, a completion marker can be displayed in their corresponding location, such as... Figure 7 In the left diagram, if subtasks A, B, and C have been completed, a "√" is used to indicate that the subtask is in the completed state.

[0085] The above-described display of the workflow list and the execution of subtasks is an exemplary description of how a computer device displays an agent executing tasks based on the workflow list. When displaying an agent executing tasks based on the workflow list, different task content based on each subtask can also be displayed, along with corresponding controls. For example, when the user needs to actively import or select an image, an import control or multiple candidate images can be displayed on an extended page for the user to operate.

[0086] In step 307, the computer device displays the task result when the task is completed.

[0087] When the task is completed, the computer device outputs the task result. In order to perform further operations on the task result, the computer device can also provide a sharing control to quickly share the generated task result to the application. Of course, the computer device also provides a selection control to provide users with selection functions, so that users can select the task result through this selection function. Optionally, it can also provide, for example, a download control and a save control. The download control is used to store the generated task result in local storage space, while the save control is used to store the generated task result in storage space such as a database.

[0088] This disclosure provides a solution that displays the actions performed by an intelligent agent in the foreground, breaking away from the original black-box execution method. This allows users to modify any item in the displayed workflow list, effectively guiding the intelligent agent to accurately execute tasks. As a result, the task execution process is within the user's control, producing the expected results, greatly improving the accuracy of task results and enhancing human-computer interaction efficiency.

[0089] In the aforementioned process, by visualizing the execution of the intelligent agent, the "black box" of intelligent agent execution is broken, and the operation and data processing are displayed intuitively, achieving the goal of transparent execution. This allows users to shift from passively receiving information to actively witnessing it, enhancing their sense of security and trust. Furthermore, users can confirm, modify, interrupt, or restart the AI's execution tasks at any time, achieving full-process controllability, significantly improving interactive autonomy, and meeting personalized needs. Moreover, this process enables two-way dynamic collaboration, allowing visualization to drive two-way feedback between AI and users. Users can issue commands instantly based on the displayed information, and AI can respond quickly, optimizing the human-machine collaboration loop. For application scenarios such as material generation, precise control over material generation can be achieved. Users can view and adjust the generation process in real time, reducing result deviations and improving the quality and efficiency of material output.

[0090] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0091] Figure 8 This is a block diagram illustrating an agent-based task display device according to an exemplary embodiment. See also... Figure 8 The device includes a list display unit 801 and a task display unit 802.

[0092] The list display unit 801 is configured to display a workflow list of the task in response to the task's requirement information. The workflow list includes multiple subtasks arranged in execution order. The multiple subtasks are generated by an agent based on the task's requirement information. The agent is used to automatically execute the task based on a large model.

[0093] The task display unit 802 is configured to display the task executed by the intelligent agent based on the workflow list, and to display the execution progress of the subtask during the execution of any subtask among the plurality of subtasks;

[0094] The task display unit is further configured to execute the task based on the adjusted task or subtask in response to an adjustment operation on the task or any subtask.

[0095] In some embodiments, the task display unit is configured to highlight subtasks that are currently in execution among the plurality of subtasks in the workflow list.

[0096] In some embodiments, the task display unit is configured to display the agent executing the task based on the workflow list, which includes: if any subtask is completed, displaying the subtask in the workflow list as being in a completed state.

[0097] In some embodiments, the task display unit is configured to display the steps being executed in any of the plurality of subtasks during the execution of the subtask; and to display the subtask result of the subtask if the subtask is completed.

[0098] In some embodiments, the task display unit is further configured to display setting options for each subtask, the setting options being used to configure whether the execution of the subtask is visible;

[0099] In response to the settings option of the first subtask being set to invisible, the execution progress of the first subtask will not be displayed during its execution.

[0100] The task display unit is also configured to display the execution progress of the second subtask during its execution, in response to the setting option of the second subtask being set to visible.

[0101] In some embodiments, the task display unit is further configured to display an interaction reference option, which is used to set whether to reference the user's historical interaction data when displaying the task;

[0102] The task display unit is configured to display the execution progress of the third subtask during the execution of the third subtask in response to the interaction reference option being set to reference historical interaction data. The third subtask is a subtask among the plurality of subtasks in which the user has performed interactive operations based on the historical interaction data.

[0103] In some embodiments, the task display unit is further configured to perform at least one of the following: display at least one evaluation data of the subtask result of the subtask; if the number of subtask results of the subtask is multiple, display comparison data between the subtask results based on the evaluation data of each subtask result.

[0104] In some embodiments, the task display unit is further configured to re-execute the subtask in response to a modification operation on the subtask result of the subtask, so as to obtain a new subtask result.

[0105] In some embodiments, the task display unit is further configured to execute the task based on the modified workflow list in response to a modification operation on the workflow list.

[0106] In some embodiments, the task display unit is further configured to execute the task based on the workflow list by the agent in response to a confirmation operation on the workflow list;

[0107] Display a countdown timer, and in response to the countdown ending, execute the task based on the workflow list through the agent.

[0108] In some embodiments, the task display unit is further configured to display requirement information for at least one candidate task; in response to a selection operation of the requirement information for any candidate task, the requirement information of the selected candidate task is output as the requirement information for the task.

[0109] It should be noted that the agent-based task display device provided in the above embodiments is only illustrated by the division of the above-described functional units when displaying tasks based on agents. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the computer device can be divided into different functional units to complete all or part of the functions described above. In addition, the agent-based task display device and the agent-based task display method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0110] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0111] When a computer device is provided as a terminal, Figure 9 This is a block diagram illustrating a terminal 900 according to an exemplary embodiment. Figure 9 A structural block diagram of a terminal 900 provided in an exemplary embodiment of this disclosure is shown. The terminal 900 may be a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 900 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0112] Typically, terminal 900 includes a processor 901 and a memory 902.

[0113] Processor 901 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 901 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 901 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 901 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 901 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0114] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 902 are used to store at least one computer program, which is executed by the processor 901 to implement the agent-based task display method provided in the method embodiments of this application.

[0115] In some embodiments, the terminal 900 may also optionally include a peripheral device interface 903 and at least one peripheral device. The processor 901, memory 902, and peripheral device interface 903 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 903 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 904, a display screen 905, a camera assembly 906, an audio circuit 907, and a power supply 908.

[0116] Peripheral device interface 903 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 901 and memory 902. In some embodiments, processor 901, memory 902 and peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 901, memory 902 and peripheral device interface 903 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0117] The radio frequency (RF) circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 904 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit 904 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 904 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 904 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0118] Display screen 905 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 905 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 901 for processing. In this case, display screen 905 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 905, disposed on the front panel of terminal 900; in other embodiments, there may be at least two display screens 905, disposed on different surfaces of terminal 900 or in a folded design; in other embodiments, display screen 905 may be a flexible display screen, disposed on a curved or folded surface of terminal 900. Furthermore, display screen 905 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 905 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0119] The camera assembly 906 is used to acquire images or videos. In some embodiments, the camera assembly 906 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 906 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0120] The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 901 for processing, or to the radio frequency circuit 904 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 900. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0121] Power supply 908 is used to power the various components in terminal 900. Power supply 908 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 908 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0122] Those skilled in the art will understand that Figure 9 The structure shown does not constitute a limitation on terminal 900, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0123] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions, which can be executed by a processor of a computer device, such as a processor 901 of a terminal 900, to complete the above-described agent-based task display method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0124] This disclosure also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-described agent-based task display method.

[0125] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0126] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A task display method based on intelligent agents, characterized in that, The method includes: In response to the task's requirement information, a workflow list for the task is displayed. The workflow list includes multiple subtasks arranged in execution order. These multiple subtasks are generated by an agent based on the task's requirement information. The agent is used to automate the execution of the task based on a large model. The agent is shown to execute the task based on the workflow list, and the execution progress of the subtask is displayed during the execution of any subtask among the plurality of subtasks; In response to an adjustment operation on the task or any subtask, the task is executed based on the adjusted task or subtask.

2. The task display method based on intelligent agents according to claim 1, characterized in that, The description of the agent executing the task based on the workflow list includes at least one of the following: In the workflow list, the subtasks that are currently in the execution state are highlighted among the multiple subtasks; If any subtask is completed, the workflow list will show that the subtask is in the completed state.

3. The task display method based on intelligent agents according to claim 1, characterized in that, Displaying the execution progress of any of the plurality of subtasks during execution includes: During the execution of any of the plurality of subtasks, the steps being executed in that subtask are displayed; If the subtask is completed, the subtask result will be displayed.

4. The task display method based on intelligent agents according to claim 1, characterized in that, The method further includes: Displays the settings options for each subtask, which are used to configure whether the execution of the subtask is visible; In response to the settings option of the first subtask being set to invisible, the execution progress of the first subtask will not be displayed during its execution. Displaying the execution progress of any of the plurality of subtasks during execution includes: In response to the settings option of the second subtask being set to visible, the execution progress of the second subtask is displayed during its execution.

5. The task display method based on intelligent agents according to claim 1, characterized in that, The method further includes: The interaction reference option is used to set whether to reference the user's historical interaction data when displaying tasks; Displaying the execution progress of any of the plurality of subtasks during execution includes: In response to the interaction reference option being set to reference historical interaction data, during the execution of the third subtask, the execution progress of the third subtask is displayed. The third subtask is a subtask among the plurality of subtasks in which the user has performed interactive operations based on the historical interaction data.

6. The task display method based on intelligent agents according to claim 3, characterized in that, The method further includes any of the following: Display at least one evaluation data point of the subtask result of the subtask; If there are multiple subtask results, the comparison data between the subtask results is displayed based on the evaluation data of each subtask result.

7. The task display method based on intelligent agents according to claim 3, characterized in that, The method further includes any of the following: In response to a modification operation on the result of the subtask, the subtask is re-executed to obtain a new result. In response to a modification operation on the workflow list, the task is executed based on the modified workflow list; In response to a confirmation operation on the workflow list, the agent executes the task based on the workflow list; Display a countdown timer, and in response to the countdown ending, execute the task based on the workflow list through the intelligent agent; Display the requirement information of at least one candidate task, and in response to the selection operation of the requirement information of any candidate task, output the requirement information of the selected candidate task as the requirement information of the task.

8. A task display device based on an intelligent agent, characterized in that, include: The list display unit is configured to display a workflow list of the task in response to the task's requirement information. The workflow list includes multiple subtasks arranged in execution order. The multiple subtasks are generated by an agent based on the task's requirement information. The agent is used to automate the execution of the task based on a large model. The task display unit is configured to display the task executed by the agent based on the workflow list, and to display the execution progress of the subtask during the execution of any subtask among the plurality of subtasks; The task display unit is further configured to execute the task based on the adjusted task or subtask in response to an adjustment operation on the task or any subtask.

9. A computer device, characterized in that, The computer device includes: One or more processors; Memory used to store the executable program code of the processor; The processor is configured to execute the program code to implement the agent-based task display method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of a computer device, the computer device is enabled to perform the agent-based task display method as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the agent-based task display method according to any one of claims 1 to 7.

Images