Information display method and device, computer equipment and storage medium

Abstract

The invention relates to an information display method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining query content; displaying task planning nodes for the query content; under the condition that the display style of the task planning node represents that the task is executed, displaying a task planning thought aiming at the query content; displaying at least one task node under the condition that the display style of the task planning node represents that task execution is completed; the task nodes are used for representing tasks planned according to a task planning thought; the execution result of the task is used for obtaining a query result of the query content. By adopting the method, the generation quality and the generation efficiency of the query result can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to an information display method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the rapid development of computer technology, an intelligent dialogue system based on an artificial intelligence agent (AI Agent) appears. The intelligent dialogue system is an agent built on a large language model (LLM, Large Language Model) and has the ability of autonomous understanding, perception, planning, memory and tool use. In terms of technical architecture, the artificial intelligence agent changes from a process-oriented architecture to a goal-oriented architecture, aiming to complete complex tasks through the close combination of perception, thinking and action.

[0003] In the related art, a user inputs query content in a display interface, an artificial intelligence agent generates an answer to the query content, and the answer is displayed in the display interface. The above end-to-end display process lacks effective information display, thereby affecting the generation quality and efficiency of the answer. SUMMARY

[0004] Therefore, it is necessary to provide an information display method and device, computer equipment, computer readable storage medium and computer program product capable of improving the generation quality and efficiency of reply content in view of the above technical problems.

[0005] In a first aspect, the present application provides an information display method. The method comprises:

[0006] obtaining query content;

[0007] displaying a task planning node for the query content;

[0008] displaying a task planning idea for the query content when a display style of the task planning node represents a situation in task execution;

[0009] displaying at least one task node when the display style of the task planning node represents a situation of completed task execution; the task node is used to represent a task planned according to the task planning idea; and an execution result of the task is used to obtain a query result of the query content.

[0010] In a second aspect, the present application further provides an information display device. The device comprises:

[0011] an obtaining module configured to obtain query content;

[0012] a planning node display module configured to display a task planning node for the query content;

[0013] a planning thought display module configured to display a task planning thought for the query content when the display style of the task planning node represents a situation in which a task is being executed;

[0014] a task node display module configured to display at least one task node when the display style of the task planning node represents a situation in which the task is completed; the task node is used to represent a task planned according to the task planning thought; and an execution result of the task is used to obtain a query result of the query content.

[0015] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. The processor implements the steps of the information display method when executing the computer program.

[0016] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores a computer program. The computer program, when executed by a processor, implements the steps of the information display method.

[0017] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. The computer program, when executed by a processor, implements the steps of the information display method.

[0018] The information display method, device, computer device, computer readable storage medium, and computer program product can obtain query content, display a task planning node for the query content, and implement splitting of a complex task by executing a planning task represented by the task planning node, thereby improving the generation quality and efficiency of a reply content. Further, when the display style of the task planning node represents a situation in which a task is being executed, a task planning thought for the query content is displayed, and when the display style of the task planning node represents a situation in which the task is completed, at least one task node planned according to the task planning thought is displayed. On the one hand, the progress of task planning can be intuitively presented by changing the display style, and more information can be provided to a user. On the other hand, the implementation process of task planning can be ensured to meet expectations by visualizing the task planning thought and ensuring that a task planning action is executed after the user knows the task planning thought, thereby ensuring that a task used to obtain a query result can match actual demands, reducing the number of times of asking for query content, and improving the generation quality and efficiency of a query result. BRIEF DESCRIPTION OF DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a diagram illustrating the application environment of the information display method in some embodiments;

[0021] Figure 2 These are schematic diagrams illustrating the information display method in some embodiments;

[0022] Figure 3 This is a flowchart illustrating the information display method in some embodiments;

[0023] Figure 4 This is a schematic diagram of the display page of the task planning node in some embodiments;

[0024] Figure 5 This is a schematic diagram of the display page of a task node in some embodiments;

[0025] Figure 6 This is a schematic diagram of the task decomposition process in some embodiments;

[0026] Figure 7 This is a schematic diagram of the task decomposition process in some other embodiments;

[0027] Figure 8 This is a schematic diagram of the task decomposition results in some embodiments;

[0028] Figure 9 This is a timing diagram of the information display process in some embodiments;

[0029] Figure 10 This is a schematic diagram of the query results display page in some embodiments;

[0030] Figure 11 This is a schematic diagram of the display page for task execution results in some embodiments;

[0031] Figure 12 This is a flowchart illustrating the information display method in some other embodiments;

[0032] Figure 13 These are schematic diagrams comparing the solutions of this application with conventional technical solutions in some embodiments;

[0033] Figure 14 The following are schematic diagrams illustrating the core architecture and data flow of this application in some embodiments;

[0034] Figure 15This is a schematic diagram illustrating the complete workflow of information display in some embodiments;

[0035] Figure 16 This is a schematic diagram of backend state events and data structures in some embodiments;

[0036] Figure 17 This is a schematic diagram of the front-end state-color mapping protocol in some embodiments;

[0037] Figure 18 This is a structural block diagram of the information display device in some embodiments;

[0038] Figure 19 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0040] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0041] First, the key terms and definitions used in this application will be introduced:

[0042] Large language models: Large-scale AI models with natural language understanding and generation capabilities, such as GPT-4 and LLaMA, are the core engines that drive agents to perform task planning and decision-making.

[0043] An agent is an autonomous software entity capable of perceiving its environment, planning, invoking tools (or its own capabilities), and executing actions to achieve its goals. An agent can encapsulate complex logic and capabilities for solving specific types of problems.

[0044] Global Planning: This refers to a preliminary and complete sequence of task execution steps (such as "analysis-search-comparison-summary") generated by the planning agent at the beginning of task execution, based on the complex goals input by the user.

[0045] A Directed Acyclic Graph (DAG) is a graph data structure consisting of nodes and directed edges, without any cycles. In this invention, it is used for fine-grained decomposition and dependency modeling of global programming.

[0046] Task Node: The basic unit in a DAG, representing an atomic task that can be assigned to a specific Agent for execution.

[0047] Task Node State Machine: A set of lifecycle states defined for each task node in the DAG and driven by the scheduling engine. It is the data foundation of this visualization solution.

[0048] State-Color Mapping Protocol: A set of predefined rules for mapping the state machine of background task nodes to the colors of the front-end interface.

[0049] Real-time State Synchronization Channel: A two-way communication mechanism (such as WebSocket-based) connecting the backend scheduling engine and the frontend visualization interface, used to push changes in node state to the frontend in real time with low latency.

[0050] Dynamic DAG Viewport: A visual canvas used in the front end to render the DAG structure. It can dynamically and animatedly update the appearance of each node according to the state-color mapping protocol, providing users with a perceptible understanding of the system's workflow.

[0051] JSON Patch Incremental Update Protocol: A specification for incremental data updates based on JSON format. The backend only sends changed node states, task lists, or message content to the frontend via a real-time status synchronization channel in the form of JSON Patch operations (such as replace and add). The frontend applies these patches to update the view with minimal cost.

[0052] Dependency Edge: A directed edge in a Directed Acyclic Graph (DAG) connecting two task nodes, defining the execution order constraints between tasks. The edge "A→B" indicates that node A must complete successfully before node B begins.

[0053] Concurrent execution refers to the simultaneous scheduling and execution of task nodes in a DAG that do not have direct or indirect dependencies, in order to make full use of system resources and shorten the total execution time.

[0054] Summary & Merge Node: A special type of node in a DAG whose responsibility is to wait for all its preceding dependent nodes to finish executing, and then summarize, integrate, deduplicate, or refine the outputs of these nodes to generate a structured intermediate or final report.

[0055] The information display method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the application environment may include application terminal 102 and server terminal 104. Application terminal 102 and server terminal 104 can communicate via a communication network. This communication network can be a wired network or a wireless network. Therefore, application terminal 102 and server terminal 104 can be directly or indirectly connected via wired or wireless communication. For example, application terminal 102 can be indirectly connected to server terminal 104 via a wireless access point, or application terminal 102 can be directly connected to server terminal 104 via the Internet; this application does not impose any limitations on this.

[0056] The application terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Optionally, the application terminal 102 can have a client related to content query installed; this client can be an application, webpage, or mini-program. The server terminal 104 is the backend server corresponding to the client, or a server specifically designed to provide content query services. Furthermore, the server terminal 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The data storage system can store the data that the application terminal 104 needs to process. The data storage system can be set up separately, integrated into the server terminal 104, or placed in the cloud or on other computer devices.

[0057] In the embodiments of this application, such as Figure 2As shown, users can interact with application 102 and input query content 201. For example, the query content could be "Compare model A and model B, how much do they cost recently, and is it worth buying?" This query content can be further sent to server 104 to request the corresponding query results. Server 104 can obtain the query content, generate a planning task for the query content, and then application 102 can display a task planning node 202 representing this planning task. During the execution of the planning task, server 104 can send the task planning ideas for the query content to application 102, and then application 102 can display the task planning ideas 204 for the query content, while the task planning node's display style indicates task execution. For example, as... Figure 2 As shown, dynamic identifier 203 can indicate that a task is in progress. Server 104 can plan tasks for the query content according to this task planning approach to generate at least one task. Then, when the display style of the task planning node indicates that the task has been completed, application 102 can display the corresponding task node 205. For example, static identifier 206 is used to indicate that the task has been completed. Optionally, the static identifier 206 can display the task's execution time. This execution time could be, for example, 16 seconds. The task node 205 can include task nodes corresponding to multiple tasks, such as product price query, model parameter and performance comparison. The task execution result is used to obtain the query results for the query content. Figure 1 The query result can be fed back to the application terminal 102.

[0058] In some embodiments, such as Figure 3 As shown, an information display method is provided, which is executed by a computer device. In this embodiment, the method is applied to... Figure 1 Taking application terminal 102 as an example, the explanation includes the following steps:

[0059] Step S302: Obtain the query content.

[0060] The query content refers to the combination of information used to query and retrieve specific content. Optionally, the query content may include one or more elements from the following: explicit instructions, question statements, contextual background, and output format requirements, to provide sufficient and structured semantic constraints and task guidance, aiming to obtain accurate, relevant, and user-expected query results. Instructions or question statements can be used to describe the purpose of the content query. For example, the query content may include "I need to buy a tent, any purchasing advice?" or "Compare model A and model B, how much do they cost recently, and are they worth buying?", describing the query purpose in the form of a question. Similarly, the query content may include "Compare the horsepower, safety, and smart cockpit configuration of models A, B, and C," describing the query purpose in the form of an instruction. Contextual background describes the current situation and needs. For example, the query content "I like hiking and now want to go out and live in the mountains, I need to buy a tent, any purchasing advice?" includes the contextual background "I like hiking and now want to go out and live in the mountains." Output format requirements specify the output requirements of the query results, such as "Please give the results in list form."

[0061] Optionally, the search terms may not be limited to a single field and may include at least one of the following: healthcare, education, office work, and shopping.

[0062] Optionally, the query content can be entered in various ways, such as text or voice. In an exemplary embodiment, the application can display a query content input page, which includes a query content input box, allowing the user to enter their query content. Optionally, the application can also obtain the query content by collecting the user's voice.

[0063] Specifically, users can input their query content through the application, and the server can then obtain the corresponding query content by interacting with the application.

[0064] Step S304: Display the task planning node for the query content.

[0065] The task planning node identifies the planning tasks for the query content. In the specific implementation, after obtaining the query content, the server can perform task planning for that query content to obtain multiple tasks. Based on this, the application can display the task planning node for the query content.

[0066] Optional, such as Figure 2As shown, the application can display content cards for task planning nodes, showing the task title, description, and execution status. The task title could be, for example, "Make a Plan," and the task description could be, for example, "Comparison and Price of Model A Series." Optionally, the content card can also display the task type represented by the task planning node. Different task types can be represented by corresponding type icons, for example, such as... Figure 2 As shown, icon 207 represents a planning task, which analyzes the query content to determine the specific tasks that need to be performed to meet the user's needs.

[0067] In an optional embodiment, displaying a task planning node for the query content includes: displaying a content parsing node for the query content in a first display style; and displaying a task planning node for the query content when the content parsing node changes from the first display style to a second display style indicating successful execution.

[0068] The first display style is used to represent a task in progress. Optionally, each task typically undergoes multiple task state transitions during its lifecycle. When a task is waiting for its preceding tasks to complete, the corresponding task state is "waiting"; when the task's preceding tasks are empty or all preceding tasks have completed successfully but are temporarily awaiting allocation due to system resources, the corresponding task state is "pending"; when the task is executed, the corresponding task state is "running"; when the task executes successfully, the corresponding task state is "succeed"; when the task fails, the corresponding task state is "fail".

[0069] In practical implementation, the display style of a node can be associated with the task status of the task it represents to achieve state-driven visualization mapping. The display style can include at least one of the following: color, shape, status identifier, etc. Optionally, different colored task nodes can be displayed to represent different task states. For example, a gray task node indicates that it is waiting for resources; a yellow task node indicates that it is waiting for a preceding task to complete; a blue task node indicates that the task is executing; a green task node indicates that the task has been successfully executed; and an orange-red task node indicates that the task has failed.

[0070] In a specific implementation, after receiving the query content, the server can parse it to obtain the corresponding parsing results. In this case, the application can display the query content parsing node in a first display style, indicating that the task is in progress, to show that parsing is currently underway. When the content parsing node changes from the first display style to a second display style, indicating successful execution, it means that the content parsing is complete. At this point, the application can display the task planning node for the query content. Optionally, after the query content parsing is complete, the content parsing node can display a summary of the parsing results.

[0071] For example, when a user inputs a query, the server parses the content, and the application can then display the corresponding content parsing node on the display page. At this time, the display style of the content parsing node indicates that the task is in progress. Optionally, during the query parsing process, the content parsing node can display a summary of the query content. After the content parsing is complete, the server can further perform task planning. In this case, the display style of the content parsing node can indicate that the task execution is complete, displaying a summary of the parsing results and simultaneously displaying a task planning node for the query content. Figure 4 As shown, when the user inputs the query "Compare model A and model B, how much do they cost recently, and is it worth buying?", the content parsing node 401 can display the summary information "Compare model A and model B, how much do they cost recently, and is it worth buying?" while the task is being executed, and simultaneously display a dynamic icon 402 representing the progress of the task. Once content parsing is complete, the dynamic icon 402 will change to a static time icon 403 to represent the actual time taken for the content parsing process, and simultaneously display the task planning node 404 for the query content. Optionally, the content parsing node can also display summary information of the parsing results, such as "Compare model A and model B, what are their recent prices, and is it worth buying…".

[0072] In the above embodiments, when the content parsing node changes from the first display style representing task execution to the second display style representing successful execution, the task planning node for the queried content is displayed, which can intuitively show the process from content parsing to task planning and achieve a more detailed display of the execution process.

[0073] Step S306: If the display style of the task planning node indicates that the task is being executed, display the task planning ideas for the query content.

[0074] In this context, task planning strategy refers to a set of systematic thinking methods, strategies, and principles followed when planning tasks. In practical applications, when the display style of task planning nodes represents task execution, the server can first provide the application with the task planning strategy for the query content, and then the application can display this strategy. Optionally, the task planning strategy can be displayed via pop-ups or floating windows. Optionally, the task planning strategy can be displayed in areas of the display page that do not contain task nodes. For example,... Figure 4 As shown, the task planning idea 405 can be displayed above the task planning node 404 in a floating layer manner.

[0075] In an optional embodiment, the task planning approach can be displayed in a conversation panel. The conversation panel is an area used to display conversation information. Optionally, the task planning approach can be displayed in the conversation panel via a conversation. Optionally, a guiding statement may be included before the task planning approach displayed in the conversation panel. Figure 4 In the conversation panel 406, the guiding statement 407 displayed before the task planning approach 405 could be, for example, "I will solve the problem according to the following approach. If you wish to adjust the plan, please let me know."

[0076] Step S308: If the display style of the task planning node indicates that the task execution is completed, display at least one task node.

[0077] Among them, the task node is used to represent the task planned according to the task planning idea; the execution result of the task is used to obtain the query result of the query content.

[0078] In practical applications, once the task planning approach is confirmed, the server can plan tasks based on the query content according to that approach, resulting in at least one task. The application can then display the individual task nodes, indicating task completion, using the display style of the task planning nodes. Optionally, the server can also determine the execution order constraints between tasks based on the data flow dependencies between them. These execution order constraints can be represented by directed edges between task nodes.

[0079] For the query "Compare model A and model B, how much do they cost recently, and are they worth buying?", three tasks can be planned: product price query, model parameter and cost-effectiveness comparison, and generating a final purchase recommendation. Therefore, as follows: Figure 5 As shown, the application can display the task nodes corresponding to the three tasks mentioned above, and the execution results of these tasks are used to obtain the query results for the query content.

[0080] Optionally, the server can display at least one of the following in the target area corresponding to at least one task: task title, task description, task status, or execution time. For example, such as... Figure 5 As shown, the title information of task node 501 is "Commodity Price Inquiry", and the task description is "Retrieve the latest market prices of model A and model B, ensuring that the data is accurate and recent".

[0081] Optionally, the display style of a task node is used to represent the task status of the task represented by that task node. Optionally, the task status can include waiting for the preceding task to complete, pending, running, successful, and failed.

[0082] In an alternative embodiment, the server can identify the user's core intent by parsing the query content and matching keywords. Then, the server can decompose the complex request into a series of ordered tasks according to its internal predefined business process or decision tree.

[0083] In an optional embodiment, task execution can be achieved through an intelligent agent. Specifically, the planning task for the query content can be assigned to a planning agent, which parses the query content and performs global planning on the parsed content to obtain multiple tasks.

[0084] In this context, an intelligent agent can refer to an autonomous software entity capable of perceiving its environment, planning, invoking tools (or its own capabilities), and executing actions to achieve a goal. An intelligent agent typically encapsulates complex logic for solving a specific type of problem and possesses the ability to autonomously understand, perceive, plan, remember, and use tools. In an exemplary embodiment, the intelligent agent can employ a "thinking + action" reasoning pattern when determining the task of the query content. Thinking refers to the intelligent agent analyzing the current situation and considering what to do next; action refers to the actions performed by the intelligent agent, usually by invoking tools. Optionally, an intelligent agent can be implemented using a single process or through the collaborative efforts of multiple processes. For example, an intelligent agent can correspond to two processes, specifically a process responsible for decision-making and a process responsible for controlling the hardware. The deployment method of intelligent agents on physical machines is not unique. Optionally, the server can adopt a single-machine multi-agent mode, a multi-level multi-agent mode, or a hybrid deployment mode.

[0085] The aforementioned information display method retrieves query content and displays task planning nodes for that content. By executing the planned tasks represented by these nodes, it enables the breakdown of complex tasks, thereby improving the quality and efficiency of generated responses. Furthermore, when the display style of the task planning nodes indicates task execution is in progress, it displays the task planning logic for the query content. Conversely, when the display style indicates task completion, it displays at least one task node planned according to the task planning logic. On one hand, the change in display style visually presents the progress of task planning, providing users with more information. On the other hand, the visual display of the task planning logic ensures that users understand the logic before executing task planning actions, thus ensuring that the task planning process meets expectations. This guarantees that the tasks used to obtain query results match actual needs, reducing the number of follow-up queries and improving the quality and efficiency of query result generation.

[0086] In one embodiment, the task is obtained upon triggering a confirmation event for the task planning approach. In this embodiment, the information display method further includes: if task planning is completed according to the task planning approach, changing the display style of the task planning node from a first display style representing task execution in progress to a second display style representing task execution completion.

[0087] The first display style and the second display style are two different display styles. At least one of the following, such as color, shape, or status indicator, differs between the two display styles.

[0088] Specifically, upon triggering a confirmation event for the task planning approach, the server can perform task planning based on the confirmed approach, generating at least one task. When the task planning is complete, the application can change the display style of the task planning node from the first display style indicating task execution in progress to the second display style indicating task completion, and simultaneously display the task node corresponding to the planned task.

[0089] In the above embodiments, task planning is carried out after the task planning idea is confirmed, which can ensure that the implementation process of task planning meets the user's expectations, thereby ensuring that the tasks that obtain query results can match actual needs, which is conducive to improving the quality and efficiency of query result generation.

[0090] In one embodiment, the information display method further includes: obtaining feedback content regarding the task planning approach; and triggering a confirmation event for the task planning approach if the feedback content indicates approval of the task planning approach.

[0091] Feedback can be input in various ways, including text and voice. In an exemplary embodiment, the application can display the task planning approach and a feedback input box for that approach within a conversational panel. The user can then input their feedback in this box. Optionally, the application can also obtain feedback on the task planning approach by capturing the user's voice. For example,... Figure 4 As shown, the application can display the feedback content input box 408 below the task planning idea 405 according to the session order.

[0092] Optionally, upon receiving feedback, the application can perform semantic recognition on the feedback to determine whether it represents the task planning approach displayed by the user. If the feedback indicates acceptance of the task planning approach, a confirmation event for the task planning approach is triggered.

[0093] Optionally, the application can upload the received feedback to the server, which will then determine whether the feedback represents the task planning approach displayed by the user and send the feedback result back to the application.

[0094] In the above embodiments, it is possible to determine whether to trigger a confirmation event for the task planning idea by obtaining feedback content on the task planning idea. The task planning idea can be determined through interaction, which can ensure that the implementation process of task planning meets the user's expectations.

[0095] In one embodiment, the information display method further includes: displaying a new task planning approach obtained by adjusting the approach according to the feedback content when the feedback content indicates that the task planning approach is not approved.

[0096] As mentioned earlier, upon receiving feedback, the application can perform semantic recognition on the feedback to determine whether it represents the task planning approach displayed for the user's task. If the feedback indicates disapproval of the task planning approach, the application can adjust the currently provided task planning approach based on the feedback. The application can then display the new task planning approach adjusted according to the feedback and obtain feedback on the new approach.

[0097] Optionally, the task planning approach can undergo multiple rounds of feedback and adjustments until a confirmation event for the task planning approach is triggered.

[0098] In the above embodiments, when the feedback indicates that the task planning approach is not approved, a new task planning approach obtained by adjusting according to the feedback is displayed. This can support continuous improvement and evolution, ensure that the task planning approach can meet the user's expectations as soon as possible, and help improve work efficiency.

[0099] In one embodiment, the information display method further includes: displaying a timing component for the task planning approach; and, in response to the timing component ending its timeout, triggering a confirmation event for the task planning approach if no feedback content for the task planning approach is obtained.

[0100] The timing component can include countdown and clockwise components. The display format of the timing component is not unique. Optionally, the timing component can directly display the time value, use the filling or disappearing of a ring to represent the passage of time, use a horizontal bar chart to represent a progress bar, or use dynamically changing text to represent the passage of time. For example, such as... Figure 4 As shown, the timing component 409 includes the text "Please respond within 00:40, otherwise it will be automatically skipped". The "00:40" will decrease dynamically, and when it decreases to "00:00", it means the timing has ended.

[0101] Optionally, the timing component can be displayed in accordance with the task planning framework, such as below the task planning framework or in the upper right corner.

[0102] Optionally, if no feedback on the task planning approach is received by the timer component when the timer expires, a confirmation event for the task planning approach will be automatically triggered. If feedback on the task planning approach is received during the timer component's timing process, a confirmation event for the task planning approach can be triggered if the feedback indicates acceptance of the approach. If the feedback indicates disapproval, the task planning approach can be adjusted until a confirmation event for the task planning approach is triggered.

[0103] Optionally, the timing component can start timing when the task planning logic is fully displayed. Optionally, when adjusting the task planning logic, a new round of timing can start when the new task planning logic is fully displayed. For example, taking the case where timing ends after 40 seconds, the 40-second timing restarts after each adjustment of the task planning logic.

[0104] In the above embodiments, in response to the timing component ending its timeout, if no feedback content regarding the task planning approach is obtained, a confirmation event for the task planning approach is triggered. This enables the automatic triggering of the confirmation event, avoiding indefinite waiting and preventing blockage. It also improves work efficiency while ensuring that the task planning approach meets the user's expectations.

[0105] In an optional embodiment, the information display method further includes: displaying a skip guide control for the task planning approach; and triggering a confirmation event for the task planning approach in response to a triggering operation on the skip guide control.

[0106] The skip guide control can be displayed as a text link, button, icon button, etc. For example, the skip guide control can contain the text "Close" or "Skip". Optionally, the skip guide control can be displayed as a floating layer or on the same layer as the task planning logic. In an exemplary embodiment, such as... Figure 4 As shown, the skip guide control 410 can be displayed on the same content card as the timing component 409.

[0107] Specifically, the application can display a skip guide control for the task planning approach. Users can then trigger this skip guide control to indicate their acceptance of the task planning approach, and the application can respond to this trigger by issuing a confirmation event for the task planning approach. Optionally, users can initiate the skip guide control's activation by clicking or touching its location.

[0108] In the above embodiments, a skip guide control for the task planning approach is displayed, and in response to the triggering operation of the skip guide control, a confirmation event for the task planning approach is triggered. This enables flexible guidance, simplifies the confirmation method of the task planning approach, and can improve work efficiency while ensuring that the task planning approach meets the user's expectations.

[0109] In one embodiment, the information display method further includes: in response to a confirmation event for the task planning idea, canceling the display of the session panel to which the task planning idea belongs; and displaying the session entry element of the session panel corresponding to the task planning node.

[0110] The session entry element is used to restore the session panel when triggered. In specific applications, the application can display the task planning approach and a feedback input box for the task planning approach within the session panel via a conversation. The user can then input feedback through the session panel to confirm the task planning approach through a conversation with the server. In this scenario, the application can respond to the confirmation event for the task planning approach by canceling the display of the session panel containing the task planning approach and displaying the session entry element corresponding to the task planning node.

[0111] Optionally, the session entry element can correspond to the task planning node by displaying at least one of the following: location, color, shape, or associated identifier. For example, Figure 5In the context of the task planning node 404, the session entry element 502 is displayed in the lower right corner. The associated identifier can include at least one of the following: an icon, a letter label, or a dynamic connecting line. Optionally, the dynamic connecting line refers to the connecting line displayed when the session entry element or the task planning node is triggered, or when the mouse hovers over the session entry element or the task planning node.

[0112] Optionally, users can trigger the session entry element to request to view the session content in the session panel, and the application can then respond to the trigger operation on the session entry element to restore the display of the session panel.

[0113] In the above embodiments, in response to a confirmation event for the task planning approach, the display of the session panel to which the task planning approach belongs is canceled. This avoids the prolonged display of the session panel affecting the display of task nodes, ensuring the complete presentation of the task execution process. Corresponding to the task planning node, the session entry element of the session panel can support the restoration of the session panel's display, ensuring session persistence and recoverability, and guaranteeing the traceability of operations.

[0114] In an optional embodiment, the information display method further includes: displaying a session count identifier corresponding to the session entry element. The session count identifier indicates the number of historical sessions based on the session panel.

[0115] Optionally, the session count indicator can correspond to the session entry element through at least one of the following: display location, color, shape, or associated indicator. For example, the session count indicator can be placed directly next to or inside the session entry element, forming a visual block. For example, such as... Figure 5 As shown, the number "1" is displayed in the session entry element 502, which indicates that a historical session was involved in the process of confirming the task planning approach.

[0116] In one exemplary embodiment, the application can dynamically display a session count indicator when the user interacts with the session entry element. For example, when the mouse hovers over the session entry element, a number "1" appears.

[0117] In the above embodiments, by displaying the session count identifier in correspondence with the session entry element, the number of times the task planning approach has been adjusted can be presented intuitively. Within a limited display space, more and finer-grained information is provided to the user, thereby constructing a dynamic and traceable task evolution graph, which greatly enhances the traceability and continuity of the task planning process.

[0118] In one embodiment, the information display method further includes: for each task node, when the task represented by the task node is assigned to the corresponding task agent, displaying the task node according to a first display style representing the execution of the task.

[0119] In this process, any task is assigned if its corresponding prerequisite task has been completed, or if the task has no prerequisite task. When the task represented by the task node is assigned to the corresponding task agent, an execution start event for the assigned task can be triggered. Subsequently, the application can display the task node according to a first display style representing task execution. Optionally, a task can have one or more prerequisite tasks, and a task can serve as a prerequisite task for one or more other tasks.

[0120] In an optional embodiment, the server can implement task scheduling through a scheduling engine. Specifically, the scheduling engine can find target tasks whose prerequisite tasks have been completed or have no prerequisite tasks, add these target tasks to the ready task queue, and then check the available idle agent resources and the ready task queue. It then assigns the tasks in the queue to idle agents for execution, thereby triggering an execution start event for the assigned task and driving the application to display the task node assigned to the task in a first display style that indicates execution in progress.

[0121] Optionally, when there are multiple target tasks with completed prerequisite tasks or no prerequisite tasks, the server can allocate at least two target tasks to these task agents simultaneously based on the currently available agent resources, thereby achieving concurrent execution of at least two tasks. Concurrent execution of at least two tasks means having the ability to process at least two tasks within a certain period of time. These tasks can run simultaneously at the same time or alternately through rapid switching.

[0122] Optionally, scheduling techniques such as time-slice rotation can be used to alternately execute at least two tasks to achieve concurrent execution of at least two tasks. In this case, the display style of the task nodes corresponding to multiple target tasks assigned to the same task agent can be changed to the first display style; the display style of these task nodes can also be dynamically changed based on the time-slice rotation, and at any given time, only one of these task nodes will have the first display style representing the task execution.

[0123] Optionally, tasks can be assigned to different task agents to achieve parallel execution of multiple tasks. Parallel execution of at least two tasks means that within the execution time intervals of these tasks, there is at least one time period in which two tasks are executing simultaneously. In other words, the execution timelines of the tasks overlap macroscopically, but do not necessarily overlap completely. In this case, the task nodes of each parallel-executed task can be presented in the first display style.

[0124] In the above embodiments, when the task represented by the task node is assigned to the corresponding task agent, the task node is displayed according to the first display style representing the execution of the task. On the one hand, this can minimize the idle state of agent resources and improve the utilization rate of computing resources. On the other hand, each task can be executed by different agents, so that the parallel execution of each task does not block each other during the execution process, which is conducive to further improving work efficiency.

[0125] In one embodiment, displaying at least one task node includes: displaying content cards corresponding to at least one task, and displaying the corresponding task title and task type in the content cards.

[0126] In this process, each task is assigned to an idle agent if a matching task type exists. An agent is considered idle when it has not been assigned any tasks, has not performed any operations, and is waiting for new instructions. Specifically, the server can identify idle agents and assign at least two ready tasks to each agent in a one-to-one correspondence, enabling each agent to execute its assigned tasks in parallel.

[0127] Task type refers to a classification of tasks based on their core objectives, required operations, and the form of their output. It abstracts the specific content of the task and focuses on its solution pattern. Task types can include query, comparison, calculation, translation, etc.

[0128] In practical applications, specialized agents can be deployed for specific task types. This is understandable because specialized agents do not need to handle irrelevant logic, which improves response speed. Furthermore, lightweight, specialized agent deployment based on specific task requirements reduces resource consumption. In this scenario, the server can determine the task type for each task that is ready, and assign the task to a target agent that matches the task type if one of the available agents exists. For example, for query tasks, if a target agent for query tasks exists among the idle agents, the server can assign the task to that agent; if all idle agents are for non-query tasks, no task assignment is performed.

[0129] For the application side, at least one content card corresponding to each task can be displayed, with the corresponding task title and task type shown in the content card. If a task has an idle agent that matches its task type, it is assigned to that idle agent, and the content card corresponding to that task will be displayed in the first display style indicating that the task is in progress.

[0130] Optionally, the task type can be represented by at least one of the following: text, icon, etc. For example, a query task can be represented by a magnifying glass icon. In a specific implementation, the content card corresponding to the task can be displayed in the target area of ​​the display page.

[0131] In the above embodiments, the task type is displayed, and intelligent agents are matched according to the task type. Dedicated intelligent agents can be designed according to task requirements, so that intelligent agents do not need to deploy and process irrelevant logic, which can reduce resource consumption and improve response speed. At the same time, the system is decomposed into multiple dedicated intelligent agents according to task type, making the entire architecture modular. This not only enables fault isolation between different intelligent agents, but also facilitates independent development, testing, upgrading and replacement of intelligent agents, which helps to enhance the reliability and maintainability of the system.

[0132] In an optional embodiment, the information display method further includes: for each task node, if the preceding task of the task represented by the task node has not been completed, displaying the task node in a third display style that represents waiting for the preceding task to be completed; if the preceding task has been completed and all task agents matching the task are in an occupied state, changing the display of the task node from the third display style to a fourth display style that represents waiting for resources.

[0133] As mentioned earlier, the display style of a node can be associated with the task state of the task it represents to achieve state-driven visualization mapping. The display style can include at least one of the following: color, shape, state identifier, etc. For example, a task node in the first display style is blue, a task node in the second display style is green, a task node in the third display style is yellow, and a task node in the fourth display style is gray.

[0134] In practice, the agent assigned a task changes from an idle state to an occupied state. When an idle agent in the occupied state completes its current task, it changes back to an idle state, and the corresponding computing resources are released again. It's understandable that the resource release time for multiple agents simultaneously assigned tasks is not unique. Based on this, the server can continuously monitor ready tasks and idle agents, and when both idle agents and ready tasks exist simultaneously, it will perform the next round of task allocation, thus forming a continuously flowing pipeline to ensure the smooth progress of tasks. Here, ready tasks refer to tasks whose prerequisite tasks have been completed or have no prerequisite tasks.

[0135] Based on this, for each task node, the application can display the task node in a third display style, indicating that it is waiting for the preceding task to complete, if the preceding task represented by the task node has not been completed. As time progresses, if the preceding task has been completed, it further determines whether there is a matching and idle task agent. If a matching idle task agent exists, the task can be immediately assigned to that task agent, and the application can change the task node display style from the third display style to the first display style, indicating that it is in execution. If all matching task agents are occupied, the task cannot be assigned temporarily, and the application can change the task node display style from the third display style to the fourth display style, indicating that it is waiting for resources.

[0136] In the above embodiments, different display styles are used to represent waiting for the completion of the preceding tasks and waiting for resources, which can intuitively present the changes in the task status, provide users with richer information, and achieve a more detailed display of the task progress.

[0137] In one embodiment, the information display method further includes: for each task node, displaying at least one sub-task node of the task node when the display style of the task node indicates that the task is being executed.

[0138] Among them, the subtask node is used to represent the subtask obtained by decomposing the task in execution; the execution result of the subtask is used to obtain the execution result of the task to which the subtask belongs.

[0139] In practice, during the execution of a task, the task can be decomposed into multiple subtasks. Based on the execution order constraints corresponding to the task, the execution order constraints corresponding to each subtask are determined. Then, for each subtask, if the preceding task of the subtask has been completed based on the execution order constraints of the subtask, the subtask is assigned to the agent that is currently in an idle state.

[0140] Optionally, the task execution process can be implemented by calling tools. These tools can be external functions, programs, APIs, or services called through predefined interfaces, with the aim of extending the core capabilities of the intelligent agent. In specific implementations, tools may include document conversion tools, online search tools, webpage reading tools, report generation tools, image generation tools, chart generation tools, webpage generation tools, etc. In this embodiment, when the intelligent agent executes a task, the process of calling a tool can be considered a sub-task. For example, if task A involves online search tools and chart generation tools, the online search process and the chart generation process can be considered sub-tasks of task A, respectively. It is understood that calling a specific tool needs to be combined with the user's query requirements; for example, if the user indicates that online search is not needed, the online search tool will not be called.

[0141] Optionally, during task execution, the task can be decomposed into multiple sub-tasks based on semantics. For example, based on the query "Compare the horsepower, safety, and intelligent cockpit configuration of models A, B, and C," a requirements analysis task, a query task, and a comparison task can be obtained. The query task can be further decomposed into nine sub-tasks corresponding to the three models across three dimensions, and the comparison task can be further decomposed into sub-tasks for each of the three dimensions. Optionally, through task planning, complex tasks can be broken down into multiple tasks. For each task, the corresponding analysis task can be determined first, and then further decomposed into multiple sub-tasks according to the analysis results. For example, the planned search task can be implemented through search sub-tasks corresponding to the three models across three dimensions, and the initially planned search node can be understood as an analysis node with the search as its objective.

[0142] It is understandable that the execution order constraints of each subtask obtained from the decomposition are determined based on the execution order constraints corresponding to the decomposed task. Specifically, the execution order constraints between each subtask and other tasks match the execution order constraints of the decomposed task; the execution order constraints among the subtasks are determined based on the logical dependencies between them. For example, when a query task is decomposed into nine subtasks corresponding to three car models across three dimensions, since the query task before decomposition serves as a prerequisite for the comparison task, the nine subtasks after decomposition are all prerequisites for the comparison task. Because there are no logical dependencies between these nine subtasks, there are no execution order constraints among them; they are parallel tasks.

[0143] When multiple subtasks are decomposed into tasks, the server can schedule these tasks to execute concurrently. The concurrently executed objects can include at least one of tasks or subtasks. That is, for each subtask, if the server determines that the subtask is ready based on its execution order constraints, it can assign the subtask to an idle agent to achieve concurrent execution of multiple ready tasks. Optionally, for complex tasks, the server can further decompose the subtasks and perform concurrent scheduling based on the decomposition results to further improve efficiency.

[0144] For example, such as Figure 6 As shown, for the query "What are the most popular tennis rackets right now? What model of tennis racket does athlete A use? I want to buy a tennis racket, is the tennis racket used by athlete A suitable for me? I am a girl, 170cm tall, please recommend a tennis racket that suits me," four tasks can be planned through task breakdown. Task 1 is "User Needs Analysis," which analyzes the user's basic information and purchasing needs, filters popular tennis rackets suitable for women of 170cm height on the current market, and initially identifies several mainstream models; Task 2 is "Tennis Racket Used by Athlete A"; Task 3 is "Matching Analysis of Athlete A's Tennis Racket with User Needs"; and Task 4 is "Recommendation and Result Generation." Optional tasks include... Figure 6 As shown, the server can rewrite the query content entered by the user by rewriting the query content and analyzing the problem, so as to complete the task decomposition.

[0145] Tasks 1 and 2 have no prerequisite tasks and no dependencies on each other, so they can be executed concurrently. Task 3 needs to wait for the results of Tasks 1 and 2 before it can execute, and Task 4 needs to wait for the results of Tasks 1 and 3 before it can execute. In other words, Tasks 1 and 2 are prerequisite tasks for Task 3, and Tasks 1 and 3 are prerequisite tasks for Task 4.

[0146] Optionally, different task states can correspond to different display styles, which can be characterized by at least one of the following: color, status indicator, etc. For example, Figure 6 The task status for Task 1 and Task 2 is "in progress," and their corresponding text and boxes are displayed in blue.

[0147] Optional, such as Figure 7 As shown, when executing Tasks 1 and 2, Task 1 can be further broken down into three search subtasks: Task 11, Task 12, and Task 13. Task 11 searches for parameters of popular women's tennis rackets this year; Task 12 searches for recommendations of mainstream tennis racket brands; and Task 13 searches for comparisons of parameters for lightweight and easy-to-control tennis rackets. There are no execution order constraints between Tasks 11, 12, and 13; they can be executed concurrently.

[0148] Optionally, Task 2 can be further broken down into three tasks: Task 21, Task 22, and Task 23. Task 21 searches for the tennis racket model currently used by A, Task 22 determines the specific parameters after identifying the racket model, and Task 23 summarizes and organizes these parameters. Task 21 is a prerequisite sub-task of Task 22, and Task 22 is a prerequisite sub-task of Task 23. Furthermore, Task 21 is further divided into three tertiary tasks: Task 211, Task 212, and Task 213. Task 211 searches for the racket model used by A in matches, Task 212 searches for the racket model currently used by A, and Task 213 searches for the racket model for which A has a contract.

[0149] During execution, Task 1 and Task 2 can start simultaneously. Task 1 first performs task decomposition, then concurrently executes three search subtasks; Task 2 first performs task decomposition, then executes the decomposed Task 21, which in turn performs task decomposition again, and then concurrently executes three tertiary tasks. Optionally, the search agent can concurrently execute the three search subtasks of Task 1 first, then concurrently execute the three search subtasks under Task 21, meaning a maximum of six search tasks can be in execution at any given time.

[0150] In the above embodiments, the task can be further decomposed during the task execution process, and the nodes corresponding to the subtasks obtained after decomposition can be displayed. On the one hand, this can significantly increase the number of concurrent tasks, so as to maximize the use of the system's computing resources and further improve work efficiency. On the other hand, it can present more granular task information and enhance the richness of the displayed information.

[0151] In an optional embodiment, displaying at least one subtask node of a task node includes: displaying multiple subtask nodes of the task node starting from the task node, such that the multiple subtask nodes extend in a directed acyclic graph in a direction away from the task planning node.

[0152] A Directed Acyclic Graph (DAG) is a graph data structure consisting of nodes and directed edges, without any cycles. Specifically, in this embodiment, each node in the DAG represents a different task, and the directed edges connecting two nodes represent the execution order constraints between the two tasks corresponding to those two nodes.

[0153] Specifically, when a task is broken down into subtasks, the application can start from a task node and display multiple subtask nodes, allowing these subtask nodes to extend away from the task planning node in the directed acyclic graph. For example,... Figure 7 As shown, the subtasks obtained from the decomposition of Task 2 extend to the right from Task 2, and the subtasks obtained from the decomposition of Task 21 extend to the right from Task 21.

[0154] For example, the directed acyclic graph constructed for the query "Compare the horsepower, safety, and smart cockpit configuration of models A, B, and C" can be as follows: Figure 8 As shown, by executing task planning, three task nodes can be obtained: search, comparison, and summary result output. During the execution of the search task, it can be further decomposed into search sub-tasks corresponding to the three car models in three dimensions; during the execution of the comparison task, it can be further decomposed into comparison sub-tasks for each of the three dimensions.

[0155] In the above embodiments, using directed acyclic graphs to represent tasks and the execution order constraints between tasks can intuitively and clearly present all tasks and the dependencies between them, which is beneficial to improving the information display effect.

[0156] In an optional embodiment, displaying at least one subtask node of a task node includes: obtaining the task status of each of the at least one subtask obtained by decomposing the task; and for each subtask, displaying the corresponding subtask node according to a display style that matches the task status of the subtask.

[0157] The task status of a subtask can include at least one of the following: waiting for the completion of a preceding task, waiting for resources, executing, successful execution, and failed execution. In an exemplary embodiment, if the task status of subtask A is successful execution, a status indicator representing successful execution can be displayed on the subtask node corresponding to subtask A, and the text and boxes on the corresponding subtask node can be displayed in green. For example, if the task status of subtask B is executing, a status indicator representing the task is executing will be displayed on the subtask node corresponding to subtask B, and the text and boxes on the corresponding subtask node will be displayed in blue. For example, if the task status of subtask C is waiting to be assigned, a status indicator representing waiting for resources will be displayed on the subtask node corresponding to subtask C, and the text and boxes on the corresponding subtask node will be displayed in gray.

[0158] In the above embodiments, the corresponding subtask node is displayed based on the task status of the subtask, which can intuitively display the execution progress of each subtask and facilitate the display of a more detailed execution process.

[0159] In an optional embodiment, the information display method further includes: dynamically displaying the task node when there are subtasks in the execution state of the task node; and displaying the task node according to a second display style representing successful execution when the task status of each subtask of the task node is successful.

[0160] Optionally, if a task node has subtasks in an in-process state, the task node can be displayed with dynamic effects. These dynamic effects include, but are not limited to, flashing, scrolling, and color gradients. In one exemplary instance, the task status can also be displayed using a progress bar to more clearly indicate the execution progress of the task. Optionally, a percentage of progress can be displayed above the progress bar. When all subtasks of the task node have successfully completed their respective tasks, the application can display the task node according to a second display style indicating successful task execution.

[0161] In the above embodiments, the state of a task node is associated with the state of its sub-task nodes, which makes it easy to display the task status of each task intuitively and accurately. At the same time, based on the state of each task, its progress in the entire execution process can also be understood.

[0162] In an optional embodiment, the information display method further includes: if a task node has a first subtask whose execution result does not meet the set conditions, displaying a second subtask node obtained by further decomposing the task node, corresponding to the first subtask node representing the first subtask.

[0163] The second subtask node represents the second subtask, which is determined based on the first subtask. In the specific implementation, if a task node contains a first subtask whose execution result does not meet the set conditions, the corresponding task can be further decomposed. Optionally, the execution result not meeting the set conditions could mean, for example, that the execution result of the first subtask is incorrect, or that the execution result does not meet preset requirements. For example, if tasks A and C do not meet preset requirements, supplementary searches are performed on tasks A and B respectively, displaying the subtask node corresponding to subtask a retrieved for task A, and displaying the subtask node corresponding to subtask b retrieved for task B. For instance, if the task "Model A Horsepower Query" fails, multiple subtasks such as "Model A Maximum Torque Query," "Model A Maximum Power Speed ​​Query," and "Model A Horsepower Calculation" can be added to calculate the horsepower of model A based on the maximum torque and maximum power speed. Here, horsepower = maximum torque * maximum power speed / constant.

[0164] Optionally, if the display style of the first subtask node changes from indicating task execution to indicating task execution failure, it is determined that the execution result of the first subtask does not meet the set conditions.

[0165] Optionally, the second sub-task node can correspond to the first sub-task node by displaying at least one of the following: position, color, shape, or associated identifier. The associated identifier can include at least one of the following: icon, letter label, or dynamic connecting line. Optionally, the dynamic connecting line can refer to the connecting line displayed when the first or second sub-task node is triggered, or when the mouse hovers over the first or second sub-task node.

[0166] In the above embodiments, if the execution result of at least one subtask does not meet the preset conditions, a new subtask can be obtained by performing a secondary decomposition on the task to which the subtask belongs, which can improve the success rate of task execution.

[0167] In one embodiment, the information display method further includes: in response to a state change event of at least one task or subtask, performing incremental rendering on the state change node corresponding to the task or subtask whose state has changed, according to the task state before and after the change, so as to change the display style of the state change node.

[0168] In practical applications, incremental rendering can be performed only on nodes with state changes to reduce resource consumption. Optionally, a real-time state synchronization channel can be established between the application and the server, and the JSON Patch incremental update protocol can be used to ensure strong consistency between the state of the front-end view and the back-end scheduling engine with minimal synchronization overhead, so that users see a low-latency updated "system state".

[0169] In one exemplary embodiment, such as Figure 9 As shown, in the scheduling loop, the backend (server-side) DAG scheduling engine generates a status change event whenever the Status field of a Task node changes (e.g., from pending to running). This event can be encapsulated in a TaskSocketData structure and prepared for push via the PushSocketMessage function. Optionally, to optimize performance, compression algorithms can be automatically enabled for large message bodies exceeding 2MB. Optionally, PushSocketMessage can broadcast data to all connected application clients (such as desktop clients, browsers, and mini-programs) through a real-time status synchronization channel. The pushed data packet adopts a unified SocketMessage structure, and its Data field can be the complete TaskSocketData or the more efficient TaskPatches (i.e., a collection of JSON Patch operations), instructing the frontend (application-side) how to incrementally update specific fields (such as / status) of specific nodes. The frontend's dynamic DAG view component can continuously monitor this real-time status synchronization channel. Upon receiving a message: if it is full data, it parses and updates the entire DAG model; if it is a JSON Patch, it applies these patches to the local DAG model to achieve precise incremental updates. Optionally, the application can convert the node's Status (e.g., running) into a specific CSS style class (e.g., .node-state-running { fill: #2196f3;}) according to the state-color mapping protocol. Then, it can find the corresponding ID of the node DOM element, apply the new color style and animation, and keep the overall layout of the DAG stable.

[0170] In the above embodiments, incremental rendering is performed on the state change nodes corresponding to the task or subtask whose state has changed, according to the task state before and after the change, so as to change the display style of the state change nodes. This can ensure that the state of the front-end view and the back-end scheduling engine remains highly consistent and the synchronization overhead is minimized, thus saving computing resources.

[0171] In an optional embodiment, the information display method further includes: generating the execution results of the tasks to which each subtask belongs based on the execution results of each subtask; and determining and displaying the query results of the query content based on the execution results of each task.

[0172] For example, refer to Figure 7In the diagram, Task 1, Task 2, and Task 3 represent different tasks related to the query content. Task 1 has subtasks including Task 11, Task 12, and Task 13; Task 2 has subtasks including Task 21, Task 22, and Task 23; and Task 21 has subtasks including Task 211, Task 212, and Task 213. In this embodiment, the execution result of Task 21 is determined based on the execution results of Task 211, Task 212, and Task 213; the execution result of Task 2 is determined based on the execution results of Task 21, Task 22, and Task 23; the execution result of Task 1 is determined based on the execution results of Task 11, Task 12, and Task 13; and finally, the query results for the query content are determined and displayed based on the execution results of Task 1, Task 2, and Task 3.

[0173] Optional, such as Figure 10 As shown, when all tasks have been successfully executed, the application can display the query content and the task nodes represented by the directed acyclic graph in the first display area 1001 of the content display page, and display the summarized query results in the second display area 1002 of the content display page.

[0174] In the above embodiments, the execution results of each task are generated based on the execution results of the subtasks corresponding to each task; the query results of the query content are determined based on the execution results of each task; the execution results of the underlying subtasks are recursively called to generate the execution results of the upper level layer by layer, which can effectively solve more complex query content and provide accurate response content.

[0175] In an optional embodiment, displaying at least one task node includes: displaying at least one task node in a first display area of ​​the content display page. In this embodiment, the information display method further includes: in response to a trigger event for any task node, displaying detailed information of the triggered task node in a second display area of ​​the content display page.

[0176] The first display area and the second display area are different display areas on the content display page. The first and second display areas can be arranged vertically or horizontally on the same layer. Optionally, the first and second display areas can be distinguished by a dividing line. Optionally, the first and second display areas can be on different layers. For example, the second display area can be displayed as a floating layer on top of the first display area; for instance, the second display area can be a pop-up window floating on top of the first display area.

[0177] In practical applications, users can trigger nodes in any state, causing the application to query the background for detailed execution logs, LLM inference processes, or error information of the task based on the node identifier of the triggered node. The application can then display a summary of the details in the sidebar or pop-up window, thus achieving a closed loop from visualization to in-depth analysis.

[0178] In one exemplary embodiment, the details can be dynamically updated, and related operations can be performed on the second display area. For example, clicking a drop-down menu or scrolling the mouse can display the execution details for the next page. Another example is clicking the details directory to display the corresponding details.

[0179] In the above embodiments, by displaying at least one task node in the first display area of ​​the content display page and displaying the execution details information corresponding to the current task in the second display area of ​​the content display page, it is possible to display the details information of any task node.

[0180] In an optional embodiment, displaying details of the triggered task node includes: dynamically displaying execution details of the triggered task node when the task status corresponding to the triggered task node is in execution; and displaying execution result information of the triggered task node when the task status corresponding to the triggered task node is completed.

[0181] Optionally, if the task status corresponding to task node A is "in execution", clicking on task node A will dynamically display the execution details of task node A through a floating layer in the second display area.

[0182] If task node A's task status is "execution completed," clicking on task node A will display the execution result information corresponding to task node A via a floating layer in the second display area. Optionally, the floating layer can also display the execution details information corresponding to task node A. Optionally, the floating layer can be displayed directly or as a top-down pop-up window. Those skilled in the art may make other changes based on the essence of the technology in this application, but as long as the functions and effects achieved are the same as or similar to those in this application, they should all be covered within the scope of protection of this application.

[0183] Optional, such as Figure 11 As shown, when a task is terminated due to a system upgrade, the currently executing task node 1101 will display a style indicating execution failure. If the user triggers the successfully executed task node 1102, the application can display the execution result of the task represented by the task node 1102 in the second display area 1103.

[0184] In one possible implementation, the execution details information in the second display area can correspond to streaming data. Streaming data transmission is a technique that transmits data in chunks to the client in real time, rather than waiting for all data to be processed before sending it all at once. This mode can significantly improve the user experience, especially in scenarios involving large or time-consuming processing (such as responses from large language models), allowing users to see partial results as content is generated, reducing the feeling of waiting. Optionally, streaming methods include Server-Sent Events (SSE) and the WebSocket protocol.

[0185] In the above embodiments, the display of execution details can be triggered by information on task nodes that are in progress, or by information on task nodes that have finished execution, to display the corresponding execution results, facilitating the viewing of task nodes. It is understood that the above viewing function is not limited to tasks, but can also include subtasks, secondary subtasks, etc., and this disclosure does not impose any limitations on this.

[0186] In one specific embodiment, a method is provided as follows: Figure 12 As shown, an information display method is provided, which can be executed by a computer device, wherein the computer device is Figure 1 Taking the application side as an example, in this embodiment, the method includes the following steps:

[0187] Step S1201: Obtain the query content;

[0188] Step S1202: Display the content parsing node of the query content in the first display style;

[0189] The first display style is used to indicate that the task is being executed;

[0190] Step S1203: When the content parsing node changes from the first display style to the second display style indicating successful execution, the task planning node for the query content is displayed.

[0191] Step S1204: When the display style of the task planning node indicates that the task is being executed, display the task planning ideas for the query content.

[0192] Step S1205: Obtain feedback on the task planning approach;

[0193] Step S1206: If the feedback content indicates acceptance of the task planning approach, a confirmation event for the task planning approach is triggered.

[0194] Step S1207: Display the timing component for the task planning approach;

[0195] In step S1208, in response to the timing component ending, if no feedback is received regarding the task planning approach, a confirmation event for the task planning approach is triggered.

[0196] Step S1209: Display the skip guide control for the task planning approach;

[0197] Step S1210: In response to the trigger operation for skipping the guide control, a confirmation event for the task planning approach is triggered;

[0198] Step S1211: In response to the confirmation event for the task planning approach, cancel the display of the conversation panel to which the task planning approach belongs;

[0199] Step S1212, corresponding to the task planning node, displays the session entry element of the session panel, and corresponding to the session entry element, displays the session count indicator;

[0200] The session entry element is used to restore the session panel display when triggered; the session count identifier is used to indicate the number of historical sessions based on the session panel.

[0201] Step S1213: In response to the confirmation event for the task planning approach, display at least one content card corresponding to each task node according to the display style matching the task status, and display the corresponding task title and task type in the content card;

[0202] In this process, if there is an idle task agent that matches the task type, the task is assigned to the task agent; the task represented by the task node is planned according to the confirmed task planning idea.

[0203] Optionally, when the task planning is completed according to the task planning approach, the display style of the task planning node can be changed from the first display style representing the task execution to the second display style representing the task execution completion.

[0204] Optionally, if the prerequisite task of the task represented by the task node has not been completed, the task node is displayed in a third display style indicating that the prerequisite task is waiting to be completed; if the prerequisite task has been completed and all task agents matching the task are in an occupied state, the display style of the task node is changed from the third display style to a fourth display style indicating that the task is waiting for resources; if the task represented by the task node is assigned to the corresponding task agent, an execution start event for the assigned task is triggered, and the task node is displayed in a first display style indicating that the task is being executed; wherein, any task is assigned if the corresponding prerequisite task has been completed or if the task has no prerequisite task.

[0205] Step S1214: For each task node, if the display style of the task node represents the task execution, starting from the task node, display multiple sub-task nodes of the task node so that the multiple sub-task nodes extend away from the task planning node in the directed acyclic graph.

[0206] The subtask node represents a subtask obtained by decomposing the tasks in execution; the display style of the subtask node matches the task status of the task it represents.

[0207] Step S1215: In response to at least one task or subtask state change event, incremental rendering is performed on the state change node corresponding to the task or subtask whose state has changed, according to the task state before and after the change, so as to change the display style of the state change node.

[0208] Step S1216: If a task node has a first subtask whose execution result does not meet the set conditions, the second subtask node obtained by further decomposing the task node is displayed, corresponding to the first subtask node representing the first subtask.

[0209] The second subtask node represents the second subtask, which is determined based on the first subtask.

[0210] Step S1217: Based on the execution results of each subtask, generate the execution results of the corresponding task to which each subtask belongs;

[0211] Optionally, if each subtask node corresponding to a task node is a second display style representing successful execution, the application can obtain the execution result of the task represented by that task node.

[0212] Step S1218: Based on the execution results of each task, determine and display the query results of the query content.

[0213] Optionally, if each task node displays the second display style indicating successful execution, the application can obtain and display the query results of the query content.

[0214] The aforementioned information display method can break down complex tasks by executing the planning tasks represented by task planning nodes, thereby improving the quality and efficiency of response content generation. Furthermore, when the display style of the task planning node represents task execution, it displays the task planning approach for the query content and, in response to a confirmation event for the task planning approach, displays at least one task node planned according to the stated approach. This visualization and confirmation of the task planning approach ensures that the task planning process meets expectations, thereby ensuring that the task used to obtain the query results matches the actual needs. This reduces the number of follow-up queries and improves the quality and efficiency of query result generation.

[0215] In an exemplary embodiment, taking the task processing method of this application as an example, applied to a system with multiple task agents collaborating (including multiple task agents, each task agent being responsible for content query feedback of a specific task (such as problem solving, result generation), the task processing method provided by this application will be described in detail.

[0216] Current multi-agent systems based on large language models typically use directed acyclic graphs (DAGs) for task orchestration, such as... Figure 13 As shown, traditional technologies provide process definitions during the development phase but lack real-time status monitoring for end users. They focus on backend scheduling optimization but lack real-time visualization of the execution process. Furthermore, based on static DAG generation technology, only the task flow structure is displayed, failing to reflect the dynamic execution process. Therefore, using traditional technologies, the task execution process is completely black-box for users, making it impossible to perceive the scheduling status and concurrent processes in real time. The technical solution of this application uses color and animation to map the internal state (running, waiting, etc.) of the DAG scheduling engine to the front end in real time, making the concurrent process completely transparent and enabling real-time status visualization. The dynamic DAG view allows users to clearly perceive the system's efficient and parallel "thinking" and "execution" processes, enhancing user control and trust. Users can quickly identify bottlenecks through color (e.g., gray nodes indicate resource scarcity, red nodes indicate execution failures), and obtain detailed execution information through node IDs, accelerating problem troubleshooting.

[0217] For example, such as Figures 5 to 11 As shown, after a user submits a complex task, the system will track the current task's execution status in real time and display a dynamically evolving DAG flowchart, rather than a static progress bar or a blank page.

[0218] In the initial stage, the user's problem will be understood, an execution plan will be formulated, and multiple sub-steps for solving the problem will be broken down. The user will see the current task execution steps in real time and will see multiple yellow nodes (such as "product model information retrieval", "latest price query", "cost-effectiveness and purchase suggestion analysis"), indicating that the system has planned the task and is waiting to start.

[0219] During the concurrent execution phase, a batch of yellow nodes instantly turn blue, accompanied by execution animations, indicating that multiple search and analysis agents are simultaneously executing these independent tasks. Users gain their first direct visual understanding of concurrency. If resource contention exists between task nodes, users may see individual nodes turn from blue to gray, intuitively telling them, "This task is ready, but system resources are busy; it's in the queue." As the search and analysis task (blue) completes and turns green, the downstream cost-effectiveness analysis and suggestion nodes (yellow) are activated and turn blue, clearly showing the dependencies. When all nodes turn green, a complete report is generated in the "Results Output" node. Throughout the process, users are essentially watching a real-time synchronized dashboard of a highly efficient "digital factory," gaining an intuitive understanding of the system's concurrency capabilities, current progress, and resource status.

[0220] This application constructs a complete front-end and back-end state synchronization and visualization system. In an optional embodiment, its core architecture and data flow are as follows: Figure 14 As shown, its complete workflow is as follows: Figure 15 As shown. Users provide data through a query portal, which is then analyzed by a problem-understanding agent to interpret user needs. A task-planning agent can then plan multiple tasks based on these needs. The backend can construct the directed acyclic graph (DAG) corresponding to each task using a DAG builder and implement task scheduling and allocation through a DAG scheduling engine to achieve concurrent task execution. Simultaneously, the backend maintains task states and detects state changes. State changes can be encapsulated as structured messages and transmitted to the frontend via a real-time transmission channel. Optionally, to optimize performance, compression algorithms can be automatically enabled for large messages exceeding 2MB. Optionally, when the number of messages increases dramatically, additional message transmission channels can be added. Optionally, backend state events and data structures can be configured as follows: Figure 16 As shown.

[0221] The front-end visualization layer is responsible for dynamically displaying the DAG view. It implements a state-driven visualization mapping mechanism by mapping task states to the display colors of task nodes. Optionally, the front-end state-color mapping protocol can be as follows: Figure 17 As shown, the node rendering engine performs incremental mapping for task nodes with changing states, saving computing resources. Simultaneously, it provides an interactive user interface to assist in functions such as querying diagnostic information, executing detailed services, and displaying detailed panels.

[0222] The above information display method offers at least the following benefits: It presents the complex concurrent scheduling process in the background in a clear and graphical way in real time, breaking the "black box" execution process and allowing users to clearly perceive the progress, thus enhancing their understanding and trust in the system; color coding and interactive diagnostics enable developers to quickly locate fault nodes, analyze performance bottlenecks, and understand task dependencies, reducing system maintenance costs and improving operation and debugging efficiency; it transforms the background concurrent scheduling capabilities directly into product competitiveness that users can perceive through front-end visualization, highlighting the perfect combination of technological advancement and user experience; and it significantly reduces the bandwidth consumption and front-end rendering pressure of real-time synchronization by employing JSON Patch incremental updates and message compression strategies, ensuring the smoothness of large-scale DAG visualization.

[0223] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0224] Based on the same inventive concept, this application also provides an information display device for implementing the information display method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more information display device embodiments provided below can be found in the limitations of the information display method described above, and will not be repeated here.

[0225] In some embodiments, such as Figure 18 As shown, an information display device is provided, comprising:

[0226] Module 1801 is used to retrieve query content;

[0227] The planning node display module 1802 is used to display task planning nodes for the query content;

[0228] The planning idea display module 1803 is used to display the task planning idea for the query content when the display style of the task planning node represents the task execution.

[0229] The task node display module 1804 is used to display at least one task node when the display style of the task planning node indicates that the task has been completed; the task node is used to represent the task planned according to the task planning idea; the execution result of the task is used to obtain the query result of the query content.

[0230] In one embodiment, the task node display module 1804 is specifically used to: for each task node, when the task represented by the task node is assigned to the corresponding task agent, display the task node according to a first display style representing the execution of the task; wherein any task is assigned when the corresponding prerequisite task has been completed or when the task has no prerequisite task.

[0231] In one embodiment, the task node display module 1804 is specifically used to: display content cards corresponding to at least one task, and display the corresponding task title and task type in the content cards; and assign a task to a task agent if there is a task agent that matches the task type and is idle.

[0232] In one embodiment, the task node display module 1804 is specifically used to: for each task node, if the preceding task of the task represented by the task node has not been completed, display the task node in a third display style that represents waiting for the preceding task to be completed; if the preceding task has been completed and the task agents matching the task are all in an occupied state, change the display of the task node from the third display style to a fourth display style that represents waiting for resources.

[0233] In one embodiment, the information display device further includes a subtask node display module, configured to: for each task node, display at least one subtask node of the task node when the display style of the task node represents the task being executed; the subtask node is used to represent a subtask obtained by decomposing the task being executed; and the execution result of the subtask is used to obtain the execution result of the task.

[0234] In one embodiment, the subtask node display module is specifically used to: display multiple subtask nodes of the task node starting from the task node, so that the multiple subtask nodes extend in the directed acyclic graph in a direction away from the task planning node.

[0235] In one embodiment, the subtask node display module is specifically used to: obtain the task status of at least one subtask obtained by decomposing the task; and for each subtask, display the subtask node corresponding to the subtask according to a display style that matches the task status of the subtask.

[0236] In one embodiment, the task node display module is specifically used to: dynamically display the task node when there are subtasks in the execution state of the task node; and display the task node according to the second display style representing successful execution when the task status of each subtask of the task node is successful.

[0237] In one embodiment, the subtask node display module is further configured to: when a task node has a first subtask whose execution result does not meet the set conditions, display a second subtask node obtained by further decomposing the task node, corresponding to the first subtask node representing the first subtask; the second subtask represented by the second subtask node is determined based on the first subtask.

[0238] In one embodiment, the subtask node display module is specifically used to: determine that the execution result of the first subtask does not meet the set conditions when the display style of the first subtask node changes from indicating that the task is in progress to indicating that the task has failed.

[0239] In one embodiment, the task is obtained upon triggering a confirmation event for the task planning approach. In this embodiment, the planning node display module 1802 is further configured to: when task planning is completed according to the task planning approach, change the display style of the task planning node from a first display style representing task execution to a second display style representing task execution completion.

[0240] In one embodiment, the information display device further includes a confirmation event triggering module, configured to: obtain feedback content regarding the task planning approach; and trigger a confirmation event regarding the task planning approach if the feedback content indicates acceptance of the task planning approach.

[0241] In one embodiment, the planning idea display module 1803 is further configured to: display a new task planning idea obtained by adjusting according to the feedback content when the feedback content indicates that the task planning idea is not approved.

[0242] In one embodiment, the information display device further includes a confirmation event triggering module, configured to: display a timing component for the task planning approach; and, in response to the timing component ending its timeout, trigger a confirmation event for the task planning approach if no feedback content for the task planning approach is received.

[0243] In one embodiment, the information display device further includes a confirmation event triggering module, configured to: display a skip guide control for the task planning approach; and trigger a confirmation event for the task planning approach in response to a triggering operation on the skip guide control.

[0244] In one embodiment, the information display device further includes: a cancellation display module, configured to cancel the display of the session panel to which the task planning idea belongs in response to a confirmation event for the task planning idea; a session entry element display module, configured to display the session entry element of the session panel corresponding to the task planning node; and a session entry element, configured to restore the display of the session panel when triggered.

[0245] In one embodiment, the session entry element display module is specifically used to: display a session count identifier corresponding to the session entry element; the session count identifier is used to indicate the number of historical sessions based on the session panel.

[0246] In one embodiment, the planning node display module 1802 is specifically used to: display the content parsing node of the query content in a first display style; the first display style is used to indicate that the task is being executed; and when the content parsing node changes from the first display style to a second display style indicating successful execution, display the task planning node for the query content.

[0247] In one embodiment, the information display device further includes an incremental rendering module, configured to: in response to a state change event of at least one task or subtask, perform incremental rendering on the state change node corresponding to the state change task or subtask according to the task state before and after the change, so as to change the display style of the state change node.

[0248] In one embodiment, the information display device further includes a query result display module, which is used to: generate the execution result of the task to which each subtask belongs based on the execution result of each subtask; and determine and display the query result of the query content based on the execution result of each task.

[0249] In one embodiment, the task node display module 1804 is specifically used to display at least one task node in a first display area of ​​the content display page. In this embodiment, the information display device further includes a details display module, used to display details of the triggered task node in a second display area of ​​the content display page in response to a trigger event for any task node.

[0250] In one embodiment, the details display module is specifically used to: dynamically display the execution details information of the triggered task node when the task status of the triggered task node is in execution; and display the execution result information of the triggered task node when the task status of the triggered task node is in execution completed.

[0251] Each module in the aforementioned information display device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0252] In some embodiments, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 19 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an information display method. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0253] Those skilled in the art will understand that Figure 19 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0254] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described information display method.

[0255] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described information display method.

[0256] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the above-described information display method.

[0257] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data 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.

[0258] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logic devices, etc., and are not limited to these.

[0259] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0260] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An information display method characterized by comprising: The method comprises: acquiring query content; displaying a task planning node for the query content; in a case where a display style of the task planning node represents a situation in task execution, displaying a task planning idea for the query content; in a case where the display style of the task planning node represents a situation in which task execution is completed, displaying at least one task node; the task node is used to represent a task planned according to the task planning idea; and an execution result of the task is used to obtain a query result of the query content.

2. The method of claim 1, wherein, The method further comprises: for each task node, in a case where the task represented by the task node is assigned to a corresponding task agent, displaying the task node in a first display style representing a situation in task execution; wherein any task is assigned in a case where a corresponding preceding task has been completed or the task has no preceding task.

3. The method of claim 2, wherein, The display of the at least one task node comprises: displaying at least one content card corresponding to the task, and displaying a task title and a task type corresponding to the task in the content card; the task is assigned to a task agent in a case where there is a task agent matching the task type and being idle.

4. The method of claim 3, wherein, The method further comprises: for each task node, in a case where a preceding task of the task represented by the task node is not completed, displaying the task node in a third display style representing a situation of waiting for the preceding task to be completed; in a case where the preceding task has been completed and task agents matching the task are all in an occupied state, changing the display style of the task node from the third display style to a fourth display style representing a situation of waiting for resources.

5. The method of claim 1, wherein, The method further comprises: for each task node, in a case where a display style of the task node represents a situation in task execution, displaying at least one sub-task node of the task node; the sub-task node is used to represent a sub-task obtained by decomposing the task in execution; and an execution result of the sub-task is used to obtain an execution result of the task.

6. The method of claim 5, wherein, The display of the at least one sub-task node of the task node comprises: displaying a plurality of sub-task nodes of the task node from the task node as a starting point, so that the plurality of sub-task nodes extend in a directed acyclic graph away from the task planning node.

7. The method of claim 5, wherein, The display of the at least one sub-task node of the task node comprises: acquiring a task state of each sub-task obtained by decomposing the task; for each sub-task, displaying a sub-task node corresponding to the sub-task in a display style matching the task state of the sub-task.

8. The method of claim 7, wherein, The method further comprises: in a case where the task node has a sub-task in an execution state, dynamically displaying the task node; in a case where the task state of each sub-task of the task node is execution success, displaying the task node in a second display style representing execution success.

9. The method of claim 7, wherein, The method further comprises: In a case where the execution result of the first subtask does not satisfy the set condition, the task node is displayed again in a second subtask node obtained by decomposing the task node; The second subtask represented by the second subtask node is determined based on the first subtask.

10. The method of claim 9, wherein, The method further comprises: In a case where the display style of the first subtask node is changed from representing task execution to representing task execution failure, it is determined that the execution result of the first subtask does not satisfy the set condition.

11. The method according to any one of claims 1 to 10, characterized in that, The task is obtained in a case where a confirmation event for the task planning idea is triggered; The method further comprises: In a case where the task planning is completed according to the task planning idea, the display style of the task planning node is changed from representing task execution to representing task completion.

12. The method of claim 11, wherein, The method further comprises: Obtaining feedback content for the task planning idea; In a case where the feedback content represents approval of the task planning idea, a confirmation event for the task planning idea is triggered.

13. The method of claim 12, wherein, The method further comprises: In a case where the feedback content represents disapproval of the task planning idea, a new task planning idea adjusted according to the feedback content is displayed.

14. The method of claim 11, wherein, The method further comprises: Displaying a timing component for the task planning idea; In response to the timing component ending, if no feedback content for the task planning idea is obtained, a confirmation event for the task planning idea is triggered.

15. The method of claim 11, wherein, The method further comprises: Displaying a skip guide control for the task planning idea; In response to a trigger operation on the skip guide control, a confirmation event for the task planning idea is triggered.

16. The method of claim 11, wherein, The method further comprises: In response to the confirmation event for the task planning idea, the session panel to which the task planning idea belongs is canceled; Corresponding to the task planning node, a session entry element of the session panel is displayed; the session entry element is used to restore the display of the session panel when triggered.

17. The method of claim 16, wherein, The method further comprises: Corresponding to the session entry element, a session frequency identifier is displayed; the session frequency identifier is used to represent the historical session frequency based on the session panel.

18. The method according to any one of claims 1 to 17, characterized in that, The display of the task planning node for the query content comprises: Displaying a content analysis node of the query content in a first display style; the first display style is used to represent task execution; In a case where the content analysis node is changed from the first display style to a second display style representing successful execution, the task planning node for the query content is displayed.

19. The method according to any one of claims 1 to 17, characterized in that, The method further comprises: In response to a state change event of at least one task or subtask, the state change node corresponding to the state changed task or subtask is incrementally rendered according to the task state before and after the change, so as to change the display style of the state change node.

20. The method of claim 19, wherein, The method further comprises: Based on the execution result of each subtask, the execution result of the task to which each subtask belongs is generated; Based on the execution result of each task, the query result of the query content is determined and displayed.

21. The method of any one of claims 1 to 17, wherein, The display of the at least one task node comprises: displaying the at least one task node in a first display area of a content display page; The method further comprises: in response to a triggering event for any of the task nodes, displaying, in a second display area of the content display page, detail information of the triggered task node.

22. The method of claim 21, wherein, The display of the detail information of the triggered task node comprises: in a case where a task state corresponding to the triggered task node is in execution, dynamically displaying execution detail information corresponding to the triggered task node; in a case where the task state corresponding to the triggered task node is in execution end, displaying execution result information corresponding to the triggered task node.

23. An information display device, characterized by comprising: The device comprises: an acquisition module configured to acquire query content; a planning node display module configured to display a task planning node for the query content; a planning idea display module configured to, in a case where a display style of the task planning node represents task execution, display a task planning idea for the query content; a task node display module configured to, in a case where the display style of the task planning node represents task execution completion, display at least one task node; the task node is used to represent a task planned according to the task planning idea; an execution result of the task is used to obtain a query result of the query content. 24.A computer device, comprising a memory and a processor, wherein the memory stores a computer program. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 22.

25. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 22.

26. A computer program product comprising a computer program, characterised in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 22.

Images