Query processing method and device, computer equipment and storage medium

Abstract

The invention relates to a query processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining query content; displaying a plurality of task nodes planned for the query content; and in response to a trigger event for any task node, displaying the triggered node and the associated node having the execution sequence constraint with the triggered node in an associated manner. Wherein the execution results of the tasks respectively represented by the triggered node and the associated node are used for obtaining the query result of the query content. By adopting the method, the execution sequence constraint between the tasks can be visually presented, and the generation quality and the generation efficiency of the query result can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a query processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the rapid development of computer technology, intelligent dialogue systems based on artificial intelligence agents (AI agents) have emerged. These agents are built upon large language models (LLMs) and possess the ability to autonomously understand, perceive, plan, remember, and use tools. In terms of technical architecture, AI agents have shifted from a process-oriented architecture to a goal-oriented architecture, aiming to complete complex tasks through a close integration of perception, thinking, and action.

[0003] In related technologies, users input query content into the display interface, and an artificial intelligence agent generates an answer to the query content and displays the answer on the display interface. The above end-to-end display process lacks effective information display, thus affecting the quality and efficiency of answer generation. Summary of the Invention

[0004] Therefore, it is necessary to provide a query processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve work efficiency in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a query processing method. The method includes:

[0006] Retrieve query results;

[0007] Displays multiple task nodes planned for the query content;

[0008] In response to a trigger event for any of the task nodes, the triggered node and associated nodes that have execution order constraints with the triggered node are displayed together.

[0009] The triggered node and the associated node each represent the execution result of the task, which are used to obtain the query result of the query content.

[0010] Secondly, this application also provides a query processing apparatus. The apparatus includes:

[0011] The retrieval module is used to retrieve query content;

[0012] The task node display module is used to display multiple task nodes planned for the query content;

[0013] The associated display module is used to respond to a trigger event for any of the task nodes by displaying the triggered node and the associated nodes that have execution order constraints with the triggered node.

[0014] The triggered node and the associated node each represent the execution result of the task, which are used to obtain the query result of the query content.

[0015] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described query processing method.

[0016] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described query processing method.

[0017] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described query processing method.

[0018] The aforementioned query processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire query content and display multiple task nodes planned for the query content. Through task planning, complex tasks can be broken down to improve the quality and efficiency of generated response content. Furthermore, in response to a trigger event for any task node, the triggered node and associated nodes with execution order constraints with the triggered node are displayed, enabling a visual representation of the execution order constraints between tasks. This allows users to perceive and understand the execution order constraints, and by clarifying these constraints, unexpected situations can be identified in advance, facilitating subsequent modifications and improving the quality and efficiency of query result generation. Attached Figure Description

[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 query processing method in some embodiments;

[0021] Figure 2This is a schematic diagram illustrating the interface changes during the query processing in some embodiments;

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

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

[0024] Figure 5 This is a schematic diagram of the query processing procedure based on a large language model in some embodiments;

[0025] Figure 6 This is a schematic diagram of task breakdown data in some embodiments;

[0026] Figure 7 This is a schematic diagram of visualized node data in some embodiments;

[0027] Figure 8 This is a schematic diagram of task status information in some embodiments;

[0028] Figure 9 This is a schematic diagram of the display page after a task node is triggered in some embodiments;

[0029] Figure 10 This is a schematic diagram of task nodes in some embodiments;

[0030] Figure 11 This is a schematic diagram illustrating the display changes after a task node is triggered in some embodiments;

[0031] Figure 12 This is a schematic diagram illustrating the area division of the content display page in some embodiments;

[0032] Figure 13 This is a schematic diagram of the display page for task description information in some embodiments;

[0033] Figure 14 This is a flowchart illustrating the query processing method in some other embodiments;

[0034] Figure 15 For some embodiments Figure 10 A schematic diagram showing the display changes triggered by node 3 in the diagram;

[0035] Figure 16 For some embodiments Figure 10 A schematic diagram showing the display changes triggered by node 9 in the diagram;

[0036] Figure 17 For some embodiments Figure 10 A schematic diagram showing the display changes triggered by node 4 in the diagram;

[0037] Figure 18 This is a schematic diagram of task change data in some embodiments;

[0038] Figure 19 This is a timing diagram for real-time status push in some embodiments;

[0039] Figure 20 This is a structural block diagram of the query processing device in some embodiments;

[0040] Figure 21 These are internal structural diagrams of the computer device in some embodiments;

[0041] Figure 22 This is an internal structural diagram of a computer device in some other embodiments. Detailed Implementation

[0042] 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.

[0043] 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.

[0044] First, the key terms and definitions used in this application will be introduced:

[0045] 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.

[0046] 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.

[0047] Mind mapping, also known as brain map, concept map, or idea map, is a visual aid for organizing information. It uses a central keyword or idea to connect all representative words, ideas, tasks, or other related items in a radial pattern. It can represent people's ideas in different ways, such as introductory, visual, systematic, and categorized formats. It is widely used in research, organization, problem-solving, and policy-making.

[0048] Large-Model Agent System: A large-model agent is an intelligent agent built on a large language model (LLM). It possesses the ability to perceive the environment, understand autonomously, make decisions, and execute actions. The agent can simulate independent thinking processes, flexibly utilize various tools, and gradually achieve preset goals. In terms of technical architecture, the agent has shifted from a process-oriented architecture to a goal-oriented architecture, aiming to complete complex tasks through the close integration of perception, thinking, and action.

[0049] Task Decomposition: The process of breaking down a user's complex query into multiple independently executable subtasks. The system analyzes user intent using LLM to generate structured task plans, with each plan corresponding to an executable subtask node.

[0050] Task Node: The basic visual unit in a mind map, representing a task that can be assigned to a specific Agent for execution. Each task node includes attributes such as title, execution status, and execution progress.

[0051] Dynamic Node Generation: During task execution, the system dynamically generates new subtask nodes based on the actual execution status.

[0052] A Directed Acyclic Graph (DAG) is a graph data structure consisting of nodes and directed edges that does not contain any cycles. It is used for hierarchical decomposition and dependency modeling of complex tasks. Nodes correspond to tasks, and directed edges define parent-child constraints between tasks.

[0053] Dependency Edge: A directed edge in a DAG that connects parent and child task nodes to avoid circular dependencies.

[0054] Task state transition: The process of changing the state of task nodes (PENDING→READY→RUNNING→SUCCESS / FAILED) is the core logic of DAG scheduling and visualization.

[0055] The query processing 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 2 As shown, a user can interact with application 102 and input query content 201. For example, this query content could be, "Compare product A and product B, how much do they cost recently, and are they 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 and perform task planning based on the query content to generate at least one task, which can then be displayed by application 102 as a task node. The number of task nodes can be one or more. For example, such as... Figure 2As shown, the application client 102 can display task nodes 202 corresponding to multiple tasks, such as product parameter query and product performance comparison. Then, the server 104 can execute each task according to the execution order constraints between different tasks. Optionally, the user can interact with the application client 102 to trigger task nodes, and the application client 102 can respond to the triggering event by displaying the triggered node and associated nodes that have execution order constraints with the triggered node. For example, as... Figure 2 As shown, product parameter query is a prerequisite task for product performance comparison, and there is an execution order constraint between the two. Therefore, when the task node corresponding to the "product performance comparison" task is triggered, the application terminal 102 can display the association between the two task nodes by thickening the connecting line between the "product performance comparison" task node and the "product parameter query" task node. Furthermore, the triggered node and the associated node each represent the execution result of the task, which is used to obtain the query result of the query content. This query result can be fed back to the user through the application terminal 102.

[0058] In some embodiments, such as Figure 3 As shown, a query processing 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 product A and product 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 car 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 provide 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 query content through the application, which can be displayed on the application and further uploaded to the server through interaction between the application and the server, so that the server can plan tasks based on the query content.

[0064] Step S304 displays multiple task nodes planned for the query content.

[0065] The task node represents a task planned for the query content, and the execution result of this task is used to obtain the query results. For the same query content, the corresponding task breakdown results are not unique. Optionally, based on the query content "Compare the horsepower, safety, and intelligent cockpit configuration of models A, B, and C," it can be broken down into requirements analysis tasks, query tasks, comparison tasks, etc., or it can be broken down into requirements analysis tasks, nine query tasks corresponding to three dimensions for each of the three models, and comparison tasks for each of the three dimensions, etc.

[0066] In the implementation, after obtaining the query content, the server can perform task planning based on that query content to obtain multiple tasks. The application can then display the multiple task nodes planned for the query content. Optionally, the server can provide feedback on the task planning approach to the application, and if the application confirms the approach, the server will plan tasks for the query content according to that approach to obtain multiple tasks.

[0067] Optional, such as Figure 2 As shown, the application can display content cards for task nodes, showing the task title, description, and execution status of the task represented by the task node. The task title could be, for example, "Product Performance Comparison," and the task description could be, for example, "Comparison of product A and product B in suction power, battery life, navigation technology, obstacle avoidance, dust collection method, cleaning...". 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 2As shown, icon 203 is used to represent comparison tasks.

[0068] In an exemplary embodiment, for the query "Compare product A and product B, how much do they cost recently, and are they worth buying?", three tasks can be planned: product parameter query, product performance comparison, and generating a final purchase recommendation. Therefore, as Figure 2 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.

[0069] In an optional 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.

[0070] 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.

[0071] 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-machine multi-agent mode, or a hybrid deployment mode.

[0072] Step S306: In response to a trigger event for any task node, display the triggered node and the associated nodes that have execution order constraints with the triggered node.

[0073] Among them, the triggered node and the associated node each represent the execution result of the task, which are used to obtain the query results of the query content.

[0074] The execution order constraint between tasks refers to the temporal or logical dependencies between multiple tasks that are decomposed into a complex task. Essentially, this constraint defines the workflow between tasks, specifying which tasks must be executed before, after, or simultaneously with other tasks to ensure the entire task can be completed correctly and efficiently. Optionally, the execution order constraint can characterize mandatory dependencies stemming from the inherent logical or physical laws of the tasks themselves. For example, data must be "extracted from the database" before "analyzed"; or, during a snapshot check of a device's health status, the tasks "detecting real-time CPU (Central Processing Unit) utilization" and "checking current memory usage" logically need to be executed simultaneously to ensure a unified snapshot of the system state at a given moment.

[0075] In other words, the execution order constraints between tasks can include pre-constraints, post-constraints, and concurrency constraints. Correspondingly, the associated nodes that have execution order constraints with the triggered node can include at least one of the following: pre-constraint nodes that the triggered node depends on, post-constraint nodes that depend on the triggered node, or concurrent nodes that are concurrent with the triggered node. Specifically, the triggered task represented by the triggered node must be executed only after the pre-constraint task represented by the pre-constraint node has finished executing; the post-constraint task represented by the post-constraint node must be executed only after the triggered task has finished executing; and the concurrent task represented by the concurrent node must be executed concurrently with the triggered task.

[0076] Optionally, the server can break down the task based on the query content, resulting in n tasks. The execution order constraints between tasks can be represented by specific fields or by the relative positions of the tasks. For example, for each task, the "Wait Tasks" field can be used to indicate the prerequisite tasks that the task depends on, and the "WithTasks" field can be used to indicate the concurrent tasks associated with the task.

[0077] In practical applications, users can trigger task nodes in any state to query the execution order constraints between the triggered task and other tasks.

[0078] Optionally, users can initiate a trigger event for a task node by clicking or touching it. Optionally, the application can cancel the association display between the triggered node and its associated nodes if the user clicks or touches a location other than the task node.

[0079] Optionally, a trigger event can be triggered for a task node when the cursor hovers over its display area. Optionally, the application can cancel the association between the triggered node and its associated nodes when the cursor moves outside the display area.

[0080] The display method for the relationship between the triggered node and its associated nodes is not unique. Optionally, the triggered node and its associated nodes can be displayed together via a connection or association identifier. For example, such as... Figure 2 As shown, the connection line between the "Product Performance Comparison" task and the "Product Parameter Query" task nodes is thickened to achieve the associated display of these two task nodes. Optionally, the associated display can also be achieved by synchronously changing the display style of the triggered node and its associated nodes. For example, the associated display can be achieved by changing the color or shape of the triggered node and its associated nodes to be different from other task nodes, or by enlarging the size of the triggered node and its associated nodes.

[0081] In an optional embodiment, the application can also query the background for detailed execution logs, reasoning processes, or error information of the task based on the node identifier of the triggered node. Then, the application can display a summary of the details in the sidebar or pop-up window to achieve a closed loop from visualization to in-depth analysis.

[0082] The above query processing method retrieves the query content and displays multiple task nodes planned for that content. Task planning enables the breakdown of complex tasks, improving the quality and efficiency of generated responses. Furthermore, in response to a trigger event for any task node, it displays the triggered node and related nodes with execution order constraints. This provides a visual representation of these constraints, allowing users to understand and perceive them. By clarifying these constraints, unexpected situations can be identified early, facilitating subsequent modifications and ultimately improving the quality and efficiency of query result generation.

[0083] In one embodiment, the associated task represented by the associated node is in an executing state. In this embodiment, the query processing method further includes: displaying at least one sub-task node of the associated node during the execution of the associated task; and displaying the sub-task node and the triggered node together.

[0084] Among them, the subtask node is used to represent the subtask of the associated task. The subtask node inherits the execution order constraint between the associated node and the triggered node.

[0085] Optionally, each task typically undergoes several state transitions during its lifecycle. When a task is waiting for its preceding tasks to complete, its state is WAITING; when the preceding tasks are empty or have all executed successfully but are temporarily awaiting allocation due to system resources, its state is READY; when the task is being executed, its state is RUNNING; when the task executes successfully, its state is SUCCESS; and when the task fails, its state is FAILED.

[0086] During application, users can trigger a task node when it and its associated nodes are in any state. A task in execution can be further decomposed into at least one subtask; correspondingly, the application can display at least one subtask node of the task node. The resulting subtasks will inherit the execution order constraints of the parent task. For example, such as... Figure 4 As shown, when the "product parameter query" task is broken down into two sub-tasks, "product a parameter query" and "product b parameter query", both of these sub-tasks will serve as prerequisite tasks for the "product performance comparison".

[0087] Optionally, task execution order constraints can be represented using the "WaitTasks" and "WithTasks" fields. "WaitTasks" describes which tasks should execute after the decomposed subtasks; "WithTasks" describes which tasks should execute concurrently with the decomposed subtasks. For the server, the decomposed subtasks can reuse the above field content from the parent task before decomposition to achieve inheritance of task execution order constraints.

[0088] For the application side, during the execution of a related task, if the related task is further decomposed into subtasks, the application side can display at least one subtask node of the related node, and display the subtask nodes and the triggered node together to achieve dynamic updates of the visual presentation of the execution order. For example, as shown... Figure 4 As shown, if the "Product Performance Comparison" task node is triggered when its associated preceding node "Product Parameter Query" is in an executing state, and is further decomposed into two subtasks, "Product A Parameter Query" and "Product B Parameter Query," then the application will display the subtask nodes corresponding to these two subtasks, and these two subtask nodes will also be displayed as associated nodes. Optionally, the application can perform incremental rendering for the current view to achieve view updates. For example, from... Figures 2 to 4The change process only requires incremental rendering of the decomposed subtask nodes and their connections. Figure 4 Section 401.

[0089] In the above embodiments, when the associated task is further decomposed, at least one sub-task node of the associated node is displayed, and the sub-task node and the triggered node are displayed together, which can realize the dynamic presentation of the execution order constraint and ensure the consistency of data between the application and the server.

[0090] In one embodiment, displaying at least one child task node of an associated node includes: starting from the associated node and extending in a direction away from the parent node of the associated node to display at least one child task node of the associated node.

[0091] Specifically, when a related task is broken down into subtasks, the application can start from the associated node representing the related task and display multiple subtask nodes of that associated node, allowing these subtask nodes to extend in a direction away from their parent node. For example, such as... Figure 4 As shown, the subtasks obtained from the decomposition of the "Product Parameter Query" task extend to the right starting from task node 402.

[0092] Optionally, the multiple task nodes for the query content can form a directed acyclic graph (DAG). A 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 edge connecting two nodes represents the parent-child relationship between the two tasks corresponding to those nodes. In this case, the multiple sub-task nodes obtained by decomposing the associated node can extend in the DAG from the associated node in a direction away from the task planning node. The task planning node represents the planning task used to plan tasks for the query content, resulting in multiple tasks.

[0093] In an optional embodiment, such as Figure 5 As shown, the user's query is first processed and categorized by the large language model. If the question is simple, it is answered directly; if it is complex, a decomposition plan needs to be developed. Optionally, the large language model can output a structured decomposition plan. Optionally, the task execution results can be further input into the large language model for deeper breakdown. Optionally, question understanding can be the root task of the query, and the tasks derived from it can be the next-level subtasks, and so on, until the result matches the user's query requirements.

[0094] In the above embodiments, starting from the associated node, the process extends in the direction away from the parent node of the associated node to display at least one child task node of the associated node. This can intuitively present the hierarchical relationship between nodes and enrich the content information displayed.

[0095] In one embodiment, the query processing method further includes: obtaining the phased execution results of the associated task; if the phased execution results indicate that the associated task does not meet the execution completion conditions, decomposing the associated task to obtain at least one sub-task.

[0096] In practical applications, each task execution process can undergo at least one round of "thinking-action-observation" iteration. This "thinking-action-observation" process is called an iteration round, and the execution result obtained by calling the tool in one iteration round is called the stage execution result of that iteration round. The thinking content corresponding to the next thinking stage is determined based on the stage execution result of the previous round. This thinking content can represent the thought activities generated in response to the stage execution result of the previous round, including analysis of the previous stage execution result, judgment of information needs, and planning of the next action. Optionally, when the thinking content indicates that the stage execution result generated in the previous round is incomplete, the thinking content can include supplementary information expected to be obtained through the next iteration. The server can then decompose related tasks according to the thinking content to obtain at least one sub-task.

[0097] Optionally, the degree of matching can be determined by matching the phased execution results of the associated task with the task requirements of that associated task. Optionally, the task requirements can be extracted from the task description information. Optionally, the degree of matching can be determined by semantic matching or keyword matching between the phased execution results and the task requirements. Optionally, if the degree of matching between the phased execution results and the task description information is less than or equal to a matching threshold, it can be determined that the associated task does not meet the execution completion conditions.

[0098] Optionally, if the interim execution results indicate that the associated task meets the completion conditions, then the status of the associated task can be determined as completed. Optionally, the execution result information of the associated task can be determined based on the interim execution results obtained in each iteration round; specifically, the final execution result of the associated task can be obtained by integrating the interim execution results. Optionally, the execution result information of the associated task can also be obtained by summarizing the various execution results of each subtask.

[0099] In the above embodiments, when the phased execution result indicates that the associated task does not meet the execution completion conditions, the associated task is decomposed to obtain at least one sub-task. The execution result of the task can be continuously corrected through task decomposition, so that users can perceive the iterative logic in the task execution process in real time, which can improve trust, reduce the number of follow-up queries, and further improve the quality and efficiency of query result generation.

[0100] In one embodiment, the associated task is decomposed to obtain at least one subtask, including: calling a large language model to analyze the phased execution results and obtain task decomposition data of the associated task; obtaining at least one set of visualization node data by parsing the task decomposition data; and determining the subtask represented by the visualization node data.

[0101] Optional, such as Figure 5 As shown, a large language model can be used to analyze the current stage of execution results of associated tasks to determine whether the associated task meets the completion conditions. If the associated task does not meet the completion conditions, task breakdown data of the associated task is output to achieve task decomposition. Optionally, the task breakdown data can be predefined structured data. For example... Figure 6 As shown, task breakdown data can include plan name (Name), plan identifier (Id), plan description (Description), tools to be called (Agent), input parameters (Inputs), and the steps after which execution can proceed (AfterList). In other words, the specific method for breaking down related tasks is similar to the initial task breakdown for the query content, resulting in structured task breakdown data.

[0102] Optionally, the task breakdown data may include data information corresponding to multiple steps. Computer devices can parse the task breakdown data, break it down according to the steps to obtain multiple sets of visual node data, and determine the subtasks corresponding to each set of visual node data. In other words, each Step in the task breakdown data can correspond to a subtask, and when this subtask is executed, a subtask node is automatically generated.

[0103] In an optional embodiment, at least one set of visualization node data is obtained by parsing the task breakdown data, including: determining at least one tool to be invoked by parsing the task breakdown data; and determining visualization node data corresponding to the invocation process for each tool.

[0104] Optionally, the task to be performed can be achieved by invoking tools. These tools can be external functions, programs, APIs, or services invoked through predefined interfaces, with the aim of extending the core capabilities of the intelligent agent. In specific implementations, tools may include document conversion tools, web search tools, webpage reading tools, report generation tools, image generation tools, chart generation tools, webpage generation tools, etc. Optionally, the task breakdown data may contain invocation information for multiple tools, such as web retrieval and image generation. The computer device can analyze the task breakdown data to determine at least one tool to be invoked, and break down each tool invocation into a set of visual node data to obtain the corresponding sub-tasks.

[0105] For example, the data breakdown for Task A involves online search tools and chart generation tools. The invocation process of each tool can be packaged into visual node data, yielding sub-tasks corresponding to the online search process and the chart generation process, respectively. It's understandable that invoking a specific tool depends on the user's query requirements; for example, if the user indicates that an online search is not needed, the online search tool will not be invoked.

[0106] In the above embodiments, encapsulating the tool invocation process as visualized node data simplifies the task splitting logic and helps improve work efficiency.

[0107] In an optional embodiment, at least one set of visualization node data is obtained by parsing the task decomposition data, including: determining at least one tool to be invoked by parsing the task decomposition data; determining the invocation purpose of the tool if multiple agents are deployed for that tool; and determining the corresponding visualization node data for each invocation purpose.

[0108] The same tool can correspond to one or more invocation purposes. For example, the invocation purposes of an online search tool may include "querying camera parameters," "querying battery life parameters," and "querying price." When multiple agents are deployed for the same tool, splitting the data into multiple sets of visual node data according to the invocation purpose allows the tasks represented by each visual node data to be assigned to each agent for concurrent execution, thereby achieving concurrent task scheduling and improving work efficiency.

[0109] In one exemplary embodiment, the visualized node data can be structured data. For example, this visualized node data is used to describe the attribute information of task nodes, such as... Figure 7As shown, this attribute information can include task title, task description, task creation time (CreatedAt), task status, prerequisite tasks (WaitTasks), and a list of child nodes (ChildrenIds). The AfterList in the task breakdown data is a dependency description of the step names. By converting AfterList into WaitTasks and step names into task IDs, the transformation from task breakdown data to visual node data can be completed. Optionally, parent-child relationships and dependencies can be represented using the ParentId, ID, and WaitTasks fields. This ensures the atomicity of storing individual nodes; each node update only needs to save itself, without needing to understand the structure and distribution of the entire DAG graph, achieving high concurrency and distributed storage.

[0110] Optional, such as Figure 8 As shown, the task status information includes execution status and progress percentage, used to drive the front-end visualization. Task statuses include waiting to execute, executing, successful, failed, etc., along with the specific execution duration and progress percentage. In the code, the front-end status can be maintained by updating the status display of each node in real time based on the running status of each task.

[0111] Optionally, each node, during execution, checks whether all WaitTasks nodes have finished running (success or failure is considered completion). If waiting nodes exist, the current node's status is set to WAITING. This node can only execute after the preceding steps are completed. Simultaneously, the results of all preceding nodes are transmitted to this node as context information. This node can then pass this collected information to its Agent for processing.

[0112] Optionally, the pseudocode flow for execution order dependency detection and context data passing is as follows:

[0113] var collected_info string

[0114] if len(waitTasks) > 0 {

[0115] / / Set the current node to a waiting state

[0116] }

[0117] for waitTasks {

[0118] / / Recursively traverse all dependent nodes, ensuring that all child nodes generated from them are automatically dependent. Add to waitTasks

[0119] }

[0120] for waitTasks {

[0121] / / Retrieve the execution result of the node. If successful, retrieve the result and append it to the collected information (collected_info). If it failed, skip it. If it is still executing, wait 1 second and query again.

[0122] }

[0123] / / If all nodes have finished, set the current node to the RUNNING state. Run the task for the current node based on collected_info.

[0124] In the above embodiments, by calling the large language model, the phased execution results are analyzed to obtain the task decomposition data of the related tasks, and at least one set of visualization node data is further parsed to determine the sub-tasks represented by the visualization node data. This can overcome the problem that the large language model cannot directly output visualization nodes through data conversion, and realize the synchronization of task decomposition and visualization presentation.

[0125] Optionally, the triggered node and its associated nodes can be displayed in the same window. Alternatively, the triggered node and its associated nodes that have execution order constraints with the triggered node can also be displayed in other windows such as pop-ups or floating windows.

[0126] In one embodiment, multiple task nodes planned for the query content are displayed, including: displaying multiple task nodes based on the query content planning in a mind map for the query content. In this embodiment, the triggered node and associated nodes that have execution order constraints with the triggered node are displayed together, including: displaying the triggered node and associated nodes that have execution order constraints with the triggered node together in the mind map.

[0127] Specifically, a mind map can be used to display multiple task nodes planned for the query content, establishing the parent-child relationships between these nodes. Furthermore, when any task node is triggered, the mind map will display the triggered node and any related nodes with execution order constraints. This allows for incremental rendering of the association markers between the triggered node and its related nodes, building upon the current display page. This helps conserve computing resources and reduce system latency.

[0128] Understandably, when the triggered node and its associated nodes are displayed in other windows of the same window as the mind map, it is not necessary to display the complete mind map; only the triggered node and its associated nodes need to be shown.

[0129] In an optional embodiment, the associated display of the triggered node and the associated nodes that have execution order constraints with the triggered node in the mind map includes at least one of the following: enhancing at least one visual parameter of the connecting line between the triggered node and the associated node of the triggered node in the mind map; weakening at least one visual parameter of the connecting line other than the connecting line between the triggered node and the associated node in the mind map.

[0130] The visual parameters of a connecting line refer to parameters used in visual presentation to describe the appearance and visual effect of the connecting line. These parameters affect the visual performance of the connecting line in graphics and interfaces. These visual parameters can include color, line width, transparency, and line type. For example, enhancing color can mean increasing the chroma of a color, such as changing from light green to dark green; enhancing transparency can mean decreasing the transparency of the line; and enhancing line type can mean changing from a dashed line to a solid line. In an optional embodiment, the visual effect can also be enhanced by adding shadows or highlights, or by adding animation effects.

[0131] In practical applications, the association between the triggered node and its associated nodes can be displayed by highlighting the connecting lines between them. Highlighting certain connecting lines can include enhancing their visual parameters and / or weakening the visual parameters of other connecting lines. For example, such as... Figure 2 As shown, the connection between the triggered node and its associated nodes can be highlighted by increasing the line width of the connecting lines. Alternatively, the connection between the triggered node and its associated nodes can be highlighted by decreasing the line width of other connecting lines.

[0132] In an optional embodiment, taking the case where the associated node is the preceding node as an example, such as... Figure 9 As shown, a mind map can be used to display the various task nodes corresponding to the query "Compare the performance of product a and manufacturer B's latest flagship phone in terms of photography and battery life". Users can click on node 901 to trigger the node, and then the application can determine the preceding nodes of node 901 from the mind map and highlight the connecting lines between these preceding nodes and node 901.

[0133] In the above embodiments, in the mind map, at least one visual parameter of the connecting line between the triggered node and its associated nodes is enhanced, and / or at least one visual parameter of other connecting lines besides the connecting line between the triggered node and its associated nodes is weakened, so as to realize the visual presentation of the execution order constraint. Based on the current view, the changed visual parameters can be rendered incrementally, which can save computing resources and reduce system latency.

[0134] In an optional embodiment, the mind map displays the triggered node and the associated nodes that have execution order constraints with the triggered node, including: in the mind map, corresponding to the triggered node and the associated nodes that have execution order constraints with the triggered node, displaying association identifiers representing execution order constraints respectively.

[0135] The association identifier may include at least one of the following: icon, letter label, dynamic connector, etc. Optionally, the dynamic connector may refer to the connector displayed when a task node is triggered. Optionally, the association identifier may be displayed in the content cards corresponding to the triggered node and its associated nodes, or it may correspond to the association identifier through a connector or display style.

[0136] Optionally, the execution order constraints between tasks can include pre-constraints, post-constraints, and concurrency constraints. In this case, different types of order constraints can correspond to different association identifiers. For example, pre-constraints can display association identifiers containing the word "pre-"; post-constraints can display association identifiers containing the word "post-"; and concurrency constraints can display association identifiers containing the word "same".

[0137] Optionally, the display style of the triggered node and its associated nodes can be changed to achieve associated display. For example, the triggered node and its associated nodes can be displayed in pink, while other nodes can be displayed in black.

[0138] In the above embodiments, the associated display of the triggered node and its associated nodes is realized through the association identifier, which can intuitively present the execution order constraints between nodes and help improve the information display effect.

[0139] In one embodiment, in response to a triggering event for any task node, the triggered node and associated nodes that have execution order constraints with the triggered node are displayed together, including: in response to a triggering event for any task node, determining the triggered node and associated nodes that have execution order constraints with the triggered node; and for each associated node, displaying the triggered node and associated nodes together according to the type of order constraint between the triggered node and the associated node.

[0140] The sequence constraint types can include pre-constraints, post-constraints, and concurrent constraints. In response to a trigger event for any task node, the computer device can determine the triggered node and query the node information of the triggered node for associated nodes that have execution sequence constraints with it. Optionally, it can determine the pre-constraint task from the "WaitTasks" field of the triggered task, thus determining the pre-constraint node representing the pre-constraint task; or it can determine the post-constraint task by reading the "WaitTasks" field of other tasks, including other task nodes of the triggered task in the "WaitTasks" field, thus determining the post-constraint task representing the post-constraint task. Furthermore, the computer device can display the triggered node and its associated nodes in association according to the sequence constraint type between the triggered node and associated nodes.

[0141] Optionally, different sequence constraint types can be distinguished by the way the nodes are displayed. For example, the connection line between the triggered node and its predecessor node can be displayed in red, while the connection line between the triggered node and its successor node can be displayed in green.

[0142] Optionally, different association identifiers can be used to represent different types of sequence constraints.

[0143] Optionally, the associated display of the triggered node and its associated nodes can be achieved by changing the display style of the triggered node and its associated nodes. The display style may include at least one of the following: shape, color, etc.

[0144] In the above embodiments, the triggered node and the associated node are displayed in association according to the order constraint type between the triggered node and the associated node. This enables a visual display of the order constraint type, provides more information, and helps to further improve the information display effect.

[0145] In one embodiment, the sequence constraint type includes a prerequisite constraint. In this embodiment, the triggered task represented by the triggered node is executed after the prerequisite task represented by the prerequisite node on which the triggered node depends. In this embodiment, displaying the triggered node and its associated nodes together includes: determining the dependency method of the triggered node on each prerequisite node of the triggered node; and displaying the triggered node and its predecessor nodes together according to an association method that matches the dependency method.

[0146] The dependency of the triggered node on the preceding node can include execution order dependency with data transfer (referred to as data dependency) and execution order dependency without data transfer (referred to as order dependency). Data dependency is an inherent, logically mandatory dependency, meaning that without the output of the preceding task, the triggered task either cannot be executed or the execution result is incorrect. In other words, the correct execution of the triggered task depends on the calculation result or output data of the preceding task.

[0147] Sequential dependency is an external dependency based on optimization or rule constraints. Reversing the order might be logically feasible, but it's inefficient or not permitted. In other words, the triggered task doesn't need the data from the preceding task, but due to efficiency, resource, or strategy reasons, it needs to execute after the preceding task. For example, the triggered task is "to perform a write operation to file A," and the preceding task is "to read the contents of file A and analyze it." Although theoretically, file reading can be done in parallel, completing all writes before starting reading avoids read-write lock conflicts, ensures data consistency, and may utilize the better data locality generated after writing, thereby improving overall I / O efficiency. Similarly, in a multi-agent system, when the number of deployed query agents cannot support the concurrent execution of all ready query tasks, the execution order of each task can be determined based on its level. The level of a task is determined by the number of nodes between the task and the root task; the closer to the root task, the earlier it is executed. For example,... Figure 10 As shown, tasks 2, 3, and 4 are at the same level, while task 5 is at the next level. In the absence of data dependencies, if both task 5 and task 3 are query tasks in a ready state, task 3 will be assigned the corresponding query agent first because it is closer to the root task 1. Therefore, task 5 will be executed after task 3, and there is a sequential dependency between the two.

[0148] Specifically, different dependency methods can be presented in different ways. Thus, the application can determine the dependency method of the triggered node on each preceding node for the triggered node, and display the triggered node and the preceding node in association according to the association method that matches the dependency method.

[0149] Optionally, data dependencies and sequence dependencies can be distinguished by at least one of the following: connection style, color, annotation, or interactive information. For example, a solid arrow pointing from the preceding node to the triggered node indicates that the triggered node has a data dependency on the preceding node; optionally, the transmitted data content or variable name can be annotated next to the connection. A dashed arrow pointing from the preceding node to the triggered node indicates that the triggered node has a sequence dependency on the preceding node; optionally, the reason for the dependency can be displayed next to the connection. Furthermore, the type of dependency constraint can be indicated by modifying the task node itself. For example, a task node pointed to by a solid arrow can be highlighted with a special background color or a bold border to indicate "My input depends on upstream data"; only task nodes pointed to by dashed arrows retain their original display style.

[0150] In the above embodiments, the triggered node and the preceding node are displayed in association according to the dependency method of the triggered node on the preceding node, which can intuitively present the dependency method between tasks and help to further improve the information display effect.

[0151] In an optional embodiment, the triggered node and its predecessor node are displayed in association according to an association method that matches the dependency method, including: when the dependency method is sequential dependency, highlighting the connection path between the triggered node and its predecessor node. The connection path between the triggered node and its predecessor node may include multiple connection lines, and the highlighting of the connection path can be achieved by enhancing at least one visual parameter of these connection lines.

[0152] In an optional embodiment, the triggered node and the preceding node are displayed in association according to the association method that matches the dependency method, including: highlighting the connection path between the triggered node and the preceding node when the dependency method is data dependency; and displaying the data transfer direction between the triggered node and the preceding node corresponding to the connection path.

[0153] When the dependency is data-dependent, the application can highlight the connection path between the triggered node and the preceding node, and based on this, display the data transfer direction between the triggered node and the preceding node corresponding to the connection path. Optionally, the data transfer direction can be indicated by a clear arrow on the connection path (from the preceding node to the triggered node); alternatively, animation can be used to represent the data transfer direction, with the direction of the animation indicating the data flow.

[0154] For example, such as Figure 11The example shown illustrates a mind map containing tasks A, B, C, D, and E. Tasks A and B have no data dependency, but task B must be executed after task A (sequential dependency); tasks A and C have a data dependency, with A outputting data to C; tasks B and C have no dependency; tasks C and D have a data dependency, with C outputting data to D; and tasks D and E have a data dependency, with D outputting data to E. When no nodes are triggered, all nodes and connections are displayed normally. When the task node corresponding to task D is triggered, it is highlighted (e.g., in bright blue). Task C is a prerequisite node for task D with a data dependency, and task A is a prerequisite node for task C with a data dependency. Therefore, the connection path A→C→D is highlighted (e.g., displayed as a solid red line), and animations are added to these two connections to indicate data flow from A to C, and then from C to D. Optionally, other nodes (B and E) and connections can become semi-transparent. In this way, the user can clearly see the data source path for task D: A→C→D.

[0155] In the above embodiments, highlighting paths and displaying directions for data dependencies provides the system with structured visual information, driving automated system decision-making and optimization, thereby achieving a comprehensive improvement in resource utilization, execution efficiency, and system reliability. For example, when a task fails, it can quickly pinpoint which part of the data flow went wrong, facilitating subsequent modifications and further improving the quality and efficiency of query result generation.

[0156] In some embodiments, the sequence constraint type includes a post-constraint, where the triggered task represented by the triggered node is executed before the post-task represented by the subsequent node of the triggered node. In this embodiment, displaying the triggered node and associated nodes together includes: for each subsequent node of the triggered node, determining the dependency relationship between the triggered node and the subsequent node; and displaying the triggered node and the subsequent node together according to an association method that matches the dependency relationship.

[0157] Optionally, when the dependency method is data dependency, the application can highlight the connection path between the triggered node and the subsequent node, and display the data transfer direction between the triggered node and the subsequent node corresponding to the connection path.

[0158] Optionally, when the dependency type is sequential dependency, the application can highlight the connection path between the triggered node and its successor nodes. The connection path between the triggered node and its successor nodes can include multiple connection lines, and the highlighting of the connection path can be achieved by enhancing at least one visual parameter of these connection lines.

[0159] In one embodiment, the display style of a task node when it is not triggered is a first display style. In this embodiment, the query processing method further includes: in response to a trigger event for any task node, changing the display of the triggered node from the first display style to a second display style indicating that it has been triggered.

[0160] The display style may include at least one of color, shape, status indicator, etc. A first display style indicates that the node has not been triggered, and a second display style indicates that the node is in a triggered state. Optionally, the first display style differs from the second display style in at least one of color, shape, status indicator, etc. For example, an untriggered task node may be displayed as black, and a triggered task node may be displayed as blue. In an exemplary embodiment, such as... Figure 9 As shown, the triggered node 901 can be highlighted using the second display style, while the remaining nodes will be displayed using the first display style.

[0161] In the above embodiments, the triggered state of the task node can be presented intuitively by changing the display style, which can enrich the displayed information content and improve the information display effect.

[0162] In some embodiments, displaying multiple task nodes planned for the query content includes: displaying multiple task nodes planned for the query content in a first display area of ​​the content display page. In this embodiment, the query processing method further includes: displaying detailed information corresponding to the triggered node in a second display area of ​​the content display page.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] In one exemplary embodiment, such as Figure 12 As shown, the content display page 1200 may include three display areas. The first display area 1201 displays the query content (corresponding to the current question in the diagram), multiple task nodes planned for the query content, the execution results for the query content, and follow-up query content. The second display area 1202 displays the details of the triggered node. Optionally, multiple task nodes can be presented using a mind map, which can be generated and updated in real time. When any node in the mind map is triggered, the second display area 1202 can display the details of the triggered node, and the mind map in the first display area 1201 also highlights the triggered node by changing the node display style, and displays the context data transmission and execution order dependencies of the triggered node by changing the line display style. Optionally, the content display page 1200 may also include a third display area 1203 for displaying the historical task records of the currently logged-in user.

[0167] In the above embodiments, by displaying multiple task nodes in the first display area of ​​the content display page and displaying the detailed information corresponding to the current task in the second display area of ​​the content display page, it is possible to display the detailed information of any task node.

[0168] In an optional embodiment, the query processing method further includes: displaying task description information of the triggered task represented by the triggered node in a first display area, corresponding to the triggered node.

[0169] The task description information may include at least one of the following: the tools used in the task, the task content, and the task objective. For example, such as... Figure 13 As shown, the task description information for the triggered task "Overview of Mainstream Kayaks in the Market" could be "Through online searches, learn about the brands and models of kayaks currently on the market that are suitable for weekend reservoir trips and are foldable or inflatable, easy to carry and store." Optionally, the task description information can be displayed via pop-ups, floating windows, etc. Optionally, the task description information can be associated with the triggered node through at least one of the following: display location, display style, node identifier, etc. For example, such as... Figure 13 In the middle, task description information 1301 is displayed below the triggered node.

[0170] In the above embodiments, in the first display area, corresponding to the triggered node, the task description information of the triggered task represented by the triggered node is displayed, which can present richer information content for the triggered node and is conducive to improving the information display effect.

[0171] In an optional embodiment, the second display area of ​​the content display page displays detailed information corresponding to the triggered node, including: when the task status corresponding to the triggered node is in execution, displaying the execution details information corresponding to the triggered node in the second display area of ​​the content display page; and when the task status corresponding to the triggered node is completed, displaying the execution result information corresponding to the triggered node in the second display area.

[0172] Optionally, if the task status corresponding to task node A is "in execution," then when task node A is triggered, its execution details can be dynamically displayed via a floating layer in the second display area of ​​the content display page. If the task status of task node A is "execution completed," then when task node A is triggered, its execution result information can be displayed via a floating layer in the second display area. Optionally, the floating layer can also display the execution details corresponding to task node A. Optionally, the floating layer can be displayed directly or as a top-down pop-up. Those skilled in the art may make other changes based on the essence of this application's technology, but as long as the functions and effects achieved are the same as or similar to those of this application, they should all be covered within the scope of protection of this application.

[0173] Optionally, when a task is terminated due to a system upgrade, the currently executing task node will be displayed as a failure. If the user triggers a successfully executed task node, the application can display the execution result of the task represented by that task node in the second display area.

[0174] 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 application 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 transmission methods include Server-Sent Events (SSE) and the WebSocket protocol.

[0175] In the above embodiments, the display of execution details can be triggered by either an ongoing task node or a completed task node, displaying the corresponding execution result information. This facilitates the viewing of task nodes, enables dynamic interaction with task nodes, and improves the observability of the task system. 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 such limitations.

[0176] In one specific embodiment, a method is provided as follows: Figure 14 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:

[0177] Step S1401: Obtain the query content;

[0178] Step S1402: In the first display area of ​​the content display page, display multiple task nodes based on the query content planning in the first display style;

[0179] Each task node can form a mind map;

[0180] Step S1403: In response to a trigger event for any task node, the triggered node is displayed by changing from the first display style to the second display style that indicates that it has been triggered.

[0181] Step S1404: In the first display area, corresponding to the triggered node, display the task description information of the triggered task represented by the triggered node;

[0182] Step S1405: Display the details of the triggered node in the second display area of ​​the content display page;

[0183] Optionally, if the task status corresponding to the triggered node is in execution, the execution details information of the triggered node will be displayed in the second display area of ​​the content display page; if the task status corresponding to the triggered node is in execution completed, the execution result information of the triggered node will be displayed in the second display area of ​​the content display page.

[0184] Step S1406: Determine the associated nodes that have execution order constraints with the triggered node, and the type of order constraint between the triggered node and the associated node;

[0185] The sequence constraint types include pre-constraints, post-constraints, and concurrent constraints; the associated nodes that have execution sequence constraints with the triggered node may include at least one of the following: the pre-constraint node that the triggered node depends on, the post-constraint node that depends on the triggered node, or the concurrent node of the triggered node.

[0186] Step S1407: Display the triggered node and associated node in the mind map according to the association method that matches the sequence constraint type;

[0187] Optionally, different colors can be used in the mind map to represent the connecting lines between the triggered node and different types of related nodes; for example, the triggered node is connected to the predecessor node by a red line, the triggered node is connected to the successor node by a green line, and the triggered node is connected to the concurrent node by a yellow line.

[0188] Optionally, the association identifier representing the type of sequence constraint can be determined, and the corresponding association identifier can be displayed in the mind map for the triggered node and the associated nodes that have execution sequence constraints with the triggered node.

[0189] Optionally, for preceding or following nodes with data dependencies, the data transfer direction between the triggered node and its corresponding associated node can also be displayed;

[0190] Step S1408: When the associated task is in the execution state, obtain the phased execution results of the associated task;

[0191] Step S1409: If the phased execution result indicates that the associated task does not meet the execution completion conditions, call the large language model to analyze the phased execution result and obtain the task decomposition data of the associated task.

[0192] Step S1410: By parsing the task breakdown data, determine at least one tool to be invoked;

[0193] Step S1411: For each tool invocation process, determine the visualization node data corresponding to the invocation process and the subtasks represented by the visualization node data;

[0194] Step S1412: Starting from the associated node, extend in the direction away from the parent node of the associated node to display at least one child task node of the associated node in the mind map.

[0195] Among them, the subtask node is used to represent the subtask of the associated task; the subtask node inherits the execution order constraint between the associated node and the triggered node;

[0196] Step S1413: According to the association method matching the execution order constraint, display the subtask nodes and triggered nodes in the mind map;

[0197] Among them, the triggered node and the associated node each represent the execution result of the task, which are used to obtain the query results of the query content.

[0198] In the above query processing, the query content is retrieved, and multiple task nodes planned for that content are displayed. Task planning allows for the breakdown of complex tasks, improving the quality and efficiency of generated responses. Furthermore, in response to a trigger event for any task node, the triggered node and associated nodes with execution order constraints are displayed. This provides a visual representation of the execution order constraints between tasks, allowing users to perceive and understand these constraints. By understanding these constraints, unexpected situations can be identified in advance, facilitating subsequent modifications and ultimately improving the quality and efficiency of query result generation.

[0199] 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.

[0200] like Figure 5 As shown, the user's query first passes through a large model for problem understanding and classification. Simple questions are answered directly, while complex questions require a decomposition plan. Among these... Figure 5 The corresponding steps within the rectangle can be implemented by calling the large language model.

[0201] Optionally, user intent can be analyzed by reading historical user interaction data to accurately understand user needs and rewrite the query. For example, the query "Is product A worth buying?" can be rewritten as "Is product A worth buying? Please provide information on its performance, price, user reviews, etc." When developing a detailed breakdown plan, the LLM can output a structured plan. Since the LLM cannot directly output visual nodes, a structured structure is defined, such as... Figure 6 The data structure shown describes the task hierarchy and invocation dependencies. Optional, such as... Figure 5As shown, the large language model can be used to analyze the current stage execution results of related tasks to determine whether the related tasks meet the completion conditions. If the related tasks do not meet the completion conditions, task breakdown data of the related tasks is output to achieve task breakdown. That is, each plan analyzed by LLM is a list of Plans (task breakdown data), which can include plan name (Name), plan identifier (Id), plan description (Description), tools to be called (Agent), input parameters (Inputs), and after which steps can be executed (AfterList).

[0202] Optionally, the task breakdown data may include data information corresponding to multiple steps. Computer devices can parse the task breakdown data, break it down according to the steps to obtain multiple sets of visual node data, and determine the subtasks corresponding to each set of visual node data. That is, each Step in the task breakdown data can correspond to a subtask, and when this subtask is executed, a subtask node is automatically generated. For example, such as... Figure 5 As shown, the query "Is product A worth buying?" can be broken down into multiple steps, from Step 1 to Step N. Step 1 could be, for example, "Querying information about product A". Step 2 could be, for example, "Conducting a comprehensive analysis of product A from multiple dimensions such as performance, price, and user reviews". Step 3 could be, for example, "Evaluating whether product A is worth buying and ultimately providing a purchase recommendation". Step N could be, for example, "Outputting results". Step 2 is further broken down into three sub-tasks: SubStep 1, SubStep 2, and SubStep 3. The intermediate results generated after these sub-tasks are executed will be aggregated for further analysis and used to generate the final query results. Optionally, SubStep 1 could be, for example, "Analyzing and comparing the performance of products A, B, and C". SubStep 2 could be, for example, "Analyzing and comparing the prices of products A, B, and C". SubStep 3 could be, for example, "Analyzing and comparing the user reviews of products A, B, and C".

[0203] Optionally, the task can be executed by calling tools, which may include query tools, image generation tools, icon generation tools, report generation tools, web page generation tools, etc.

[0204] Optionally, after a user submits a complex task, the LLM generates a Plan list with AfterList. It parses the AfterList field in the Plan list, automatically verifies and generates a loop-free DAG structure, ensuring clear parent-child task dependencies and providing structural support for the subsequent ordered scheduling by the scheduling engine. A Tree structure is used to represent this, with parent-child relationships and dependencies represented by ParentId, ID, and WaitTasks fields. This ensures only the atomicity of single-node storage; each node update only needs to save itself, without needing to understand the entire DAG structure, achieving high concurrency and distributed storage.

[0205] Optionally, AfterList is a dependency description of the step name. The generated mind map nodes will each have a task_id. During the application, AfterList can be converted into WaitTasks by the program, from step name to task_id. Then, the execution status and result of the dependent nodes can be obtained through task_id.

[0206] Optionally, each node can check whether all WaitTasks nodes have finished running (success or failure is considered complete) during execution. If there are waiting nodes, the current node's status will be WAITING. This node can only execute after the preceding steps are completed. At the same time, the results of all preceding nodes will be brought to this node as context information. This node can then hand over this collected information to its Agent for processing.

[0207] In one exemplary embodiment, such as Figure 10 As shown, assume the WaitTasks relationship between task nodes is as follows: Task 3 depends on Task 2, Task 4 depends on both Task 2 and Task 3, Task 6 depends on Task 5, and Task 9 depends on Task 8.

[0208] During front-end interaction, if node 3 is triggered, since task 3 depends on task 2, task 3 will automatically depend on all subtasks of task 2. That is, task 3 must wait for tasks 2, 5, 6, and 7 to finish executing before it can execute. In this situation, if... Figure 15 As shown, the task node for the above task will be displayed in association with node 3.

[0209] If node 9 is triggered, since task 9 depends on task 8, and task 8 has no prerequisite tasks, in this case, as follows: Figure 16 As shown, node 8 of task 8 is displayed in association with node 9.

[0210] If node 4 is triggered, since task 4 depends on tasks 2 and 3, it depends on all subtasks of tasks 2 and 3. In this case, as follows: Figure 17 As shown, the task node for the above task will be displayed in association with node 4.

[0211] Optional, such as Figure 18 As shown, the system can establish a persistent connection via WebSocket to push task change data to the application in real time, enabling incremental updates and rendering of node states. Figure 19 As shown, the task change data can include dynamically generated child node data, task execution progress, task status changes, etc. For example, newly generated child nodes can be appended to the end of the timeline in the mind map for incremental rendering and display; updates to task execution progress can be achieved by replacing the progress percentage number; and the display color of the task node can be adjusted accordingly for task status changes.

[0212] In the above embodiments, by making the task decomposition process transparent, users can clearly see how the system breaks down complex problems into multiple sub-task nodes, understand the system's working logic, and enhance their trust in the system. This solves the problem that the task decomposition process is completely invisible to users in traditional solutions. A mind map is used to illustrate the parent-child node relationships, and nodes can be selected to display runtime node dependencies, showing the flow of collected data and the execution order dependencies.

[0213] 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.

[0214] Based on the same inventive concept, this application also provides a query processing apparatus for implementing the query processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more query processing apparatus embodiments provided below can be found in the limitations of the query processing method described above, and will not be repeated here.

[0215] In some embodiments, such as Figure 20 As shown, a query processing device is provided, including an acquisition module 2001, a task node display module 2002, and an association display module 2003, wherein:

[0216] Module 2001 is used to retrieve query content;

[0217] The task node display module 2002 is used to display multiple task nodes planned for the query content;

[0218] The associated display module 2003 is used to respond to a trigger event for any task node and to display the triggered node and the associated nodes that have execution order constraints with the triggered node. The triggered node and the associated nodes each represent the execution result of the task and are used to obtain the query result of the query content.

[0219] In one embodiment, the associated task represented by the associated node is in an executing state. In this embodiment, the query processing device further includes: a subtask node display module, used to display at least one subtask node of the associated node during the execution of the associated task; the subtask node is used to represent a subtask of the associated task; the subtask node inherits the execution order constraint between the associated node and the triggered node; the associated display module 2003 is also used to display the subtask node and the triggered node in association.

[0220] In one embodiment, the subtask node display module is specifically used to: starting from the associated node, extend in a direction away from the parent node of the associated node, and display at least one subtask node of the associated node.

[0221] In one embodiment, the query processing device further includes: a phased execution result acquisition module, used to acquire the phased execution result of the associated task; and a task decomposition module, used to decompose the associated task to obtain at least one sub-task when the phased execution result indicates that the associated task does not meet the execution completion conditions.

[0222] In one embodiment, the task decomposition module includes: a task decomposition unit, used to analyze the phased execution results by calling a large language model to obtain task decomposition data of related tasks; a node data conversion unit, used to obtain at least one set of visualized node data by parsing the task decomposition data; and a subtask determination unit, used to determine the subtasks represented by the visualized node data.

[0223] In one embodiment, the node data transformation unit is specifically used to: determine at least one tool to be invoked by parsing task decomposition data; and determine the visual node data corresponding to the invocation process for each tool.

[0224] In one embodiment, the task node display module 2002 is specifically used to: display multiple task nodes planned based on the query content in a mind map of the query content. In this embodiment, the association display module 2003 is specifically used to: display the triggered node and the associated nodes that have execution order constraints with the triggered node in the mind map.

[0225] In one embodiment, the associated display module 2003 is specifically configured to perform at least one of the following: in a mind map, enhancing at least one visual parameter of the connecting line between the triggered node and its associated nodes; in a mind map, weakening at least one visual parameter of the connecting line other than the connecting line between the triggered node and its associated nodes.

[0226] In one embodiment, the association display module 2003 is specifically used to: in the mind map, display association identifiers representing execution order constraints corresponding to the triggered node and the associated nodes that have execution order constraints with the triggered node.

[0227] In one embodiment, the associated display module 2003 includes: an associated node determination unit, configured to determine, in response to a triggering event for any task node, a triggered node and associated nodes that have execution order constraints with the triggered node; and an associated display unit, configured to display the triggered node and associated nodes in association according to the order constraint type between the triggered node and the associated node for each associated node.

[0228] In one embodiment, the sequence constraint type includes a prerequisite constraint; the triggered task represented by the triggered node is executed after the prerequisite task represented by the prerequisite node on which the triggered node depends. In this embodiment, the associated display unit is specifically used to: determine the dependency method of the triggered node on each prerequisite node of the triggered node; and associate and display the triggered node and the prerequisite node according to the association method that matches the dependency method.

[0229] In one embodiment, the associated display unit is specifically used to: highlight the connection path between the triggered node and the preceding node when the dependency method is data dependency; and display the data transmission direction between the triggered node and the preceding node corresponding to the connection path.

[0230] In one embodiment, the display style of a task node when it is not triggered is a first display style. In this embodiment, the task node display module 2002 is further configured to: in response to a trigger event for any task node, change the display style of the triggered node from the first display style to a second display style indicating that it has been triggered.

[0231] In one embodiment, the task node display module 2002 is specifically used to display multiple task nodes planned for the query content in the first display area of ​​the content display page. In this embodiment, the query processing device further includes a details information display module, used to display details information corresponding to the triggered node in the second display area of ​​the content display page.

[0232] In one embodiment, the query processing device further includes a description information display module, used to display task description information of the triggered task represented by the triggered node in a first display area, corresponding to the triggered node.

[0233] In one embodiment, the details display module is specifically used to: display the execution details information of the triggered node in the second display area of ​​the content display page when the task status of the triggered node is in execution; and display the execution result information of the triggered node in the second display area of ​​the content display page when the task status of the triggered node is in execution completed.

[0234] The above query processing configuration includes a module that retrieves the query content and a module that displays multiple task nodes planned for the query content. This task planning allows for the breakdown of complex tasks, improving the quality and efficiency of the generated response. Furthermore, the associated display module responds to trigger events for any task node, displaying the triggered node and related nodes with execution order constraints. This provides a visual representation of the execution order constraints between tasks, allowing users to perceive and understand these constraints. By understanding these constraints, unexpected situations can be identified in advance, facilitating subsequent modifications and ultimately improving the quality and efficiency of query result generation.

[0235] Each module in the aforementioned query processing 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.

[0236] In some embodiments, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 21 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data involved in query processing, specifically including resource conversion request information, quota information for different objects, and the amount of resources held. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a query processing method.

[0237] In some embodiments, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 22As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces 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 interfaces. The processor provides computational 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 interfaces are 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 executed by the processor, the computer program implements a polling processing 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.

[0238] Those skilled in the art will understand that Figure 21 or Figure 22 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.

[0239] 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 query processing method described above.

[0240] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the query processing method described above.

[0241] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the query processing method described above.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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. A query processing method, characterized in that, The method includes: Retrieve query results; Displays multiple task nodes planned for the query content; In response to a trigger event for any of the task nodes, the triggered node and associated nodes that have execution order constraints with the triggered node are displayed together. The execution results of the tasks represented by the triggered node and the associated node are used to obtain the query results of the query content.

2. The method according to claim 1, characterized in that, The associated task represented by the associated node is in the execution state; The method further includes: During the execution of the associated task, at least one sub-task node of the associated node is displayed; the sub-task node is used to represent a sub-task of the associated task; the sub-task node inherits the execution order constraint between the associated node and the triggered node; The subtask node and the triggered node are displayed together.

3. The method according to claim 2, characterized in that, The display of at least one sub-task node of the associated node includes: Starting from the associated node, extend in a direction away from the parent node of the associated node to display at least one child task node of the associated node.

4. The method according to claim 2, characterized in that, The method further includes: Obtain the phased execution results of the associated tasks; If the phased execution result indicates that the associated task does not meet the execution completion conditions, the associated task is decomposed to obtain at least one sub-task.

5. The method according to claim 4, characterized in that, The step of decomposing the associated task to obtain at least one sub-task includes: The large language model is invoked to analyze the phased execution results and obtain the task breakdown data of the associated tasks. By analyzing the task breakdown data, at least one set of visualized node data is obtained; Determine the subtask of the visualization node data representation.

6. The method according to claim 5, characterized in that, The process involves parsing the task breakdown data to obtain at least one set of visualized node data, including: By analyzing the task breakdown data, at least one tool that is expected to be invoked can be determined; For each of the tool's invocation processes, determine the corresponding visualization node data for that invocation process.

7. The method according to claim 1, characterized in that, The display shows multiple task nodes planned for the query content, including: The mind map for the query content displays multiple task nodes planned based on the query content; The associated display of the triggered node and the associated nodes that have execution order constraints with the triggered node include: The mind map displays the triggered node and the associated nodes that have execution order constraints with the triggered node.

8. The method according to claim 7, characterized in that, The association of the triggered node and the associated nodes that have execution order constraints with the triggered node in the mind map includes at least one of the following: In the mind map, enhance at least one visual parameter of the connecting line between the triggered node and the associated nodes of the triggered node; In the mind map, at least one visual parameter of the connecting lines other than the connecting line between the triggered node and the associated node is weakened.

9. The method according to claim 7, characterized in that, The mind map displays the triggered node and related nodes that have execution order constraints with the triggered node, including: In the mind map, corresponding to the triggered node and the associated nodes that have execution order constraints with the triggered node, an association identifier representing the execution order constraint is displayed.

10. The method according to any one of claims 1 to 9, characterized in that, The step of responding to a trigger event for any of the task nodes by displaying the triggered node and associated nodes that have execution order constraints with the triggered node includes: In response to a triggering event for any of the task nodes, determine the triggered node and the associated nodes that have execution order constraints with the triggered node; For each of the associated nodes, the triggered node and the associated node are displayed in association according to the order constraint type between the triggered node and the associated node.

11. The method according to claim 10, characterized in that, The sequence constraint type includes a prerequisite constraint; the triggered task represented by the triggered node is executed after the prerequisite task represented by the prerequisite node on which the triggered node depends; The association display shows the triggered node and the associated node, including: For each preceding node of the triggered node, determine the dependency relationship between the triggered node and the preceding node; The triggered node and the preceding node are displayed in association according to the association method that matches the dependency method.

12. The method according to claim 11, characterized in that, The step of associating and displaying the triggered node and the preceding node according to an association method that matches the dependency method includes: When the dependency method is data dependency, the connection path between the triggered node and the preceding node is highlighted; Corresponding to the connection path, the data transmission direction between the triggered node and the preceding node is displayed.

13. The method according to any one of claims 1 to 9, characterized in that, The task node is displayed in the first display style when it is not triggered. The method further includes: In response to a trigger event for any of the task nodes, the triggered node is changed from the first display style to a second display style that indicates that it has been triggered.

14. The method according to any one of claims 1 to 9, characterized in that, The display shows multiple task nodes planned for the query content, including: In the first display area of ​​the content display page, multiple task nodes planned for the query content are displayed; The method further includes: In the second display area of ​​the content display page, the detailed information corresponding to the triggered node is displayed.

15. The method according to claim 14, characterized in that, The method further includes: In the first display area, corresponding to the triggered node, the task description information of the triggered task represented by the triggered node is displayed.

16. The method according to claim 14, characterized in that, The second display area of ​​the content display page displays the detailed information corresponding to the triggered node, including: When the task status corresponding to the triggered node is in execution, the execution details information corresponding to the triggered node is displayed in the second display area of ​​the content display page; If the task status corresponding to the triggered node is "execution completed", the execution result information corresponding to the triggered node will be displayed in the second display area of ​​the content display page.

17. A query processing device, characterized in that, The device includes: The retrieval module is used to retrieve query content; The task node display module is used to display multiple task nodes planned for the query content; The associated display module is used to respond to a trigger event for any of the task nodes by displaying the triggered node and the associated nodes that have execution order constraints with the triggered node. The triggered node and the associated node each represent the execution result of the task, which are used to obtain the query result of the query content.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 16.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 16.

20. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 16.

Images