Intelligent agent arrangement method and device, storage medium and terminal equipment

Abstract

The embodiment of the invention discloses an agent arrangement method and device, a storage medium and terminal equipment, and relates to the field of agent editing. According to the method, the intelligent agent nodes with the same function are merged into the fused intelligent agent nodes, so that the complexity of the intelligent agent flow chart is remarkably simplified. The flow chart is clearer and easier to understand, unnecessary nodes and connecting lines are reduced, and the readability and maintainability of the flow are improved. Due to the fact that the agent nodes are combined, the user does not need to process too many details when editing and managing the agent process, the operation complexity can be reduced, and the user can complete design and adjustment of the process more quickly and more accurately. Occupancy of system resources can also be reduced by combining the agent nodes. And during operation, the fusion agent node can be processed as a whole, so that the calculation overhead and the memory occupation are reduced, and the overall performance of the system is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent body editing, and in particular to an intelligent body editing method, device, storage medium and terminal device. Background Art

[0002] In existing intelligent construction orchestration systems, the design logic generally follows the flow conditions, and then diverges to each branch node and follows a single path to the end of the process. This design seems simple and clear at first glance, but its limitations are obvious when faced with a large number of conditional branches. Specifically, this design will greatly reduce the reusability of subsequent node functions. If an existing node function needs to be used in a specific branch, the current practice is often to copy the entire process node and embed it into the target branch process. The direct consequence of this practice is that the number of nodes in the entire process increases exponentially, which greatly increases the complexity and difficulty of process design, construction, maintenance, and debugging. Summary of the invention

[0003] The embodiments of the present application provide an agent arrangement method, device, storage medium and terminal device, which can solve the problem of complex maintenance caused by the large number of agent flow chart nodes in the prior art. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for orchestrating an agent, the method comprising:

[0005] Displaying an agent arrangement page; the agent arrangement page includes a canvas and an agent template list;

[0006] Selecting an intelligent agent template from the intelligent agent template list based on a selection operation of a user, and placing the selected intelligent agent template on a canvas based on a drag operation of a user;

[0007] Adding connectors to each agent template on the canvas and configuring attribute information to generate an agent node, wherein the attribute information includes: input parameter name and output parameter name;

[0008] Detecting whether the number of agent nodes having the same function in the canvas is greater than or equal to two;

[0009] If yes, each agent node is merged into a fusion agent node according to the attribute information and connection relationship information of each agent node that meets the above conditions, and the connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

[0010] In a second aspect, an embodiment of the present application provides an agent arrangement device, the device comprising:

[0011] A push unit, used to display an agent arrangement page; the agent arrangement page includes a canvas and an agent template list;

[0012] A drawing unit, configured to select an intelligent agent template from the intelligent agent template list based on a selection operation of a user, and place the selected intelligent agent template on a canvas based on a drag operation of a user;

[0013] A configuration unit, used to generate an agent node after adding connectors to each agent template on the canvas and configuring attribute information, wherein the attribute information includes: an input parameter name and an output parameter name;

[0014] A detection unit, used to detect whether the number of agent nodes having the same function in the canvas is greater than or equal to two;

[0015] A merging unit is used to merge the various intelligent agent nodes into a fused intelligent agent node according to the attribute information and connection relationship information of the various intelligent agent nodes that meet the above conditions, if yes, wherein the connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

[0016] In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0017] In a fourth aspect, an embodiment of the present application provides a terminal device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0018] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0019] By providing an intuitive agent orchestration page, including a canvas and an agent template list, users can quickly select and place agent templates through simple drag and drop operations, simplifying the agent configuration process and improving work efficiency.

[0020] Allowing users to add connectors and configuration property information (such as input / output parameter names) to each agent template on the canvas makes the agent configuration more flexible and can meet the needs of different scenarios.

[0021] By detecting the number of agent nodes with the same function in the canvas, when the number reaches or exceeds two, these nodes are automatically merged into a fusion agent node. This function not only reduces redundant nodes and system complexity, but also optimizes resource utilization and improves the overall performance of the system.

[0022] After merging agent nodes with the same functions, the fused agent nodes formed are easier to manage and maintain on the basis of maintaining the original functions. At the same time, this merging mechanism also facilitates the future expansion of the system, making it more efficient to add new functions or modify existing functions.

[0023] By automatically detecting and merging intelligent nodes with the same functions, this technical solution demonstrates a certain level of intelligence in the system. This intelligent processing not only reduces the manual operation burden of users, but also improves the automation and response speed of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 It is a flowchart of the method for arranging an intelligent agent provided in an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of an original agent flow chart in a canvas provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of a merged agent flow chart provided in an embodiment of the present application;

[0028] Figure 4 It is a structural diagram of an arrangement device of an intelligent body provided by the present application;

[0029] Figure 5 It is a structural schematic diagram of a terminal device provided by this application. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0031] See also Figure 1 , which is a flow chart of a method for arranging an intelligent agent according to an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps:

[0032] S101. Display the agent arrangement page; the agent arrangement page includes a canvas and an agent template list.

[0033] Among them, the user starts the intelligent agent orchestration application by clicking a desktop icon, an entry in the application list, or command line input.

[0034] The terminal device (such as a computer, tablet or smart phone) loads the main program of the application and initializes the operating environment of the application, including memory allocation, process creation, etc. After the main program of the application is started, various required resources are loaded, including but not limited to: User interface (UI) resources: such as HTML, CSS, JavaScript files, which define the layout, style and interaction logic of the agent editing page. Business logic resources: such as agent template definitions, attribute configuration rules, connection relationship algorithms, etc. These resources are used to support the selection and configuration of agents. Local storage resources: such as database files, configuration files, etc. These resources may contain user historical data, application settings, etc.

[0035] The application uses the loaded UI resources to render the agent layout page through the graphics rendering engine of the terminal device (such as the browser engine, native UI framework, etc.). The page usually includes a blank canvas area (for placing agent nodes) and a list of agent templates (for users to choose from). The canvas area is implemented using the Canvas API, SVG, or other graphics technologies to support dynamic drawing and interaction. The list of agent templates is displayed through a list control (such as HTML's 、 element or native list view), each template item contains information such as the agent's icon, name, and brief description S102, selects an agent template from the agent template list based on the user's selection operation, and places the selected agent template on the canvas based on the user's drag operation.

[0036] In some embodiments of the present application, the list of agent templates is related to the application scenario, and the application first displays an application scenario selection interface. This interface may contain options for multiple application scenarios, such as "data analysis", "automated process", "Internet of Things monitoring", etc. Users specify the application scenario to which the agent arrangement they want to create or edit belongs by clicking or selecting options on the interface. Based on the application scenario selected by the user, the application loads the list of agent templates related to the scenario from a predefined template library or server. These template lists may contain agent types specific to the application scenario, such as "data source node", "data processing node", "data visualization node", etc. in the data analysis scenario.

[0037] S102: Selecting an intelligent agent template from the intelligent agent template list based on a user's selection operation, and placing the selected intelligent agent template on the canvas based on a user's dragging operation.

[0038] Among them, a click event listener is added to each entry in the agent template list. When the user clicks on an entry, the ID or index of the entry is recorded, indicating that the user has selected the agent template. Use the HTML5 drag and drop (Drag and Drop) API to add drag event listeners (such as dragstart, dragover, drop, etc.) to the selected agent template. When the user starts dragging, the dragstart event is triggered on the drag source (that is, the selected agent template), and the template information is stored in the drag data (DataTransfer object). Listen for the dragover event in the canvas area to allow the drag operation to enter the canvas. When the user releases the drag, a drop event is triggered on the canvas, and a new agent node is rendered at the corresponding position on the canvas according to the template information in the drag data.

[0039] S103, adding connectors to each agent template on the canvas and configuring attribute information to generate an agent node, the attribute information including: input parameter name and output parameter name.

[0040] Among them, SVG or Canvas API is used to draw connecting lines (connectors) between intelligent agent nodes to indicate the data flow relationship between them. The drawing of the connecting lines can be determined based on the user's operations (such as clicking and dragging) through the GUI (Graphical User Interface). An attribute configuration panel is provided for each intelligent agent node, allowing the user to enter the input parameter name and output parameter name. When the user enters information in the configuration panel, the terminal device stores this information in the attribute object of the node. Combined with the user-configured attribute information and the default configuration of the intelligent agent template, a complete intelligent agent node object is generated. These objects usually contain information such as node ID, type, location, attributes (input / output parameters), connection relationship, etc.

[0041] Furthermore, the process of configuring the attribute information includes:

[0042] The terminal device continuously monitors the user's interactive operations on the agent template. These operations may include but are not limited to: clicking on a template item in the agent template list. Drag the agent template from the list to the canvas and release it. Double-click the placed agent node on the canvas. When these preset trigger operations are detected, the terminal device believes that the user wants to configure or view the properties of the agent.

[0043] Based on the detected trigger operation, the terminal device displays a property configuration panel on the user interface. The property configuration panel may be a modal dialog box, a sidebar, or a floating window, and the specific form depends on the UI design of the application. The panel contains attribute fields related to the agent template, such as name, description, input parameters, output parameters, configuration options, etc. For some attributes, the panel may provide controls such as drop-down selection boxes, text boxes, check boxes, and sliders for users to enter or select values. Users enter or select attribute values ​​through the controls in the property configuration panel. The terminal device listens to user operations on these controls, such as input events of text boxes, change events of selection boxes, etc. When the user completes the input or selection of attribute values, the terminal device obtains these values ​​and stores them as attribute information. This attribute information may be associated with the agent node and stored in the application's memory or persistent storage (such as a database, configuration file, etc.).

[0044] During the process of user configuration of attributes, the terminal device may update the display of the agent node on the canvas in real time to reflect the change of attribute value (such as changing the node color, displaying a new attribute label, etc.). At the same time, the attribute configuration panel may also dynamically update its display content according to the user's selection or input (such as hiding or displaying specific attribute fields). When the user completes all necessary attribute configurations and closes the attribute configuration panel, the terminal device considers that the attribute configuration of the agent is complete. At this point, the terminal device can add the configured agent node to the workflow on the canvas and prepare for subsequent orchestration and connection operations.

[0045] In some embodiments of the present application, each agent node is configured with input ports and / or output ports. The number of input ports of the agent node strictly corresponds to the number of its input parameter names. This means that for each input parameter, there will be a dedicated input port for receiving data or instructions. The number of output ports of the agent node matches the number of its output parameter names. That is, each output parameter will have a corresponding output port for sending processed data or instructions.

[0046] During the transmission of data flow or instruction flow, the input port of the intelligent node will establish a one-to-one connection with the output port of its upper node (i.e., the node from which the data or instruction comes). This connection ensures that the data or instruction can be accurately transmitted from the upper node to the current node. Correspondingly, the output port of the intelligent node will establish a one-to-one connection with the input port of its lower node (i.e., the node from which the data or instruction is received). This connection ensures that the data or instruction processed by the current node can be smoothly passed to the next node for further processing.

[0047] Data or instructions flow unidirectionally between agent nodes following a user-defined process or workflow. They flow out from the output port of the upper node, enter the node through the input port of the current node for processing, and then flow out from the output port of the current node and enter the input port of the lower node.

[0048] During the agent orchestration process, users can flexibly add, delete or reconnect agent nodes and their ports according to actual needs. This dynamic adjustment capability enables users to build complex processes that meet specific business needs.

[0049] S104. Detect whether the number of agent nodes with the same function in the canvas is greater than or equal to two.

[0050] The terminal device traverses the list of all agent nodes on the canvas. For each node, check whether its type (or function) is the same as other nodes, usually by comparing the type attribute of the node (such as nodeType). Use a counter to record the number of nodes with the same function. If the counter value is greater than or equal to 2, proceed to the next step; otherwise, no merge operation is performed.

[0051] S105. If yes, merge the agent nodes into a fusion agent node according to the attribute information and connection relationship information of the agent nodes that meet the above conditions. The connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

[0052] Among them, for all intelligent agent nodes that meet the conditions, their attribute information (input / output parameters) and connection relationship information (identifiers of upper and lower nodes) are collected. Based on the collected information, a new fused intelligent agent node is created. This node should contain the input and output parameters of all merged nodes (parameter name conflicts may need to be handled) and inherit their connection relationships. All merged intelligent agent nodes are removed from the canvas, and new fused intelligent agent nodes are rendered in the same or appropriate position. All connection lines related to the fused node on the canvas are updated to ensure the correctness of data flow. The fused node list and connection relationship are stored in the storage of the terminal device or server so that the state can be restored when the user refreshes the page or reloads.

[0053] In some embodiments of the present application, the terminal device traverses the list of all agent nodes on the canvas, and determines which nodes meet the merging condition (i.e., have the same function and the number is greater than or equal to two) according to the type (or function) of the node. For nodes that meet the condition, the terminal device visually marks them on the canvas, such as using highlight colors, borders, or icons, etc., to highlight these nodes. After marking the nodes that meet the condition, the terminal device pops up a prompt window to notify the user that there are agent nodes that can be merged.

[0054] The prompt window may contain the following information: The number of nodes that can be merged. The potential benefits of the merge operation, such as simplifying the process and reducing resource consumption. A confirmation button that allows the user to perform the merge operation. A cancel button or close option that allows the user to ignore the merge prompt. Receiving user instructions for the prompt window: The terminal device listens for user interaction events on the prompt window, especially the click event of the confirmation button. When the user clicks the confirmation button, the terminal device is deemed to have received an instruction to perform a merge operation. If the user chooses to cancel or close the prompt window, the terminal device does not perform the merge operation and maintains the current canvas state. Obtaining the connection relationship information and attribute information of the intelligent agent node: After receiving the merge instruction, the terminal device traverses all intelligent agent nodes marked as mergeable. For each node, the terminal device obtains its connection relationship information (including the identifiers of the upper and lower nodes) and attribute information (such as the input / output parameter names).

[0055] Based on the acquired connection relationship information and attribute information, the terminal device creates a new fused agent node. The fused agent node should contain the input and output parameters of all merged nodes (parameter name conflicts may need to be handled) and inherit their connection relationships. The terminal device removes all merged agent nodes on the canvas and renders the new fused agent node in the same or appropriate position. Update all connection lines related to the fused node on the canvas to ensure the correctness of data flow. The terminal device stores the fused node list and connection relationship in the application's memory or persistent storage (such as a database, configuration file, etc.). Update the internal state of the application to reflect the canvas state after the merge operation. After the user confirms, the terminal device can merge the agent nodes that meet the conditions to generate a fused agent node and update the canvas and application status. This helps to simplify the user's agent orchestration process and improve efficiency and accuracy.

[0056] Furthermore, the fusion agent node can be expanded into multiple agents. The specific process includes:

[0057] The terminal device continuously monitors the user's interactive operations on the fusion agent node on the canvas. When the user performs a specific operation, such as double-clicking the fusion agent node, clicking the expand button on the node, or selecting the expand option in the menu, the terminal device assumes that the user wants to expand the fusion node.

[0058] Before performing the expansion operation, the terminal device may verify some conditions to ensure the legitimacy of the operation. These conditions may include: whether the fused node is in an editable state, whether the user has sufficient permissions, whether there is enough space on the canvas to place the expanded node, etc. The terminal device obtains the relevant information of the fused agent node from the application's memory or persistent storage, including its attribute information, connection relationship information, and the original merged agent template information. Based on the obtained information, the terminal device creates multiple new agent nodes on the canvas, which correspond to the original merged agent template. The newly created nodes should inherit the attribute information and connection relationship information of the fused node, and make appropriate adjustments as needed to ensure the correctness of data flow. The terminal device removes the fused agent node on the canvas and replaces it with these newly created nodes and their connecting lines. The terminal device updates the internal state of the application to reflect the canvas state after the expansion operation. This may include updating the node list, connection relationship list, attribute information storage, etc.

[0059] To ensure that the layout of nodes and connections on the canvas is clear and easy to understand, the terminal device may automatically adjust the positions of nodes and the paths of connections. This may involve using layout algorithms to optimize the distribution of nodes and the intersection of connections. The terminal device may notify the user that the expansion operation is complete by popping up a prompt window, displaying a status bar message, or updating UI elements.

[0060] For example, Figure 2 is a schematic diagram of the original agent flow chart in the canvas, and the terminal device is Figure 2 It is detected in the agent flow chart in that: the number of agents with the same function of three-level judgment is 3, the number of agents with the same function of processing a is 5, and the number of agents with the same function of processing b is 5. According to the connection association information and attribute information of the agents, the above three agents of three-level judgment are merged into one fusion agent, and the above five agents of processing a are merged into one fusion agent, and the above five agents of processing b are merged into one fusion agent. The agent flow chart after the merged processing is shown in Figure 3 shown.

[0061] Through the above steps, the terminal device can detect the user's expansion instruction, verify the conditions, obtain the information of the fused node, and expand the fused agent node into multiple original agent nodes on the canvas. This provides users with a flexible operation mode, allowing them to view and edit the internal details of the fused node when needed.

[0062] The embodiments of the present application specifically include the following beneficial effects:

[0063] By merging agent nodes with the same functions into fused agent nodes, this technical solution significantly simplifies the complexity of agent flowcharts. This not only makes the flowchart clearer and easier to understand, but also reduces unnecessary nodes and connecting lines, improving the readability and maintainability of the process.

[0064] Improve process management efficiency: Since agent nodes are merged, users do not need to deal with too many details when editing and managing agent processes. This reduces the complexity of operations and enables users to design and adjust processes more quickly and accurately.

[0065] Optimize resource utilization: Merging agent nodes can also reduce system resource usage. At runtime, the fused agent nodes can be processed as a whole, which reduces computational overhead and memory usage, and improves the overall performance of the system.

[0066] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0067] See also Figure 4 , which shows a schematic diagram of the structure of an intelligent agent arrangement device provided by an exemplary embodiment of the present application, hereinafter referred to as device 4. The device 4 can be implemented as all or part of the terminal device through software, hardware or a combination of both. The device 4 includes: a push unit 401, a drawing unit 402, a configuration unit 403, a detection unit 404, and a merging unit 405.

[0068] The push unit 401 is used to display an agent arrangement page; the agent arrangement page includes a canvas and an agent template list;

[0069] A drawing unit 402, configured to select an agent template from the agent template list based on a selection operation of a user, and place the selected agent template on a canvas based on a drag operation of a user;

[0070] A configuration unit 403 is used to generate an agent node after adding connectors to each agent template on the canvas and configuring attribute information, wherein the attribute information includes: an input parameter name and an output parameter name;

[0071] A detection unit 404, used to detect whether the number of agent nodes having the same function in the canvas is greater than or equal to two;

[0072] The merging unit 405 is used to merge the various intelligent agent nodes into a fused intelligent agent node according to the attribute information and connection relationship information of the various intelligent agent nodes that meet the above conditions, if yes, wherein the connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

[0073] In one or more possible embodiments, a corresponding list of intelligent agent templates is displayed on the canvas according to the application scenario selected by the user.

[0074] In one or more possible embodiments, the step of merging the agent nodes into a fused agent node according to the attribute information and connection relationship information of the agent nodes that meet the above conditions includes:

[0075] Mark each agent node that meets the above conditions and pop up a prompt window;

[0076] When receiving a shrinking instruction issued by the user to the prompt window, the connection relationship information and attribute information of each intelligent agent node are obtained, and each two intelligent agent nodes are merged into a fusion intelligent agent according to the obtained information.

[0077] In one or more possible embodiments, the configuration attribute information includes:

[0078] Detecting a preset trigger operation of a certain agent template by the user, displaying the attribute configuration panel;

[0079] Configure property information based on the user's output operations in the property configuration panel

[0080] In one or more possible embodiments, it further includes:

[0081] The expansion unit is used to expand the fused agent node into multiple agent nodes when detecting a user's expansion instruction for the fused agent node.

[0082] In one or more possible embodiments, detecting whether the number of agent nodes having the same function in the canvas is greater than or equal to two includes:

[0083] When receiving a save instruction from the user for the canvas, it is detected whether the number of agent nodes with the same function in the canvas is greater than or equal to two.

[0084] In one or more possible embodiments, each intelligent agent node is provided with an input port and / or an output port, the number of the intelligent agent node input ports is the same as the number of its input parameter names, and the number of the intelligent agent node output ports is the same as the number of its output parameter names; the input ports of the intelligent agent node are connected one-to-one with the output ports of its upper-level node, and the output ports of the intelligent agent are connected one-to-one with the input ports of its lower-level node.

[0085] It should be noted that the device 4 provided in the above embodiment only uses the division of the above functional modules as an example when executing the intelligent body arrangement method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above functions. In addition, the intelligent body arrangement device provided in the above embodiment and the intelligent body arrangement method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0086] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0087] The present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 1 The method steps of the embodiment shown in the figure can be found in the specific implementation process. Figure 2 The specific description of the illustrated embodiment will not be repeated here.

[0088] The present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the agent orchestration method described in the above embodiments.

[0089] See also Figure 5 , which is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Figure 5 As shown, the terminal device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0090] The communication bus 502 is used to realize the connection and communication between these components.

[0091] The user interface 503 may include a display screen (Display) and a camera (Camera), and the optional user interface 503 may also include a standard wired interface and a wireless interface.

[0092] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0093] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts within the entire terminal device 500, and executes various functions and processes data of the terminal device 500 by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0094] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. As Figure 5 As shown, the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program.

[0095] exist Figure 5 In the terminal device 500 shown in FIG. 1 , the user interface 503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 501 can be used to call the application stored in the memory 505 and specifically execute the following steps: Figure 1 The specific process can be referred to Figure 1 As shown, no further description is given here.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0097] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for arranging an intelligent agent, characterized in that: include: Display the agent arrangement page; The agent arrangement page includes a canvas and an agent template list; Selecting an intelligent agent template from the intelligent agent template list based on a selection operation of a user, and placing the selected intelligent agent template on the canvas based on a drag operation of a user; Adding connectors to each agent template on the canvas and configuring attribute information to generate an agent node, wherein the attribute information includes: input parameter name and output parameter name; Detecting whether the number of agent nodes having the same function in the canvas is greater than or equal to two; If yes, each agent node is merged into a fusion agent node according to the attribute information and connection relationship information of each agent node that meets the above conditions, and the connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

2. The method according to claim 1, characterized in that A corresponding list of intelligent agent templates is displayed on the canvas according to the application scenario selected by the user.

3. The method according to claim 1 or 2, characterized in that: The method of merging the agent nodes into a fusion agent node according to the attribute information and connection relationship information of the agent nodes that meet the above conditions includes: Mark each agent node that meets the above conditions and pop up a prompt window; When receiving a shrinking instruction issued by the user to the prompt window, the connection relationship information and attribute information of each intelligent agent node are obtained, and each two intelligent agent nodes are merged into a fusion intelligent agent according to the obtained information.

4. The method according to claim 3, characterized in that The configuration attribute information includes: Detecting the user's preset trigger operation on a certain agent template, displaying the attribute configuration panel; Configure the property information based on the user's output operation in the property configuration panel.

5. The method according to claim 1, 2 or 4, characterized in that: Also includes: When a user's expansion instruction for the fused agent node is detected, the fused agent node is expanded into multiple agent nodes.

6. The method according to claim 5, characterized in that The detecting whether the number of agent nodes having the same function in the canvas is greater than or equal to two comprises: When receiving a save instruction from the user for the canvas, it is detected whether the number of agent nodes with the same function in the canvas is greater than or equal to two.

7. The method according to claim 6, characterized in that Each intelligent agent node is provided with an input port and / or an output port. The number of the input ports of the intelligent agent node is the same as the number of its input parameter names, and the number of the output ports of the intelligent agent node is the same as the number of its output parameter names; the input ports of the intelligent agent node are connected one-to-one with the output ports of its upper-level node, and the output ports of the intelligent agent are connected one-to-one with the input ports of its lower-level node.

8. An agent arrangement device, characterized in that: include: A push unit, used to display the agent arrangement page; The agent arrangement page includes a canvas and an agent template list; A drawing unit, configured to select an intelligent agent template from the intelligent agent template list based on a selection operation of a user, and place the selected intelligent agent template on a canvas based on a drag operation of a user; A configuration unit, used to generate an agent node after adding connectors to each agent template on the canvas and configuring attribute information, wherein the attribute information includes: an input parameter name and an output parameter name; A detection unit, used to detect whether the number of agent nodes having the same function in the canvas is greater than or equal to two; A merging unit is used to merge the various intelligent agent nodes into a fused intelligent agent node according to the attribute information and connection relationship information of the various intelligent agent nodes that meet the above conditions, if yes, wherein the connection relationship information includes the node identifier of the upper node and the node identifier of the lower node.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

10. A terminal device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images