Task model generation method and computer device

Abstract

The application discloses a task model generation method and a computer device. The method comprises the following steps: in response to receiving task description information of a target terminal, determining framework coding information of a task model based on the task description information, and sending the framework coding information to the target terminal; when the target terminal receives the framework coding information of the task model sent by the server, rendering a task model framework based on the framework coding information; and in response to a task content filling operation on the task model framework, generating a task model of a target task. The technical solution can reduce the professional requirements of the task model generation process and improve the generation efficiency of the task model.

Description

Technical Field

[0001] This application relates to the field of software development technology, and in particular to a method for generating a task model and a computer device. Background Technology

[0002] In related technologies, different components on the canvas can be combined by dragging and dropping related components and connecting them with lines to form a visual task model. However, the process of generating such a visual task model requires a high level of expertise and involves a large workload, which is not conducive to improving the efficiency of task model generation. Summary of the Invention

[0003] The purpose of this application is to provide a method and computer device for generating task models, so as to reduce the professional requirements of the task model generation process and improve the efficiency of task model generation.

[0004] In a first aspect, embodiments of this application provide a method for generating a task model, comprising:

[0005] In response to receiving task description information from the target terminal, the framework encoding information of the task model is determined based on the task description information;

[0006] The frame encoding information is sent to the target terminal, which then uses the frame encoding information to render the task model.

[0007] Using the above technical solution, task description information can be obtained from the target terminal. Then, based on the task description information, the framework encoding information of the task model is determined, and the framework encoding information is sent to the target terminal so that the target terminal can render the task model based on the framework encoding information. Therefore, the method of this application embodiment can intelligently generate a task model based on a task description model, without needing to execute the target task. This reduces the difficulty of generating the task model, improves the efficiency of task model generation, and allows even users with lower levels of expertise to generate task models using the method of this application.

[0008] In one possible implementation, the framework encoding information of the task model is determined based on the task description information, including:

[0009] The first encoded fragment is obtained from the encoded knowledge information in the knowledge base based on the task description information. The task description information is then input into the encoding inference model to obtain the second encoded fragment. Based on the first and second encoded fragments, the frame encoding information is determined. By cooperating with the encoding inference model and the knowledge base, frame encoding information is generated from multiple dimensions, ensuring the accuracy of the frame encoding information.

[0010] In one possible implementation, the method of this application embodiment further includes:

[0011] Upon receiving updated frame encoding information from the target terminal, the training data for the encoding inference model is determined based on the updated frame encoding information and the task description information; the encoding inference model is then optimized based on the training data. Optimizing the encoding inference model using updated frame encoding information from the target terminal makes the encoding inference model more closely resemble the actual scenario.

[0012] In one possible implementation, the method of this application embodiment further includes:

[0013] Upon receiving task model encoding information from the target terminal, the encoded knowledge information in the knowledge base is updated based on the task model encoding information and task description information. Updating the encoded knowledge information in the knowledge base using task model encoding information and task description information enriches the encoded knowledge information in the knowledge base and improves the accuracy of querying framework encoded information.

[0014] In one possible implementation, the encoded knowledge information includes a text description, encoded fragments, and a mapping relationship between the text description and the encoded fragments. The first encoded fragment is obtained from the encoded knowledge information in the knowledge base based on the task description information, including:

[0015] Based on the task description information, obtain the target text description that matches the task description information from the encoded knowledge information; based on the target text description and the mapping relationship, obtain the first encoded fragment from the encoded knowledge information. The first encoded fragment is the fragment description corresponding to the target text description.

[0016] In one possible implementation, the method of this application embodiment further includes:

[0017] Upon receiving supplementary task information from the target terminal, supplementary encoding information for the framework encoding information is determined based on the supplementary task information; the supplementary encoding information is then sent to the target terminal, which uses the supplementary encoding information to update the task model framework.

[0018] The process of updating the task model in the above way is essentially an incremental update of the task model framework, rather than a full update of the task model framework. This can reduce computational overhead and save resources.

[0019] In one possible implementation, the supplementary encoding information may include the encoded segment to be supplemented and the supplementation strategy for the encoded segment within the task model framework. For example, the encoded information to be supplemented can be added to the task model framework based on the supplementation strategy for the encoded segment within the task model framework.

[0020] In one possible implementation, the task model is visualized and rendered on a rendering canvas whose encoding information matches the frame encoding information in terms of format. This ensures that the target terminal can directly render the data onto the rendering canvas based on the frame encoding information.

[0021] Secondly, embodiments of this application also provide a method for generating a task model, comprising:

[0022] In response to input of task description information for the target task, send task description information to the server;

[0023] Upon receiving the task model's framework encoding information from the server, the task model framework is rendered based on the framework encoding information, and the framework encoding information is matched with the task description information.

[0024] In response to the task content population operation of the task model framework, a task model for the target task is generated.

[0025] When using the above technical solution, the task description information of the target task can be sent to the server when inputting the task description information. This allows the server to automatically generate the framework encoding information of the task model based on the task description information. Upon receiving the framework encoding information from the server, the task model framework can be rendered directly based on the framework encoding information. Then, by filling in the task content within the task model framework, the task model of the target task can be generated.

[0026] As can be seen, the method in this application embodiment can automatically generate a task model for a target task without executing the target task by inputting the task description information of the target task and filling in the task content of the task model framework. This can reduce the professionalism of generating the task model of the target task, reduce the difficulty of generating the task model, and improve the efficiency of generating the task model.

[0027] In one possible implementation, the task model framework is rendered based on the framework-encoded information, including:

[0028] Multiple coded segments and the relationships between them are obtained from the framework encoding information. These coded segments include graphical and non-graphical coded segments. Then, a target graphical template matching the graphical coded segment is obtained from a graphical template library. Based on the target graphical template, the non-graphical coded segments, and the relationships between the multiple coded segments, the task model framework is determined.

[0029] As can be seen, the method of this application embodiment can divide the framework encoding information into non-graphical encoding segments and graphical encoding segments according to the encoding object, and then directly determine the target graphic template that matches the graphical encoding segment through model mapping. Then, based on the target graphic template, the non-graphical encoding segment and the association between the multiple encoding segments, the task model framework is determined, thereby reducing the rendering pressure of the task model framework.

[0030] In one possible implementation, the framework encoding information is generated at least by an encoding inference model for the task description information, and the method further includes:

[0031] In response to the adjustment operation of the task model framework, the updated information of the framework encoding information is determined; the updated information of the framework encoding information is sent to the server, which is used to optimize the encoding inference model based on the updated information of the framework encoding information.

[0032] By adjusting the task model framework, the framework encoding information is indirectly modified, thereby obtaining updated framework encoding information. This ensures data consistency, eliminates the situation where the framework encoding information remains unchanged after the task model framework is modified, and prevents data gaps. Moreover, this modification method only requires adjusting the task model framework and does not require executing the generated task model to obtain indirectly modified framework encoding information, making it highly user-friendly.

[0033] Furthermore, sending updated frame encoding information to the server allows the server to optimize the encoding inference model based on the updated frame encoding information, thereby improving the encoding inference capability of the encoding inference model and making the inference results more consistent with reality.

[0034] In one possible implementation, the task model framework includes multiple task nodes, including a first task node and a second task node. The adjustment operation of the task model framework includes at least one of the following operations:

[0035] The operation of exchanging the positional relationship between the first task node and the second task node;

[0036] The deletion operation for the first task node;

[0037] And the operation of adding a third task node in the task model framework.

[0038] By adjusting the task model framework, the framework encoding information can be adjusted in reverse to obtain updated information about the framework encoding information, thus ensuring data consistency and user-friendly interaction.

[0039] In one possible implementation, the method of this application embodiment further includes: in response to an input operation on supplementary task information for the target task, sending supplementary task information to a server; and upon receiving supplementary encoding information from the server regarding the supplementary task information, updating the task model based on the supplementary encoding information. By sending the supplementary task information to the server through an input operation on the supplementary task information for the target task, the server automatically returns supplementary encoding information based on the supplementary task information, and then updates the task model using the supplementary encoding information. This incremental update method can reduce the computational pressure on the server and save resources.

[0040] In one possible implementation, the supplementary encoding information may include the encoded segment to be supplemented and the supplementation strategy for the encoded segment in the frame encoding information. The target terminal can then supplement the encoded segment to be supplemented into the frame encoding information according to the supplementation strategy.

[0041] In one possible implementation, the method of this application embodiment further includes: sending the encoded information of the task model to a server. In this way, the server can save the encoded information of the task model to a knowledge base to update the encoded knowledge information in the knowledge base. For example, the server can update the encoded knowledge information in the knowledge base based on the encoded information of the task model and the task description information.

[0042] Thirdly, embodiments of this application also provide a task model generation apparatus, comprising:

[0043] The processing module is used to determine the framework encoding information of the task model based on the task description information received from the target terminal in response to the task description information received.

[0044] A communication module is used to send the framework encoding information to a target terminal, and the target terminal is used to render a task model based on the framework encoding information.

[0045] Fourthly, embodiments of this application also provide a computer device, including:

[0046] Processor; and,

[0047] Memory for stored programs;

[0048] The program includes instructions that, when executed by a processor, cause the processor to perform the method according to the first aspect of the embodiments of this application or any possible implementation thereof.

[0049] Fifthly, embodiments of this application also provide a computer storage medium storing computer instructions that, when executed on an electronic device, cause the processor of the electronic device to perform the method described in accordance with the first aspect of the embodiments of this application or any possible implementation thereof.

[0050] In a sixth aspect, embodiments of this application also provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0051] The beneficial effects of the technical solutions of the third to sixth aspects of the embodiments of this application can be referred to the beneficial effects of the methods described in the first aspect or any possible implementation of the first aspect of the embodiments of this application, which will not be repeated here.

[0052] In a seventh aspect, embodiments of this application also provide a task model generation apparatus, comprising:

[0053] The communication module is used to send task description information to the server in response to an input operation that receives task description information of the target task;

[0054] The rendering module is used to render the task model framework based on the framework encoding information when it receives the framework encoding information of the task model sent by the server, and the framework encoding information is matched with the task description information.

[0055] The populate module is used to generate a task model for the target task in response to the task content population operation of the task model framework.

[0056] Eighthly, embodiments of this application also provide a computer device, including:

[0057] Processor; and,

[0058] Memory for stored programs;

[0059] The program includes instructions that, when executed by a processor, cause the processor to perform the method according to the second aspect of the embodiments of this application or any possible implementation thereof.

[0060] Ninthly, embodiments of this application also provide a computer storage medium storing computer instructions that, when executed on an electronic device, cause the processor of the electronic device to perform the method described according to the second aspect or any possible implementation thereof according to embodiments of this application.

[0061] In a tenth aspect, embodiments of this application also provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method described in the second aspect or any possible implementation thereof.

[0062] Eleventhly, embodiments of this application also provide a computer system, including: a terminal and a server, wherein the terminal and the server are communicatively connected.

[0063] The terminal is used to execute the method described in the second aspect or any possible implementation of the second aspect of the embodiments of this application, and the server is used to execute the method described in the first aspect or any possible implementation of the first aspect of the embodiments of this application.

[0064] The beneficial effects of the technical solutions of the seventh to eleventh aspects of the embodiments of this application can be referred to the beneficial effects of the methods described in the second aspect or any possible implementation of the second aspect of the embodiments of this application, which will not be repeated here. Attached Figure Description

[0065] Further details, features, and advantages of this application are claimed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0066] Figure 1 A schematic diagram of an example system architecture in which various methods described herein can be implemented according to embodiments of this application is shown;

[0067] Figure 2 A flowchart illustrating the task model generation method according to an embodiment of this application is shown;

[0068] Figure 3 A schematic diagram illustrating the update process of the task model according to an embodiment of this application is shown;

[0069] Figure 4 This document illustrates a schematic diagram of the optimization process for the coding inference model in an embodiment of this application.

[0070] Figure 5 A schematic diagram illustrating the generation principle of the task model in an embodiment of this application is shown;

[0071] Figure 6A A schematic diagram of the input window for the target task in an embodiment of this application is shown;

[0072] Figure 6B A schematic diagram of the task model framework of an embodiment of this application is shown;

[0073] Figure 7A A schematic diagram of the framework content of an HTTP node according to an embodiment of this application is shown;

[0074] Figure 7B A schematic diagram illustrating the framework of an SQL node according to an embodiment of this application is shown;

[0075] Figure 7C A supplementary schematic diagram of a PYTHON node according to an embodiment of this application is shown;

[0076] Figure 7DA supplementary schematic diagram of the offline task node in an embodiment of this application is shown;

[0077] Figure 7E A schematic diagram illustrating supplementary content of the data audit node in an embodiment of this application is shown;

[0078] Figure 8 A supplementary result diagram of the offline task node in an embodiment of this application is shown;

[0079] Figure 9 A schematic block diagram of a functional module of a task model generation apparatus according to an exemplary embodiment of this application is shown;

[0080] Figure 10 A schematic block diagram of another functional module of a task model generation apparatus according to an exemplary embodiment of this application is shown;

[0081] Figure 11 A schematic block diagram of a chip according to an exemplary embodiment of this application is shown;

[0082] Figure 12 A structural block diagram of an exemplary computer device that can be used to implement embodiments of this application is shown. Detailed Implementation

[0083] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0084] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0085] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this application are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0086] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0087] Before introducing the embodiments of this application, the relevant terms involved in the embodiments of this application are first explained as follows:

[0088] JavaScript Object Notation (JSON) Schema is a JSON-based format used to describe and validate the structure of JSON data. It provides a set of definitional languages ​​to specify rules for JSON formatting, including object properties, data types, relationships between data, and constraints, thereby enabling automated validation, annotation, and manipulation of JSON data.

[0089] JSON is a lightweight data-interchange format that is text-based, easy for humans to read and write, and also easy for machines to parse and generate. JSON is a data format used to represent structured data and is commonly used for data transmission in network communication.

[0090] The rendering engine is a key component in computer graphics, responsible for converting 3D models or scenes into realistic 2D images. Based on computer graphics and visual perception theory, it receives geometric data, texture data, lighting data, and other data from applications, and through a series of algorithms and computational steps, ultimately generates 2D images that conform to human visual perception.

[0091] Figure 1 A schematic diagram of an example system architecture is shown, illustrating embodiments of this application in which various methods described herein can be implemented. For example... Figure 1 As shown, the computer system 100 of this application embodiment may include a terminal 101 and a server 102. Optionally, the number of terminals 101 may be one or more.

[0092] like Figure 1 As shown, the terminal 101 can be a user device with display function, such as a mobile phone, tablet computer, wearable device, in-vehicle device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), and wearable device based on augmented reality (AR) and / or virtual reality (VR) technology.

[0093] For example, when the terminal is a wearable device, the wearable device can also be a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories.

[0094] Wearable devices are not merely hardware devices; they achieve powerful functionality through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large sizes, and the ability to perform complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses. They also include devices focused on a specific application function that require interaction with other devices like smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0095] like Figure 1 As shown, in this embodiment of the application, the terminal 101 can establish a communication connection with the server 102 through the application interface layer 103. For example, the application interface layer 103 can have application gateway and load balancing functions. The server 102 can include a data layer 1021, a database 1022, and a runtime environment 1023. The runtime environment 1023 of the server 102 can be implemented through a smart server and a cloud server to support task framework coding inference and other data processing functions. The data layer 1021 has data caching, file reading and writing, database reading and writing, transaction processing, and data synchronization functions. The database 1022 can be used to store task description information, task models, etc. from the terminal 101.

[0096] This application provides a method and computer device for generating a task model, which automatically generates the framework encoding information of the task model using task description information, and then generates the task model on the terminal using the framework encoding information, thereby reducing the professional requirements of the task model generation process and improving the generation efficiency of the task model.

[0097] The task model generation method of this application embodiment can be executed collaboratively by the target terminal and the server. Figure 2 A flowchart illustrating the task model generation method according to an embodiment of this application is shown. Figure 2 As shown, the method in this application embodiment may include steps 201 to 205.

[0098] In step 201, the target terminal responds to the input operation of the task description information of the target task by sending the task description information to the server.

[0099] When the target terminal detects an input operation on the task description information of the target task, it can obtain the task description information of the target task and send the task description information to the server through the application interface layer.

[0100] Optionally, the input operation for the task description information of the target task can be a text input operation, a voice input operation, or an image input operation. For example, a dialog box can be set in the display interface of the target terminal to input task description text, or the task description information can be sent in the form of a file.

[0101] In step 202, the server responds to receiving the task description information from the target terminal and determines the framework encoding information of the task model based on the task description information.

[0102] When the server receives the task description information, it can cache the task description information through data caching at the data layer. When caching the task description information, the server can generate framework encoding information using at least one method. For example, it can obtain a first encoding fragment from the encoded knowledge information in the knowledge base based on the task description information, input the task description information into the encoding inference model, and obtain a second encoding fragment. In this way, the framework encoding information can be determined based on the first and second encoding fragments.

[0103] As can be seen, frame-encoded fragments can be generated by combining a knowledge base and an encoding inference model to ensure the integrity of the frame-encoded information. For example, task nodes with strong generality in the task description information can be generated through the encoding inference model; while task nodes with high customization in the task description information can be obtained through knowledge base queries.

[0104] Optionally, the server can obtain the first encoded information from the encoded knowledge information in the knowledge base through the database read / write function of the data layer. At the same time, the server can read the task description information in the cache through the file read / write function of the data layer, and infer the second encoded information corresponding to the task description information through the encoding reasoning model.

[0105] In one example, the encoded knowledge information includes a text description, encoded fragments, and a mapping relationship between the text description and the encoded fragments. In this case, the first encoded fragment is obtained from the encoded knowledge information in the knowledge base based on the task description information, including:

[0106] Based on the task description information, a target text description matching the task description information is obtained from the encoded knowledge information; based on the target text description and the mapping relationship, a first encoded fragment is obtained from the encoded knowledge information, and the first encoded fragment is a fragment description corresponding to the target text description.

[0107] For example, encoded knowledge information includes multiple text descriptions and multiple encoded segments, with a mapping relationship between the multiple text descriptions and the same encoded segment. Here, the multiple text descriptions can be text descriptions with high semantic similarity.

[0108] In step 203, the server sends frame encoding information to the target terminal. Here, the server can send this information to the target terminal through the application interface layer.

[0109] In step 204, when the target terminal receives the frame encoding information of the task model from the server, it renders the task model frame based on the frame encoding information. Here, since the server generates the frame encoding information based on the task description information, the frame encoding information matches the task description information.

[0110] Optionally, when the target terminal receives the frame encoding information, it can display the frame encoding information in a dialog box on the target terminal's display interface. If there is a problem with the frame encoding information, it can be adjusted in the dialog box, and then the frame encoding information is rendered into a task model framework by the rendering engine.

[0111] According to the encoding type, the framework encoding information in this application embodiment can be divided into graphical encoding segments and non-graphical encoding segments. In order to reduce rendering pressure, multiple encoding segments and the relationship between multiple encoding segments can be obtained from the framework encoding information. The multiple encoding segments include graphical encoding segments and non-graphical encoding segments. Then, a target graphical template matching the graphical encoding segment is obtained from the graphical template library. Based on the target graphical template, the non-graphical encoding segment, and the relationship between multiple encoding segments, the task model framework is determined.

[0112] Optionally, the frame encoding information carries a type identifier (type). The type identifier (type) can be used to identify the graphics template library from the frame encoding information. Then, the target graphics template that matches the graphics encoding fragment can be obtained from the graphics template library. This method of obtaining the target graphics template in advance can effectively reduce the rendering pressure on the rendering canvas of the task model framework.

[0113] In one example, the frame encoding information can be input into the canvas's rendering engine to visualize and render the task model framework onto the rendering canvas. The format of the rendering canvas's encoding information matches the frame encoding information to ensure the adapter can correctly render onto the canvas through the rendering layer. For example, the rendering engine could be the Antv X6 engine, the GoJS engine, or the mxGraph engine.

[0114] In step 205, the target terminal responds to the task content population operation of the task model framework to generate a task model for the target task. Since the task model framework lacks detailed information related to the target task, task content can be populated into the task model framework on the rendering canvas to obtain the task model for the target task.

[0115] Optionally, after the task content is populated in the task model framework, the framework encoding information corresponding to the task model framework will also change and be transformed into task model encoding information. Therefore, the task model frameworks in this embodiment maintain data consistency with each other.

[0116] Optionally, the target terminal can send task model encoding information to the server. When the server receives the task model encoding information from the target terminal, it can update the encoding knowledge information in the knowledge base based on the task model encoding information and task description information. This can enrich the encoding knowledge information in the knowledge base and improve the accuracy of querying the framework encoding information.

[0117] In one example, the task description information can be segmented to obtain multiple text fragments. Correspondingly, different text fragments correspond to different encoded fragments in the task model's encoding information. Therefore, after obtaining multiple text fragments, the corresponding encoded fragment can be retrieved from the task model's encoding information for each text fragment. This allows us to obtain multiple text fragments, multiple encoded fragments, and the mapping relationship between these multiple text fragments and their encoded fragments.

[0118] As can be seen, in the method of this application embodiment, when the target terminal inputs the task description information of the target task, the task description information is sent to the server, so that the server can determine the framework encoding information of the task model based on the task description information, and then send the framework encoding information to the target terminal. In this way, the target terminal can directly render the task model framework based on the framework encoding information, and then generate the task model of the target task by filling in the task content of the task model framework. Therefore, the method of this application embodiment can intelligently generate the task model based on the task description model without executing the target task, thereby reducing the difficulty of generating the task model, improving the efficiency of generating the task model, and enabling users with less professional skills to use the method of this application to generate the task model, avoiding the errors and time consumption of manually writing the framework encoding information.

[0119] To conserve resources, incremental updates can be used to update the task model. Figure 3 A schematic diagram illustrating the task model update process according to an embodiment of this application is shown. Figure 3 As shown, the task model update method in this application embodiment may include steps 301 to 304.

[0120] In step 301, the target terminal, in response to the input operation of supplementary task information for the target task, sends supplementary task information to the server. Here, the supplementary task information can be entered in a dialog box on the target terminal's display interface and then transmitted to the server through the application interface layer.

[0121] Optionally, the supplementary task information is a supplement to the task description information of the target task. It can be a newly added task description based on the original task description information, or it can be a deletion or modification of some fragments in the original task description information.

[0122] In step 302, when the server receives the task supplement information from the target terminal, it determines the supplementary encoding information of the framework encoding information based on the task supplement information.

[0123] Based on the task supplementary information, it is possible to obtain the first coded supplementary fragment from the coded knowledge information in the knowledge base, or it is possible not to obtain the first coded supplementary fragment. Inputting the task supplementary information into the coding inference model may or may not yield a second coded supplementary fragment. Therefore, supplementary coded information corresponding to the task supplementary information can be obtained from both the knowledge base and the coding inference model.

[0124] In step 303, the server sends supplementary encoding information to the target terminal. Here, the server sends the supplementary encoding information through the application interface layer.

[0125] In step 304, upon receiving supplementary encoding information from the server regarding the task supplementary information, the task model framework is updated based on the supplementary encoding information. Here, the supplementary encoding information can be input into the rendering engine, allowing the rendering engine to render the supplementary content of the task model on the rendering canvas without clearing the task model on the rendering canvas.

[0126] Optionally, the supplementary encoding information may include the encoded segment to be supplemented and the supplementation strategy for the encoded segment in the task model framework. Therefore, the encoding information to be supplemented can be added to the task model framework based on the supplementation strategy for the encoded segment in the task model framework. This update method for the task model framework can be incremental rather than full, thus reducing the computational overhead of the server and saving server resources.

[0127] In one example, the supplementation strategy may include the location parameters of the coded segment to be supplemented within the task model framework and the supplementation method. For instance, the supplementation location information of the task model framework can be determined based on the location parameters of the coded segment to be supplemented within the task model framework, and then the coded segment to be supplemented is added to the task model framework based on the supplementation location information and the supplementation method of the coded segment to be supplemented within the task model framework.

[0128] When the supplementary information for a task is a new task description added on top of the original task description information, then during the process of rendering the supplementary content of the task model rendered on the canvas, model fragments can be added on top of the original task model.

[0129] In one example, when supplementary task information involves deleting parts of the original task description information, the process of supplementing the task model rendered on the rendering canvas could be a process of deleting a certain area from the original task model.

[0130] In one example, when the supplementary information for the task modifies a portion of the original task description information, the process of supplementing the task model rendered on the rendering canvas can be a process of modifying a certain area of ​​the original task model.

[0131] In one possible implementation, the coded reasoning model can also be optimized. Figure 4 A schematic diagram illustrating the optimization process of the encoded inference model in an embodiment of this application is shown. For example... Figure 4 As shown, the method for optimizing the coding reasoning model in this embodiment may include steps 401 to 404.

[0132] In step 401, the target terminal, in response to the adjustment operation of the task model framework, determines the update information of the framework encoding information.

[0133] Optionally, the task model framework of the rendering canvas can be visually adjusted, which means that the frame encoding information corresponding to the task model framework can be modified in reverse. This can ensure the data consistency between the task model framework and the frame encoding information on the rendering page.

[0134] When modifying the frame encoding information, the task model frame of the rendering canvas is visually adjusted without requiring much professional knowledge to edit the frame encoding information. Therefore, the method of this application embodiment has good interactivity and can easily modify the frame encoding information to obtain updated frame encoding information.

[0135] In step 402, the target terminal sends updated framework encoding information to the server. Here, the target terminal can transmit updated mining machine encoding information to the server via the application interface layer.

[0136] In step 403, when the server receives the update information of the frame encoding information from the target terminal, it determines the training data of the encoding inference model based on the update information of the frame encoding information and the task description information.

[0137] Considering that the frame encoding information generated by the encoding inference model based on the task description information may be inaccurate, the server can collect the updated frame encoding information from the target terminal, use the updated frame encoding information as reference information, and combine it with the task description information to determine the training data for the encoding inference model.

[0138] In step 404, the server optimizes the encoding inference model based on the training data of the encoding inference model. Optionally, the updated frame encoding information includes the modified frame encoding information. Using the modified frame encoding information as a reference value and the task description information as the input information of the encoding inference model, the encoding inference model can be retrained, thereby optimizing the encoding inference model and making it more closely resemble the real-world scenario.

[0139] Optionally, the task model framework of this application embodiment includes multiple task nodes, including a first task node and a second task node. The update information of the framework's encoded information includes at least one of the following operations.

[0140] The first operation involves swapping the positions of the first and second task nodes. For example, the positions of the first and second task nodes can be swapped by dragging on the rendering canvas.

[0141] The second operation is the deletion of the first task node. For example, the first task node can be deleted from the rendering canvas using the delete function.

[0142] The third operation involves adding a third task node to the task model framework. For example, a third task node can be added to the rendering canvas.

[0143] To clearly explain the process of generating the task model in the embodiments of this application, Figure 5 A schematic diagram illustrating the generation principle of the task model in an embodiment of this application is shown. For example... Figure 5 As shown, the user inputs a task description of the target task into the terminal. This task description can be in natural language or in document form. The terminal transmits the task description to the interface interaction layer 501; the interface interaction layer 501 retrieves a JSON-encoded fragment from the knowledge base 502 via an API call.

[0144] like Figure 5 As shown, the interface interaction layer 501 outputs task description information to the encoding inference engine 503. The encoding inference engine 503 can parse the task encoding information into a structured JSON framework based on a natural language processing (NLP) model. The structured JSON framework includes node encoding, the relationship encoding between nodes, and node encoding attributes.

[0145] like Figure 5As shown, JSON encoded fragments and structured JSON frames can constitute JSON frame encoded information. This JSON frame encoded information can be returned to the X6 adapter 504 through the interface interaction layer 501. The X6 adapter 504 identifies graphical and non-graphical encoded fragments from the JSON frame encoded information through the node attribute 'type' in the JSON frame encoded information. Then, it obtains multiple target graphic templates corresponding to the graphical encoded fragments from the graphic template library 505 through rule mapping. The non-graphical encoded fragments can reflect the relationship between different node encoded attributes. Therefore, the X6 adapter 504 can perform X6 node connections or connection configurations based on the non-graphical encoded fragments, so that the X6 adapter 504 renders multiple target graphic templates (each target graphic template is equivalent to a task node of a task template) and the connections between different target graphic templates in the AntV X6 rendering layer 506, thereby obtaining the task model framework. The task model framework is then rendered on the rendering canvas, and the missing content in the task model framework is filled in to obtain the task model of the target task.

[0146] It can be seen that, as Figure 5 As shown, non-technical personnel only need to input task description information to automatically generate JSON framework encoding information through the encoding reasoning model and knowledge base 502. Then, with the assistance of X6 adapter 504, the task model with high business complexity is generated by combining the graphics template library 505 and AntV X6 rendering layer 506. Therefore, the task model generation method of this application embodiment has a low threshold for use and can also avoid the time consumption and possible errors caused by manually writing framework encoding information.

[0147] Optional, such as Figure 5 As shown, the graphic template library 505 can adapt to any industry symbol library (such as business process modeling and symbol library, unified modeling language library, or information technology industry symbol library), including multiple node attributes and multiple graphic templates, and there is a one-to-one correspondence between the multiple node attributes and multiple graphic templates. The X6 adapter 504 can map the graphical encoding fragment to the pre-registered target graphic template (such as rectangle, cylinder, or Vue component) of AntV X6 through the node attribute type of the graphical encoding fragment using a rule-based mapping method. At the same time, custom graphic templates can also be stored in the graphic template library 505, and a correspondence between the graphic template and the type of graphic module can be established, thus making the graphic template library 505 highly extensible.

[0148] Optional, such as Figure 5As shown, in response to user drag events, the X6 adapter 504 can automatically update the JSON framework encoding information in reverse to obtain the updated JSON. The X6 adapter 504 can then transmit the updated JSON (through the interface interaction layer 501) to the encoding inference engine 503 to optimize the encoding inference engine 503, thereby maintaining the consistency between the JSON framework encoding information and the visual task model framework, eliminating data gaps caused by user modifications. This method of modifying JSON framework encoding information has good interactivity, does not require high professional knowledge to implement, and improves the adjustment speed of the task model by 60%.

[0149] Optionally, the X6 adapter can generate node relationships based on non-graphical coded fragments, and then call X6 layout algorithms (such as directed acyclic graph algorithms or force-guided algorithms) to generate a task model. In this task model, relationships between different task nodes can be connected by arrows representing those relationships. This avoids the problems of overlapping task nodes and intersecting lines, and improves the clarity of complex relationship visualization by more than 40%, resulting in high readability.

[0150] The following describes the process of generating the task model using the Enterprise Resource Planning (ERP) database migration as an example.

[0151] Figure 6A A schematic diagram of the input window for the target task in an embodiment of this application is shown. Figure 6A As shown, the display page 601 is divided into left and right sides. The left side is the custom node list 601A, and the right side is the rendering canvas 601B. The rendering canvas 601B can be used to display the task model of the target task.

[0152] like Figure 6A As shown, the custom node list 601A includes general nodes, logical nodes, and migration nodes. General nodes include HTTP nodes, SQL nodes, and PYTHON nodes; logical nodes include SWITCH nodes, CONDITION nodes, condition, sub_process, and dependent nodes; migration nodes include offline tasks and data audit nodes (to verify data consistency after the task is completed).

[0153] When entering the task description information for the target task, such as Figure 6AAs shown, you can click "Create Control" 602 on the terminal's display page 601 to bring up an AI interaction pop-up 603. This AI interaction pop-up 603 offers two interaction modes: dialogue and file. If you choose the dialogue interaction mode, you can fill in the task description information of the target task in the dialogue information field; if you choose the file interaction mode, you can select the target file through the pop-up file box, which contains the task description information of the target task; by clicking the submit control, you can submit the task description information of the target task to the server.

[0154] Optionally, the task description information of the target task may include: making a data request via Hypertext Transfer Protocol (HTTP), then packaging the data with Structured Query Language (SQL), then performing secondary optimization on the SQL-packaged data using a Python script, synchronizing the offline task based on the results of the secondary optimization, and finally performing data auditing.

[0155] The server can refer to the methods described above to generate JSON frame-encoded information and return it to the terminal, and in such cases... Figure 6A The rendering canvas 601B shown is rendered on the task model framework corresponding to the JSON frame encoded information. Figure 6B A schematic diagram of the task model framework according to an embodiment of this application is shown. Figure 6B As shown, the task template framework can include five task nodes: HTTP node 605A, SQL node 605B, Python node 605C, offline task node 605D, and data audit node 605E. These five task nodes are connected by arrows, the direction of which indicates the execution order of the different task nodes. Furthermore, clicking on any task node will bring up its framework content, allowing users to fill in any additional information within that framework.

[0156] In one example, you can click sequentially. Figure 6B The HTTP node 605A, SQL node 605B, PHYTHON node 605C, offline task node 605D, and data audit node 605E can be displayed sequentially. Figure 7A The supplementary interface 701 for the HTTP node shown. Figure 7B The supplementary interface 702 for the SQL node shown. Figure 7C The supplementary interface 703 for the PHYTHON node shown. Figure 7D The supplementary interface 704 for the offline task node shown, and Figure 7EThe supplementary interface 705 for the data audit node is shown. Taking the supplementary results of the offline task node as an example, the supplementary results 800 for the offline task node are as follows: Figure 8 As shown.

[0157] Optional, after supplementing Figure 6B After accessing the task model framework, you can obtain the task model. Clicking... Figure 6B After the save control returns to 604, the terminal can send the task model's encoding information to the server, so that the server can save the task model's encoding information to the knowledge base to update the encoded knowledge information in the knowledge base.

[0158] As can be seen, in the method of this application embodiment, the user only needs to input the task description information of the target task to complete most of the work of the task model, thereby greatly reducing the workload of generating the task model and shortening the time required to fill in the nodes that need to be arranged. Moreover, for the same type of task template, the same task model framework can be used, thereby reducing the secondary construction of the task model.

[0159] Optionally, the JSON framework encoding information returned by the server in this application embodiment can be adapted not only to the AntVX6 engine, but also to other engine configurations such as the GoJS engine or the mxGraph engine. This can solve the compatibility problem of multiple visualization tools for enterprises and achieve the effect of generating once and rendering on multiple platforms.

[0160] Optionally, the method in this application embodiment can also be combined with the Conflict-Free Replicated Data Types (CRDT) algorithm to realize multi-user synchronous editing and rendering of the canvas, and can also coordinate conflict values ​​in real time to support remote team collaborative modeling, such as online whiteboard review meetings.

[0161] The above mainly describes the solutions provided by the embodiments of this application from the perspectives of the terminal and the server. It is understood that, in order to achieve the above functions, the terminal and server include corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments applied herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0162] This application embodiment can divide the terminal and server into functional units according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0163] By dividing the functions into modules corresponding to each function, an exemplary embodiment of this application provides a task model generation apparatus. This apparatus can be a server or a chip applied to a server. Figure 9 A schematic block diagram of a functional module of a task model generation apparatus according to an exemplary embodiment of this application is shown. Figure 9 As shown, the task model generation device 900 includes:

[0164] Processing module 901 is used to determine the framework encoding information of the task model based on the task description information received from the target terminal in response to receiving the task description information.

[0165] The communication module 902 is used to send the framework encoding information to the target terminal, and the target terminal is used to render the task model based on the framework encoding information.

[0166] In one possible implementation, a determining module is configured to obtain a first encoded fragment from encoded knowledge information in a knowledge base based on task description information; input the task description information into an encoded reasoning model to obtain a second encoded fragment; and determine the framework encoded information based on the first and second encoded fragments.

[0167] In one possible implementation, the processing module 901 is further configured to, upon receiving update information on the frame encoding information from the target terminal, determine the training data for the encoding inference model based on the update information on the frame encoding information and the task description information, and optimize the encoding inference model based on the training data.

[0168] In one possible implementation, the processing module 901 is further configured to update the encoded knowledge information in the knowledge base based on the task model encoding information and task description information when receiving the task model encoding information from the target terminal.

[0169] In one possible implementation, the encoded knowledge information includes text descriptions, encoded fragments, and the mapping relationship between the text descriptions and encoded fragments.

[0170] The processing module 901 is used to obtain a target text description that matches the task description information from the encoded knowledge information based on the task description information; and to obtain a first encoded fragment from the encoded knowledge information based on the target text description and the mapping relationship, wherein the first encoded fragment is a fragment description corresponding to the target text description.

[0171] In one possible implementation, the processing module 901 is further configured to determine supplementary encoding information of the framework encoding information based on the task supplementary information received from the target terminal.

[0172] The communication module 902 is also used to send supplementary encoding information to the target terminal, which is used to update the task model framework of the task model based on the supplementary encoding information.

[0173] By dividing the functions into modules corresponding to each function, an exemplary embodiment of this application provides a task model generation apparatus. This apparatus can be a terminal or a chip applied to a terminal. Figure 10 A schematic block diagram of another functional module of a task model generation apparatus according to an exemplary embodiment of this application is shown. Figure 10 As shown, the task model generation device 1000 includes:

[0174] Communication module 1001 is used to send task description information to the server in response to input operation of task description information of target task;

[0175] Rendering module 1002 is used to render the task model framework based on the framework encoding information when it receives the framework encoding information of the task model sent by the server. The framework encoding information is matched with the task description information.

[0176] The population module 1003 is used to generate a task model for the target task in response to the task content population operation of the task model framework.

[0177] In one possible implementation, the rendering module 1002 is used to obtain multiple coded segments and the relationships between the multiple coded segments from the framework encoding information. The multiple coded segments include graphical coded segments and non-graphical coded segments; obtain a target graphical template that matches the graphical coded segments from the graphical template library; and determine the task model framework based on the target graphical template, the non-graphical coded segments, and the relationships between the multiple coded segments.

[0178] In one possible implementation, the frame-encoded information is generated at least by the encoded inference model in response to the task description information.

[0179] The rendering module 1002 is also used to determine the update information of the framework encoding information in response to the adjustment operation of the task model framework;

[0180] The communication module 1001 is also used to send update information of the frame encoding information to the server, and the server uses the update information of the frame encoding information to optimize the encoding inference model.

[0181] In one possible implementation, the communication module 1001 is further configured to send supplementary task information to the server in response to an input operation for supplementary task information of the target task.

[0182] The rendering module 1002 is also used to update the task model framework based on the supplementary encoding information received from the server for supplementary task information.

[0183] Figure 11 A schematic block diagram of a chip according to an exemplary embodiment of this application is shown. Figure 11 As shown, the chip 1100 includes one or more processors 1101 and a communication interface 1102.

[0184] In one possible implementation, the communication interface 1102 can support the terminal to perform the data transmission and reception steps in the above method, and the processor 1101 can support the terminal to perform the data processing steps in the above method.

[0185] In another possible implementation, the communication interface 1102 can support the server to perform the data sending and receiving steps in the above method, and the processor 1101 can support the server to perform the data processing steps in the above method.

[0186] Optional, such as Figure 11 As shown, the chip 1100 also includes a memory 1103, which may include read-only memory and random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include non-volatile random access memory (NVRAM).

[0187] In some implementations, such as Figure 11As shown, processor 1101 executes corresponding operations by calling operation instructions stored in memory (which may be stored in the operating system). Processor 1101 controls the processing operations of any terminal device; processor can also be called a central processing unit (CPU). Memory 1103 may include read-only memory and random access memory, and provides instructions and data to processor 1101. A portion of memory 1103 may also include NVRAM. For example, in applications, memory, communication interfaces, and other components are coupled together via a bus system, which may include, in addition to a data bus, a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 11 The general designated all buses as Bus System 1104.

[0188] The methods disclosed in the embodiments of this application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams of the application in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods applied in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0189] An exemplary embodiment of this application also provides a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the computer device to perform a method according to an embodiment of this application.

[0190] An exemplary embodiment of this application also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0191] An exemplary embodiment of this application also provides a computer program product, including a computer program, wherein, when executed by a computer's processor, the computer program is used to cause the computer to perform a method according to an embodiment of this application.

[0192] refer to Figure 12 The following is a structural block diagram of the computer device 1200 that can be used as described in this application, which is an example of a hardware device that can be applied to various aspects of this application. The term "computer device" is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The computer device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0193] like Figure 12 As shown, the computer device 1200 includes a computing unit 1201, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1202 or a computer program loaded from a storage unit 1208 into a random access memory (RAM) 1203. The RAM 1203 may also store various programs and data required for the operation of the computer device 1200. The computing unit 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0194] like Figure 12As shown, multiple components in computer device 1200 are connected to I / O interface 1205, including: input unit 1206, output unit 1207, storage unit 1208, and communication unit 1209. Input unit 1206 can be any type of device capable of inputting information to computer device 1200. Input unit 1206 can receive input numerical or character information and generate key signal inputs related to user settings and / or function control of the computer device. Output unit 1207 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1208 may include, but is not limited to, hard disks and optical disks. Communication unit 1209 allows computer device 1200 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0195] like Figure 12 As shown, computing unit 1201 can be various general-purpose and / or dedicated processing components with processing and computing capabilities. Some examples of computing unit 1201 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 1201 performs the various methods and processes described above. For example, in some embodiments, the methods of the embodiments of this application can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 1208. In some embodiments, part or all of the computer program can be loaded and / or installed on computer device 1200 via ROM 1202 and / or communication unit 1209. In some embodiments, computing unit 1201 can be configured to perform the methods of the embodiments of this application by any other suitable means (e.g., by means of firmware).

[0196] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0197] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0198] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0199] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0200] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0201] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); or it can be a semiconductor medium, such as a solid-state drive (SSD).

[0202] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A method for generating a task model, characterized in that, include: In response to receiving task description information from the target terminal, the framework encoding information of the task model is determined based on the task description information; The method involves sending the frame encoding information to the target terminal, which renders a task model framework based on the frame encoding information. In response to a user's operation of filling task content into the task model framework on a canvas, a task model for the target task is generated. The task model framework includes multiple task nodes, and the filling operation includes filling in the required supplementary content within the framework content of any task node. The method further includes: Upon receiving the task supplementary information from the target terminal, supplementary encoding information for the framework encoding information is determined based on the task supplementary information; wherein, the task supplementary information is used to represent the content used to fill in the missing content in the task model framework on the canvas; The supplementary encoding information is sent to the target terminal, which updates the task model framework based on the supplementary encoding information to obtain the task model of the target task; the step of determining the framework encoding information of the task model based on the task description information includes: The first encoded fragment is obtained from the encoded knowledge information in the knowledge base based on the task description information; The task description information is input into the coding inference model to obtain the second coding segment; The frame encoding information is determined based on the first and second encoded segments.

2. The method according to claim 1, characterized in that, The method further includes: Upon receiving update information from the target terminal regarding the framework encoding information, the training data for the encoding inference model is determined based on the update information of the framework encoding information and the task description information. The encoding inference model is optimized based on the training data of the encoding inference model.

3. The method according to claim 1, characterized in that, The method further includes: Upon receiving the task model encoding information from the target terminal, the encoded knowledge information in the knowledge base is updated based on the task model encoding information and the task description information.

4. The method according to claim 1, characterized in that, The encoded knowledge information includes text descriptions, encoded fragments, and the mapping relationship between text descriptions and encoded fragments. The step of obtaining the first encoded fragment from the encoded knowledge information in the knowledge base based on the task description information includes: Based on the task description information, obtain the target text description that matches the task description information from the encoded knowledge information; Based on the target text description and the mapping relationship, a first encoded fragment is obtained from the encoded knowledge information, wherein the first encoded fragment is a fragment description corresponding to the target text description.

5. A method for generating a task model, characterized in that, include: In response to an input operation of task description information for a target task, the task description information is sent to a server, the server being used to execute the method described in any one of claims 1 to 4; Upon receiving the task model's framework encoding information sent by the server, the task model framework is rendered based on the framework encoding information, and the framework encoding information is matched with the task description information. In response to the task content population operation of the task model framework, a task model for the target task is generated; In response to the input operation of supplementary task information for the target task, the supplementary task information is sent to the server; Upon receiving supplementary encoding information from the server regarding task supplementary information, the task model framework is updated based on the supplementary encoding information.

6. The method according to claim 5, characterized in that, The rendering task model framework based on the encoded information of the framework includes: Multiple coded segments and the relationship between the multiple coded segments are obtained from the frame encoding information, wherein the multiple coded segments include graphical coded segments and non-graphical coded segments; Obtain a target graphic template that matches the graphic encoded fragment from the graphic template library; The task model framework is determined based on the target graphical template, the non-graphical coded segments, and the relationships between the multiple coded segments.

7. The method according to claim 5, characterized in that, The framework encoding information is generated at least by an encoding inference model for the task description information, and the method further includes: In response to the adjustment operation of the task model framework, the update information of the framework encoding information is determined; The update information of the framework encoding information is sent to the server, and the server is used to optimize the encoding inference model based on the update information of the framework encoding information.

8. A computer device, characterized in that, include: processor; as well as, Memory for stored programs; The program includes instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 4 or 5 to 7.

Images