Document generation method and device, electronic equipment, storage medium and program

Abstract

The embodiment of the invention discloses a document generation method and device, electronic equipment, a storage medium and a program, and relates to the technical field of financial science and technology. The method comprises the following steps: acquiring key process element information of each key process element in a target development process; constructing a multi-tuple model of a development process document according to the key process element information; converting the information of the key process elements included in the multi-tuple model into a knowledge graph; and converting the knowledge graph into a development process document of the target development process. According to the technical scheme provided by the embodiment of the invention, the efficiency, flexibility and accuracy of development process document generation can be improved, and the readability and maintainability of the development process document can be improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of financial technology, and in particular, to a document generation method, device, electronic device, storage medium and program. Background Art

[0002] Currently, the creation of development process documents mainly relies on manual writing by developers or using automated tools to generate them. Manually writing documents is time-consuming, error-prone, and difficult to keep up to date. Although automated tools can quickly generate documents, they often output in a single format and lack readability. The above methods result in a lack of flexibility in development process documents, which are difficult to maintain and update. Summary of the invention

[0003] The embodiments of the present invention provide a document generation method, device, electronic device, storage medium and program, which can improve the efficiency, flexibility and accuracy of development process document generation, and improve the readability and maintainability of the development process document.

[0004] According to one aspect of the present invention, there is provided a document generation method, comprising:

[0005] Obtain key process element information of each key process element in the target development process;

[0006] Constructing a multi-tuple model of the development process document according to the key process element information;

[0007] Converting the information of the key process elements included in the multi-tuple model into a knowledge graph;

[0008] The knowledge graph is converted into a development process document of the target development process.

[0009] According to another aspect of the present invention, there is provided a document generating device, comprising:

[0010] An information acquisition module is used to obtain key process element information of each key process element in the target development process;

[0011] A model building module, used for building a multi-tuple model of the development process document according to the key process element information;

[0012] A knowledge graph generation module, used for converting the information of the key process elements included in the multi-tuple model into a knowledge graph;

[0013] A development process document generation module is used to convert the knowledge graph into a development process document of the target development process.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the document generation method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the document generation method described in any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the document generation method described in any embodiment of the present invention is implemented.

[0020] The embodiment of the present invention obtains key process element information of each key process element in the target development process, and constructs a multi-tuple model of the development process document based on the key process element information. Further, the information of the key process elements included in the multi-tuple model can be converted into a knowledge graph, so that the knowledge graph can be converted into a development process document of the target development process, thereby solving the problems of poor flexibility and difficulty in updating and maintaining the generated documents in the existing development process document generation methods, and can improve the efficiency, flexibility and accuracy of the development process document generation, and improve the readability and maintainability of the development process document.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a document generation method provided by Embodiment 1 of the present invention;

[0024] Figure 2is a flow chart of a document generation method provided by Embodiment 2 of the present invention;

[0025] Figure 3 is a schematic diagram of a document generation device provided in Embodiment 3 of the present invention;

[0026] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "target", "intermediate", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flowchart of a document generation method provided in the first embodiment of the present invention. This embodiment can be applied to the case where a knowledge graph is automatically generated based on process element information in a development process to generate a development process document through a knowledge graph. The method can be executed by a document generation providing device, which can be implemented by software and / or hardware and can generally be integrated in an electronic device. The electronic device can be a terminal device or a server device. As long as it can execute the document generation method, the embodiment of the present invention does not limit the specific device type of the electronic device. Accordingly, Figure 1 As shown, the method includes the following operations:

[0031] S110. Obtain key process element information of each key process element in the target development process.

[0032] Among them, the target development process may be a development process for which a development process document is to be generated. Exemplarily, the target development process may include, but is not limited to, a continuous integration development process and a development process of a system platform or a software, etc., and the embodiment of the present invention does not limit the specific development process included in the target development process. Among them, continuous integration may be a software development practice that allows developers to frequently integrate code into a shared repository and verify each integration through automated builds, so as to find and resolve errors in the integration process as early as possible. Key process element information may be key process information in the target development process. Exemplarily, taking the development scenario of continuous integration as an example, in the development process of continuous integration, the key process element information may include, but is not limited to, time description, involved servers, execution paths, and related scripts, etc., and the embodiment of the present invention does not limit the specific content included in the key process element information. It can be understood that the types of key process element information may also be different if the development scenarios applicable to the target development process are different.

[0033] In an embodiment of the present invention, in order to generate a development process document of a target development process, key process element information of each key process element in the target development process may be first obtained as basic data for constructing a multi-tuple model of the development process document.

[0034] S120: Construct a multi-tuple model of the development process document according to the key process element information.

[0035] The development process document may be a document describing the relevant development information and process information of the target development process. For example, the development process document may be a collection of files that record in detail the software development, product development or other project development process. The multi-tuple model may be an information model of key process elements representing the target development process.

[0036] Accordingly, after obtaining the key process element information of each key process element in the target development process, a multi-tuple model of the development process document can be constructed based on the key process element information. The multi-tuple model can be used to display the key process element information in the target development process in a structured manner. Exemplarily, the multi-tuple model may include but is not limited to execution actions, device objects, execution paths, and execution contents. An execution action may be a specific operation taken to achieve a certain step in the target development process. Optionally, the execution action may be described in the form of subject-predicate inversion, for example, the execution action may be described as code submission completion. The device object may be an object that processes the execution action in the target development process. Exemplarily, the device object may include but is not limited to servers, etc. The execution path may be a code path that may be passed through during the execution of the target development process. The execution content may be a specific task that needs to be completed in the target development process.

[0037] S130. Convert the information of the key process elements included in the multi-tuple model into a knowledge graph.

[0038] Among them, the knowledge graph can be a structured data representation method that presents knowledge in a graphical way, usually composed of nodes, edges and attributes.

[0039] Correspondingly, after constructing a multi-tuple model of the development process document based on the key process element information, the information of the key process elements included in the multi-tuple model can be used as nodes and edges in the knowledge graph, thereby generating a knowledge graph corresponding to the target development process.

[0040] Optionally, the information of key process elements included in the multi-tuple model may be converted into a UML (Unified Modeling Language) diagram, so that a development process document of the target development process may be generated according to the UML diagram.

[0041] S140. Convert the knowledge graph into a development process document of the target development process.

[0042] Accordingly, after converting the information of key process elements included in the multi-group model into a knowledge graph, available tools such as a knowledge graph generation tool or a customized document can be used to convert the knowledge graph into a development process document of a target development process with higher readability.

[0043] The embodiment of the present invention obtains key process element information of each key process element in the target development process, and constructs a multi-tuple model of the development process document based on the key process element information. Further, the information of the key process elements included in the multi-tuple model can be converted into a knowledge graph, so that the knowledge graph can be converted into a development process document of the target development process, thereby solving the problems of poor flexibility and difficulty in updating and maintaining the generated documents in the existing development process document generation methods, and can improve the efficiency, flexibility and accuracy of the development process document generation, and improve the readability and maintainability of the development process document.

[0044] Embodiment 2

[0045] Figure 2 is a flowchart of a document generation method provided by the second embodiment of the present invention. This embodiment is specific based on the above embodiment. In this embodiment, multiple specific optional implementation methods are provided for obtaining key process element information of each key process element in the target development process, converting the multi-tuple model into a knowledge graph, and converting the knowledge graph into a development process document. Figure 2 As shown, the method of this embodiment may include:

[0046] S210: Using a flowchart drawing tool, draw and generate a target development flowchart according to the development requirements of the target development process.

[0047] The development requirements of the target development process may be conditions and standards that need to be met in order to achieve the development goals. The target development flow chart may be a graphical tool that can be used to describe the various stages and steps in the target development process.

[0048] In an embodiment of the present invention, in order to obtain key process element information of each key process element in a target development process, firstly, a target development flowchart can be generated by using a flowchart drawing tool according to the development requirements of the target development process.

[0049] S220. Extract key process element information of each key process element in the target development flowchart through the target big model.

[0050] Among them, the target large model can be any available large language model, which can be used to extract key process element information of each key process element in the target development flow chart. The large language model is also called a large language model, which refers to a deep learning model that can process text sequences using a large amount of relevant data (such as text data, voice data, or text and picture data, etc.), which can generate natural language text or understand the meaning of language text. Such models usually have a parameter scale of more than billions. The large language model can handle a variety of natural language tasks, such as text classification, question and answer, and dialogue, and is widely used. The input of the large language model is data, such as text data, voice data, or text and picture data, etc. The large language model can obtain the corresponding word vector representation by encoding the input data, and further decodes the encoded word vector, thereby automatically completing the processing of the input data and obtaining the output data corresponding to the input data. Exemplarily, text can be input to the large language model, and the large language model processes and predicts the input text, and outputs the answer text corresponding to the text.

[0051] Accordingly, after the target development flow chart is generated by using a flow chart drawing tool according to the development requirements of the target development process, the key process element information of each key process element in the target development process can be extracted through the target large model. The target large model can automatically extract the key process element information from the target development process without manually writing the development process document, which reduces the workload of generating the development process document and improves the accuracy of the key process element information.

[0052] In an optional embodiment of the present invention, extracting key process element information of each key process element in the target development flowchart through the target big model may include: converting the flowchart content of the target development flowchart into JSON (JavaScript Object Notation) text data; performing JSON parsing and content extraction on the JSON text data to obtain intermediate extracted data; inputting the intermediate extracted data into the target big model to extract key process element information of each key process element in the target development flowchart through the target big model; wherein the key process elements of the target development flowchart include execution actions, device objects, execution paths and execution contents.

[0053] The JSON text data may be text data in JSON format, and the intermediate extracted data may be data obtained by performing JSON parsing and content extraction on the JSON text data.

[0054] In an embodiment of the present invention, before extracting the key process element information of each key process element in the target development process diagram through the target macro model, the flowchart content of the target development process diagram can be first converted into JSON text data, and the JSON text data can be parsed and the content extracted to obtain intermediate extracted data. Further, the intermediate extracted data can be input into the target macro model to automatically and intelligently extract the key process element information such as execution actions, device objects, execution paths, and execution contents in the target development process diagram through the target macro model.

[0055] In the above scheme, the flowchart content of the target development flowchart is converted into JSON text data to extract intermediate extraction data, realizing the preprocessing process of the model input data. Then, the intermediate extraction data is further extracted through the big model to extract key process element information such as execution action, device object, execution path and execution content, which can further improve the efficiency and accuracy of the model in extracting key process element information.

[0056] S230: construct a multi-tuple model of the development process document according to the key process element information.

[0057] S240: Convert the execution actions in the multi-tuple model into edges of the knowledge graph.

[0058] Among them, the edge of the knowledge graph can be a line segment connecting two nodes, representing the relationship or interaction between entities.

[0059] S250: Convert the device objects in the tuple model into nodes of the knowledge graph.

[0060] Among them, the nodes of the knowledge graph can be entities in the knowledge graph, and each node corresponds to a unique entity.

[0061] S260: Convert the execution path and execution content in the multi-tuple model into attributes of nodes in the knowledge graph.

[0062] Among them, the attributes of the nodes in the knowledge graph can describe the characteristics or status of the nodes in the knowledge graph.

[0063] Accordingly, after constructing a multi-tuple model of the development process document based on the key process element information, the execution actions in the multi-tuple model can be converted into edges of the knowledge graph, and the device objects in the multi-tuple model can be converted into nodes of the knowledge graph. Furthermore, the execution path and execution content in the multi-tuple model can be converted into attributes of the nodes in the knowledge graph. Thus, by converting the execution actions, device objects, execution paths, and execution contents included in the multi-tuple model into a knowledge graph, the key process element information in the target development process can be more structured, which is convenient for storage, query, and update. At the same time, through the visual knowledge graph, the entire target development process is intuitively displayed, which is convenient for developers to quickly understand.

[0064] S270. Generate a document overview of the development process document based on the nodes and edges in the knowledge graph.

[0065] The document overview of the development process document may be a high-level view of each stage and step in the target development process. Exemplarily, the document overview of the development process document may include a project introduction, key stages of project development, and main tasks of each stage, etc. The embodiment of the present invention does not limit the specific content of the document overview of the development process document.

[0066] Accordingly, after converting the information of key process elements included in the multi-tuple model into a knowledge graph, a document overview of the development process document can be generated based on the nodes and edges in the knowledge graph.

[0067] S280, traverse the nodes and edges in the knowledge graph to generate a detailed description of each process step in the development process document.

[0068] The detailed description of the process steps may be a comprehensive description of each stage, step and task involved in the target development. Exemplarily, the detailed description of the process steps includes device objects, execution paths and related scripts, etc. The embodiment of the present invention does not limit the specific content included in the detailed description of the process steps.

[0069] Correspondingly, after generating a document overview of the development process document based on the nodes and edges in the knowledge graph, the nodes and edges in the knowledge graph can be traversed to generate a detailed description of the process steps in the development process document including device objects, execution paths, and related scripts.

[0070] S290, converting the knowledge graph into a visual diagram of the development process document.

[0071] Among them, the visualization chart of the development process document can be a visualization chart generated according to the development process document, which can be used to display charts of various stages, steps and tasks in the target development process.

[0072] Accordingly, after generating a detailed description of each process step in the development process document, the knowledge graph can be converted into a visual diagram of the development process document. In the above scheme, by converting the knowledge graph into a development process document of the target development process and a visual diagram of the development process document, the entire development process can be clearly presented, making the complex target development process easier to understand.

[0073] In an optional embodiment of the present invention, after converting the knowledge graph into a development process document of the target development process, it may also include: optimizing the development process document of the target development process; formatting the optimized development process document according to a preset template to obtain a target development process document.

[0074] The preset template may be a template pre-designed and defined for the target development process. For example, the preset template may include grammar correction and paragraph reorganization, etc. The embodiment of the present invention does not limit the specific content included in the preset template.

[0075] In an embodiment of the present invention, after converting the knowledge graph into a development process document of a target development process, the development process document of the target development process can also be optimized. Furthermore, the development process document after document optimization can be formatted according to a preset template to obtain a target development process document. By optimizing the development process document to obtain a target development process document, the readability of the target development process document can be improved, thereby improving the work efficiency of developers.

[0076] The embodiment of the present invention generates a target development flowchart by using a flowchart drawing tool to draw according to the development requirements of the target development process, and extracts the key process element information of each key process element in the target development flowchart through the target large model. Further, a multi-tuple model of the development process document can be constructed according to the key process element information, and the execution actions in the multi-tuple model are converted into the edges of the knowledge graph, the device objects are converted into the nodes of the knowledge graph, and the execution paths and execution contents are converted into the attributes of the nodes in the knowledge graph. Thus, a document overview of the development process document can be generated according to the nodes and edges in the knowledge graph. Further, the nodes and edges in the knowledge graph can be traversed to generate a detailed description of each process step in the development process document, and the knowledge graph can be converted into a visual diagram of the development process document, so as to solve the problems of poor flexibility and difficulty in updating and maintaining the generated documents in the existing development process document generation method, and improve the efficiency, flexibility and accuracy of the development process document generation, and improve the readability and maintainability of the development process document.

[0077] Specific application scenarios

[0078] In order to more clearly describe the technical solution provided by the embodiment of the present invention, the embodiment of the present invention provides a document generation method suitable for a continuous integration scenario.

[0079] Step 1: Draw a continuous integration flow chart.

[0080] Use flowchart drawing tools to draw detailed continuous integration flow charts, including information such as each step, server, and execution path.

[0081] Step 2: Use the target large model to extract process information.

[0082] Input the drawn flowchart into the target large model and extract the key information from the flowchart. The specific steps are as follows:

[0083] a. Convert the flowchart content into JSON for storage.

[0084] b. Perform JSON parsing and content extraction: First, the data in JSON format can be read and converted into a dictionary or list object of the programming language Python. Further, the nodes in the flowchart data can be traversed, and the event, server, path and script information can be extracted for each node, and the extracted information can be organized into a list and returned. Then, a prompt word including the key information to be extracted can be constructed, and a text output can be generated according to the provided prompt word.

[0085] c. Input the extracted text information into the target large model, requiring the model to identify and extract key information in the process, including event descriptions, involved servers, execution paths, and related scripts, etc.: the output text information can be parsed according to the predefined four-tuple model, and the parsed information can be converted into a data structure and return structured optimization information.

[0086] Step 3: Construct a quadruple model.

[0087] Based on the information extracted from the target big model, the four-tuple model (execution action, server, execution path, execution content) proposed by the present invention is constructed. For example: ("code submission completed", "GitLab server", " / home / git / repositories", "post-receive-hook.sh"); ("build trigger", "jenkins server", " / var / lib / jenkins / jobs", "build.groovy").

[0088] Step 4: Generate knowledge graph.

[0089] Use graph database tools or knowledge graph visualization tools to convert the information in the quadruple model into a knowledge graph. The specific steps are as follows:

[0090] First, you can create a Graph object to establish a connection with the database, and you can use the Graph object to create nodes and edges in the knowledge graph. Traverse the list of quads, and for each quad, use "server" as a node in the knowledge graph to create or obtain a server node; use "execution action" as an edge in the knowledge graph to create an event relationship; use "execution path" and "execution content" as node attributes to set the attributes of the relationship. Furthermore, you can create remote nodes and relationships corresponding to the nodes and relationships in the local subgraph, and return the created graph object.

[0091] Step 5: Generate development process documentation based on knowledge graph

[0092] Use knowledge graph generation tools or custom document generation scripts to convert knowledge graphs into easy-to-read and easy-to-understand documentation manuals. The development process document generation process includes:

[0093] a. Generate process overview: Generate an overview of the entire continuous integration process based on the nodes and edges in the knowledge graph.

[0094] b. Generate detailed step description: traverse the nodes and edges in the knowledge graph, and convert the node and relationship information into a structured text description. Furthermore, you can construct a prompt word including the text description of the knowledge graph, and generate a development process document including detailed descriptions of each step based on the provided prompt words and preset templates, including the servers involved, execution paths and related scripts, etc., and return the generated document.

[0095] c. Generate visual diagrams: Convert the knowledge graph into visual diagrams to intuitively display the entire process.

[0096] Step 6: Document optimization and formatting.

[0097] Use large-model natural language processing technology to optimize the generated development process documents, including grammatical correction, paragraph reorganization, etc., and format them according to predefined templates to generate the final document manual.

[0098] The embodiment of the present invention generates a continuous integration flowchart by using a flowchart drawing tool to draw according to the development requirements of the target development process, and extracts the key process element information of each key process element in the continuous integration flowchart through the target large model. Further, a four-tuple model of the development process document can be constructed according to the key process element information, and the execution action in the four-tuple model is converted into the edge of the knowledge graph, the device object is converted into the node of the knowledge graph, and the execution path and execution content are converted into the attributes of the node in the knowledge graph. Thus, a document overview of the development process document can be generated according to the nodes and edges in the knowledge graph. Further, the nodes and edges in the knowledge graph can be traversed to generate a detailed description of each process step in the development process document, and the knowledge graph is converted into a visual diagram of the development process document, which solves the problem that the existing development process document generation method has poor flexibility and the generated document is difficult to update and maintain, and can improve the efficiency, flexibility and accuracy of the development process document generation, and improve the readability and maintainability of the development process document.

[0099] In the technical solution of the present disclosure, the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0100] It should be noted that, in the embodiment of the present invention, a corresponding operation entry may be provided for the user to choose to agree or reject the automated decision result; if the user chooses to reject, the expert decision process is entered.

[0101] It should be noted that any arrangement and combination of the technical features in the above embodiments also falls within the protection scope of the present invention.

[0102] Embodiment 3

[0103] Figure 3 is a schematic diagram of a document generation device provided by Embodiment 3 of the present invention, such as Figure 3 As shown, the device includes: an information acquisition module 310, a model building module 320, a knowledge graph generation module 330 and a development process document generation module 340, wherein:

[0104] The information acquisition module 310 is used to acquire key process element information of each key process element in the target development process.

[0105] The model building module 320 is used to build a multi-tuple model of the development process document according to the key process element information.

[0106] The knowledge graph generation module 330 is used to convert the information of the key process elements included in the multi-tuple model into a knowledge graph.

[0107] The development process document generation module 340 is used to convert the knowledge graph into a development process document of the target development process.

[0108] The embodiment of the present invention obtains key process element information of each key process element in the target development process, and constructs a multi-tuple model of the development process document based on the key process element information. Further, the information of the key process elements included in the multi-tuple model can be converted into a knowledge graph, so that the knowledge graph can be converted into a development process document of the target development process, thereby solving the problems of poor flexibility and difficulty in updating and maintaining the generated documents in the existing development process document generation methods, and can improve the efficiency, flexibility and accuracy of the development process document generation, and improve the readability and maintainability of the development process document.

[0109] Optionally, the information acquisition module 310 is specifically used to use a flowchart drawing tool to draw and generate a target development flowchart according to the development requirements of the target development process; and extract key process element information of each key process element in the target development flowchart through a target large model.

[0110] Optionally, the information acquisition module 310 is also used to convert the flowchart content of the target development flowchart into JSON text data; perform JSON parsing and content extraction on the JSON text data to obtain intermediate extracted data; input the intermediate extracted data into the target big model to extract key process element information of each key process element in the target development flowchart through the target big model; wherein the key process elements of the target development flowchart include execution actions, device objects, execution paths and execution contents.

[0111] Optionally, the knowledge graph generation module 330 is specifically used to convert the execution actions in the multi-tuple model into edges of the knowledge graph; convert the device objects in the multi-tuple model into nodes of the knowledge graph; and convert the execution path and execution content in the multi-tuple model into attributes of the nodes in the knowledge graph.

[0112] Optionally, a development process document generation module 340 is specifically used to generate a document overview of the development process document based on the nodes and edges in the knowledge graph; traverse the nodes and edges in the knowledge graph to generate a detailed description of each process step in the development process document; the detailed description of the process steps includes device objects, execution paths and related scripts; and convert the knowledge graph into a visual chart of the development process document.

[0113] Optionally, the above-mentioned device may also include a document optimization module, which is specifically used to optimize the development process document of the target development process; format the development process document after document optimization according to a preset template to obtain the target development process document.

[0114] The document generation device can execute the document generation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the document generation method provided by any embodiment of the present invention.

[0115] Since the document generation device described above is a device that can execute the document generation method in the embodiment of the present invention, based on the document generation method described in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the document generation device in the present embodiment and its various variations, so how the document generation device implements the document generation method in the embodiment of the present invention is not described in detail here. As long as a person skilled in the art implements the device used in the document generation method in the embodiment of the present invention, it belongs to the scope of protection of this application.

[0116] Embodiment 4

[0117] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0118] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0120] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a document generation method.

[0121] In some embodiments, the document generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the document generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the document generation method in any other appropriate manner (e.g., by means of firmware).

[0122] Optionally, the document generation method may include: obtaining key process element information of each key process element in the target development process; constructing a multi-tuple model of the development process document based on the key process element information; converting the information of the key process elements included in the multi-tuple model into a knowledge graph; and converting the knowledge graph into a development process document of the target development process.

[0123] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0125] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0127] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0128] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0129] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0130] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A document generation method, characterized in that: include: Obtain key process element information of each key process element in the target development process; Constructing a multi-tuple model of the development process document according to the key process element information; Converting the information of the key process elements included in the multi-tuple model into a knowledge graph; The knowledge graph is converted into a development process document of the target development process.

2. The method according to claim 1, characterized in that The key process element information of each key process element in the target development process is obtained, including: Using a flowchart drawing tool, draw and generate a target development flowchart according to the development requirements of the target development process; The key process element information of each key process element in the target development flowchart is extracted through the target big model.

3. The method according to claim 2, characterized in that The key process element information of each key process element in the target development flow chart is extracted through the target large model, including: Convert the flowchart content of the target development flowchart into JSON text data; Performing JSON parsing and content extraction on the JSON text data to obtain intermediate extracted data; Inputting the intermediate extracted data into the target macro model, so as to extract key process element information of each key process element in the target development process diagram through the target macro model; Among them, the key process elements of the target development flowchart include execution actions, device objects, execution paths and execution contents.

4. The method according to claim 3, characterized in that The converting the information of the key process elements included in the multi-tuple model into a knowledge graph includes: Converting the execution actions in the multi-tuple model into edges of the knowledge graph; Converting the device objects in the multi-tuple model into nodes of the knowledge graph; The execution path and execution content in the multi-tuple model are converted into attributes of nodes in the knowledge graph.

5. The method according to claim 1, characterized in that The step of converting the knowledge graph into a development process document of the target development process includes: Generate a document overview of the development process document based on the nodes and edges in the knowledge graph; Traversing the nodes and edges in the knowledge graph to generate a detailed description of each process step in the development process document; the detailed description of the process step includes a device object, an execution path, and related scripts; The knowledge graph is converted into a visual diagram of the development process document.

6. The method according to claim 4, characterized in that After converting the knowledge graph into a development process document of the target development process, the method further includes: Optimizing the development process document of the target development process; The optimized development process document is formatted according to the preset template to obtain the target development process document.

7. A document generation device, characterized in that: include: An information acquisition module is used to obtain key process element information of each key process element in the target development process; A model building module, used for building a multi-tuple model of the development process document according to the key process element information; A knowledge graph generation module, used for converting the information of the key process elements included in the multi-tuple model into a knowledge graph; A development process document generation module is used to convert the knowledge graph into a development process document of the target development process.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the document method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the document method described in any one of claims 1 to 6 when executed.

10. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the document method according to any one of claims 1 to 6 is implemented.

Images