A document analysis method, device, apparatus and storage medium

Abstract

The application belongs to the technical field of artificial intelligence, and relates to a document analysis method, device, equipment and storage medium. Information data contained in a to-be-analyzed document is extracted; entity relationship representation content and business demand representation content are extracted; a target general business entity relationship knowledge graph is screened out; adjustment and update are performed to obtain an updated graph; a demand development mapping document designed in advance for the to-be-analyzed document is acquired; business function nodes, business processing dependency relationships and business processing processes are determined; business logic conflicts are detected according to the updated graph to obtain a detection result; a structured document analysis report is generated and fed back to a target receiving end. By using artificial intelligence processing and a knowledge graph, an actual development task can be efficiently determined, and the application in a financial business or medical health care business development scene with relatively complicated business logic processing nodes can greatly reduce the amount of artificial demand analysis processing and improve the actual development task determination efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and is applied to scenarios involving the generation, detection, and updating of requirement development mapping documents based on business requirement information provided by customers. It relates to a document analysis method, apparatus, device, and storage medium. Background Technology

[0002] In system development, requirements analysis is a crucial step in analyzing actual development tasks before project development. Traditional requirements analysis methods mainly rely on manual reading and understanding of requirements documents, which is inefficient, error-prone, and struggles to handle the multi-dimensional relationships between complex system requirements. This is especially true in financial or healthcare business development scenarios with complex business logic processing nodes. The inherent complexity of these business logic processing nodes leads to higher manpower consumption for requirements analysis in these scenarios, resulting in reduced development efficiency.

[0003] Therefore, existing technologies, when performing requirement segmentation analysis, still rely on human experience, which can easily lead to analytical errors and reduced development efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a document analysis method, apparatus, device, and storage medium to solve the problem that existing technologies, when performing requirement classification analysis, still rely on human experience, which can easily lead to analysis errors and reduce development efficiency.

[0005] Firstly, embodiments of this application provide a document analysis method, which employs the following technical solution: A document analysis method includes the following steps: Extract information data contained in the document to be analyzed; The information data is input into a preset entity relationship extraction component to extract the entity relationship representation content and business requirement representation content contained in the information data. Filter out the pre-built target general business entity relationship knowledge graph; Based on the entity relationship representation content, the target general business entity relationship knowledge graph is adjusted and updated to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; Obtain the requirements development mapping document pre-designed for the document to be analyzed; The business entities and execution steps of the requirement development mapping document are identified to determine the business function nodes, business processing dependencies and business processing flow contained in the requirement development mapping document; Based on the business entity relationship knowledge graph corresponding to the document to be analyzed, detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, and obtain the detection results. A structured document analysis report is generated based on the detection results and fed back to the target receiving end.

[0006] Secondly, embodiments of this application also provide a document analysis device, which adopts the technical solution described below: A document analysis device, comprising: The information data extraction module is used to extract information data contained in the document to be analyzed. The relation representation content extraction module is used to input the information data into a preset entity relation extraction component and extract the entity relation representation content and business requirement representation content contained in the information data. The target knowledge graph filtering module is used to filter out pre-built target general business entity relationship knowledge graphs; The target knowledge graph adjustment module is used to adjust and update the target general business entity relationship knowledge graph based on the entity relationship representation content, so as to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed. The requirement development mapping document acquisition module is used to acquire the requirement development mapping document pre-designed for the document to be analyzed; The document content recognition and determination module is used to identify business entities and execution steps in the requirement development mapping document, and determine the business function nodes, business processing dependencies and business processing flow in the requirement development mapping document; The logical conflict detection module is used to detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and to obtain the detection results. The detection result feedback module is used to generate a structured document analysis report based on the detection results and feed it back to the target receiving end.

[0007] Thirdly, embodiments of this application also provide a computer device that adopts the technical solution described below: A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the document analysis method described above.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium, which adopts the technical solutions described below: A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the document analysis method described above.

[0009] Compared with the prior art, the embodiments of this application have the following main advantages: The document analysis method described in this application extracts information data from the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a pre-designed requirement development mapping document for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts in business function nodes in terms of business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method realizes the rapid analysis of requirement description documents by utilizing artificial intelligence processing and general business entity relationship knowledge graphs, thereby efficiently determining the actual development tasks. Applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis processing and improve the efficiency of determining the actual development tasks in financial business development scenarios or medical and health care business development scenarios. Attached Figure Description

[0010] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is an exemplary system architecture diagram to which this application can be applied; Figure 2 This is a flowchart of an embodiment of a document analysis method according to this application; Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 201 shown; Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 202 shown; Figure 5 yes Figure 4A flowchart of a specific embodiment of step 402 shown; Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 203 shown; Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 204 shown; Figure 8 yes Figure 2 A flowchart of a specific embodiment of step 207 shown; Figure 9 This is a schematic diagram of one embodiment of a document analysis device according to this application; Figure 10 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0012] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0013] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0015] like Figure 1 As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables.

[0016] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0017] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0018] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0019] It should be noted that the document analysis method provided in this application embodiment is generally executed by a server, and correspondingly, a document analysis device is generally set in the server.

[0020] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0021] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of a document analysis method according to this application. The document analysis method includes the following steps: Step 201: Extract the information data contained in the document to be analyzed.

[0022] In this embodiment, the document to be analyzed includes a requirement description document sent by the software development client to the software development contractor before the actual software development task is assigned. The software development client includes the party requesting the software development task, while the software development contractor refers to the party that writes the code to actually develop the required software. Specifically, since the document to be analyzed mainly contains information data describing requirements, the information data can generally be in text form. In another case, since some information data cannot clearly express the requirements in text description, it can also be in the form of image tags.

[0023] In this embodiment, the extraction of information data contained in the document to be analyzed, that is, the extraction of multimodal information data from the document to be analyzed, can be achieved using a preset multimodal information extraction model, such as: a multimodal information extraction model based on LayoutLMv3, Hunyuan, Wenxin, etc., which supports the extraction of information data from text data and image data in the document to be analyzed.

[0024] Step 202: Input the information data into a preset entity relationship extraction component to extract the entity relationship representation content and business requirement representation content contained in the information data.

[0025] In this embodiment, the preset entity relationship extraction component includes a semantic information recognition sub-component and a word segmentation processing sub-component. Specifically, the semantic information recognition sub-component includes a pre-trained semantic information recognition sub-component based on natural language understanding, as well as a pre-trained semantic information recognition sub-component based on BERT, etc.; the word segmentation processing sub-component includes a word segmentation processing sub-component based on part-of-speech analysis.

[0026] Specifically, the semantic information recognition subcomponent is first used to perform semantic information recognition on the information data. Then, based on the semantic information recognition results, the word segmentation subcomponent is used to perform word segmentation on the information data. Based on the word segmentation results, the entity relationship representation content and business requirement representation content contained in the information data are extracted.

[0027] Step 203: Filter out the pre-built target general business entity relationship knowledge graph.

[0028] In this embodiment, the target general business entity relationship knowledge graph is stored in a preset general business entity relationship knowledge graph library. Specifically, the preset general business entity relationship knowledge graph library stores a large number of general business entity relationship knowledge graphs generated based on previous development tasks.

[0029] It should be understood that each general business entity relationship knowledge graph contains the minimum business logic processing nodes required for different development tasks. For example, when developing a secure login task, it should at least include an input task, a verification task, and a post-verification execution task. That is, if the verification is successful, the login is successful; if it fails, a prompt to log in again should be displayed.

[0030] In this embodiment, by filtering out the pre-built target general business entity relationship knowledge graph, the optimal development task implementation logic can be provided to the task developer when different development tasks are identified. That is, when the requester only points out the login task, a secure login method can be extended to enrich and expand the business logic processing nodes that the requester missed when making the request, so as to ensure the integrity of the development task design.

[0031] Step 204: Adjust and update the target general business entity relationship knowledge graph based on the entity relationship representation content to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed.

[0032] In this embodiment, the adjustment and updating of the target general business entity relationship knowledge graph based on the entity relationship representation content not only includes updating and adjusting the target general business entity relationship knowledge graph according to the entity relationship representation content, but also implicitly includes the subsequent reverse supplementation of the business logic processing nodes not mentioned in the document to be analyzed but actually required by combining the adjusted business entity relationship knowledge graph, thereby ensuring the integrity of the business logic.

[0033] Step 205: Obtain the requirements development mapping document pre-designed for the document to be analyzed.

[0034] In this embodiment, the requirement development mapping document designed in advance for the document to be analyzed can be a requirement development mapping document initially compiled by the requirement development organizer, which contains different development tasks. Specifically, each development task involves a corresponding business entity and execution steps.

[0035] In this embodiment, by obtaining a pre-designed requirement development mapping document for the document to be analyzed, it is clear that all development tasks involve the corresponding business entities and execution steps.

[0036] Step 206: Identify business entities and execution steps in the requirement development mapping document to determine the business function nodes, business processing dependencies, and business processing flow contained in the requirement development mapping document.

[0037] Step 207: Based on the business entity relationship knowledge graph corresponding to the document to be analyzed, detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, and obtain the detection results.

[0038] Specifically, if the business function nodes are consistent with the directed relationships between their corresponding entities in the business entity relationship knowledge graph in terms of business processing dependencies and business processing flow, then there is no logical conflict. Otherwise, there is a certain logical conflict, and optimization and adjustment are required.

[0039] Step 208: Generate a structured document analysis report based on the detection results and feed it back to the target receiving end.

[0040] In this embodiment, the target receiving end includes the software development contractor, referring to the code writer who actually develops the required software, and also includes the software development task requester. This facilitates quick negotiation between the task requester and the actual development team to reach a satisfactory actual development task.

[0041] In this embodiment, the document analysis method can be applied to financial business development scenarios or medical and health care business development scenarios where the business logic processing nodes are relatively complex. It can significantly reduce the amount of manual requirement analysis and processing, and use artificial intelligence processing and general business entity relationship knowledge graphs to quickly analyze requirement description documents, thereby efficiently determining the actual development tasks and improving the efficiency of determining the actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0042] The speech generation method provided in this embodiment extracts information data from the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a pre-designed requirement development mapping document for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts in business function nodes in business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method realizes the rapid analysis of requirement description documents by utilizing artificial intelligence processing and general business entity relationship knowledge graphs, thereby efficiently determining the actual development tasks. Applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis processing and improve the efficiency of determining the actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0043] Continue to refer to Figure 3 , Figure 3 yes Figure 2A flowchart of a specific embodiment of step 201 shown includes: Step 301: Input the document to be analyzed into the pre-trained multimodal information extraction model, wherein the document to be analyzed contains textual data and non-textual data; Specifically, the textual data refers to the textual data directly contained in the document to be analyzed, while the non-textual data refers to the image-based example data provided in the document to be analyzed.

[0044] Step 302: Obtain the textual description information data output by the multimodal information extraction model for the textual data and non-textual data in the document to be analyzed; Specifically, the text content extraction component in the multimodal information extraction model is used to directly extract the textual data as the textual description information data corresponding to the textual data. The image content extraction component in the multimodal information extraction model is used to extract the data content of non-textual data and generate textual description information data for non-textual data by combining preset textual description prompts.

[0045] Step 303: Integrate the textual description information data corresponding to the textualized data and the textual description information data corresponding to the non-textualized data as the information data extraction result of the document to be analyzed.

[0046] Specifically, the integration of the textual description information data corresponding to the textual data and the textual description information data corresponding to the non-textual data can be combined with a preset integration strategy. For example, if the textual description information data corresponding to the current textual data is explanatory data for a certain image, the textual description information data and the textual description information data corresponding to that image can be integrated into the same textual description information data.

[0047] In this embodiment, a pre-trained multimodal information extraction model is used to extract information data contained in the document to be analyzed. This can fully extract the information data contained in the document to be analyzed and finally output textual description information data, which is also convenient for subsequent information data processing.

[0048] Continue to refer to Figure 4 , Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 202 shown includes: Step 401: Using the semantic information recognition sub-component, identify the semantic expression contained in each sentence in the information data; Step 402: Based on the expressed semantics and the word segmentation processing sub-component, perform word segmentation processing on all sentences in the information data to obtain the word segmentation processing result; Specifically, a semantic information recognition method is adopted. First, the information data is semantically recognized. Then, word segmentation is performed based on the semantic information recognition results, which ensures the accuracy of subsequent extraction of entity relationship representation content and business requirement representation content.

[0049] Step 403: Based on the word segmentation results, determine the business entity names, business constraints, logical relationships between different business entities, business functional requirement description fields, and business non-functional requirement description fields contained in the information data. Step 404: Select the business entity name, business constraints, and logical relationships between different business entities as the entity relationship representation content; Step 405: Select the functional business requirement description field and the non-functional business requirement description field as the business requirement representation content.

[0050] Continue to refer to Figure 5 , Figure 5 yes Figure 4 A flowchart of a specific embodiment of step 402 shown includes: Step 501: Based on the semantic expression of the current sentence, identify the text field content of different parts of speech in the current sentence; Specifically, based on the part of speech of different word fields in the sentence, such as nouns, verbs, prepositions, etc., the text field content of different parts of speech in the current sentence is identified.

[0051] Step 502: Use the word segmentation processing sub-component to segment the text fields with different parts of speech in the current sentence according to the part of speech distinction, and obtain the word segmentation processing result.

[0052] Specifically, this involves segmenting text fields of different parts of speech to obtain text field content for nouns, verbs, prepositions, etc.

[0053] By repeatedly executing steps 501 and 502, word segmentation processing is achieved for all sentences in the information data.

[0054] In this embodiment, based on the word segmentation results, the business entity names, business constraints, logical relationships between different business entities, and functional and non-functional business requirement description fields contained in the information data are determined. Generally, business entity names are mostly text fields of name or pronoun type, business constraints are mostly text fields of qualifying words, and the logical relationships between different business entities need to be determined by combining the verb expressions between nouns. The functional and non-functional business requirement description fields need to be determined based on the specific meanings of the verb expressions. The specific determination strategy can be compiled and determined based on historical batches of actual business requirement descriptions.

[0055] Continue to refer to Figure 6 , Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 203 shown includes: Step 601: Summarize all business entity names contained in the entity relationship representation content; Step 602: Using all the business entity names as the filtering criteria, filter out the business entity relationship knowledge graph that fully contains all the business entity names from the preset general business entity relationship knowledge graph filtering library; In this embodiment, the preset general business entity relationship knowledge graph filtering library records all graph nodes contained in each general business entity relationship knowledge graph, and the naming of the graph node is consistent with the name of the corresponding business entity.

[0056] Step 603: Count the number of business entities in each selected business entity relationship knowledge graph; Specifically, the number of business entities in the business entity relationship knowledge graph refers to the graph node data contained in the business entity relationship knowledge graph. In other words, each graph node corresponds to a business entity name.

[0057] Step 604: After mutual comparison, the business entity relationship knowledge graph corresponding to the minimum number of business entities is obtained as the target general business entity relationship knowledge graph.

[0058] Specifically, since different business entity relationship knowledge graphs contain different graph node data, that is, they map different combinations of business entity names, in the optimal case, the number of graph nodes in the business entity relationship knowledge graph corresponding to the minimum number of selected business entities is exactly the same as the number of extracted business entity names. However, considering that the documents to be analyzed are not actually provided by the developers, but mostly by the requesters, there is a problem of incompleteness. Therefore, in most cases, the number of extracted business entity names is less than the number of graph nodes in the corresponding business entity relationship knowledge graph. Therefore, after comparison, the business entity relationship knowledge graph corresponding to the minimum number of business entities is obtained as the target general business entity relationship knowledge graph, which can meet the design requirements of the corresponding actual development task. While ensuring compliance with the target business development requirements, it avoids selecting an overly complex and large general business entity relationship knowledge graph.

[0059] In this embodiment, after performing the step of comparing and obtaining the business entity relationship knowledge graph corresponding to the minimum number of business entities as the target general business entity relationship knowledge graph, the method further includes: counting the number of business node names contained in the entity relationship representation content; identifying the number of graph nodes in the target general business entity relationship knowledge graph; comparing the size relationship between the number of graph nodes and the number of business node names; if the number of graph nodes is greater than the number of business node names, then supplementing the business node names contained in the entity relationship representation content according to the graph nodes in the target general business entity relationship knowledge graph, and obtaining the supplemented entity relationship representation content.

[0060] Specifically, since the target general business entity relationship knowledge graph is the business entity relationship knowledge graph corresponding to the minimum number of business entities, there are two possible scenarios regarding the relationship between the number of graph nodes and the number of business node names: they are equal, and the number of business entity names is less than the number of graph nodes. When the number of extracted business entity names is less than the number of graph nodes in the corresponding business entity relationship knowledge graph, since the business entity relationship knowledge graph contains the minimum combination of business entity names corresponding to different actual development needs, the entity relationship representation content is supplemented in reverse to ensure the completeness of the requirements for the document to be analyzed. After the requirements have been supplemented, logical conflict comparison is performed. When they are equal, there is no need to supplement the document to be analyzed, and subsequent logical conflict comparison is performed directly.

[0061] Continue to refer to Figure 7 , Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 204 shown includes: Step 701: Add business constraints to the target general business entity relationship knowledge graph based on the business constraints contained in the information data; In this embodiment, the business constraints include numerical size relationship conventions and judgment condition constraints.

[0062] Step 702: Based on the logical relationships between different business entities contained in the information data, adjust the logical pointing relationships of different business entity names in the target general business entity relationship knowledge graph; Specifically, the logical relationships between the different business entities map the execution sequence of different business logic processing nodes.

[0063] Step 703: Obtain the business entity relationship knowledge graph after adding business constraints and adjusting logical pointing relationships as the business entity relationship knowledge graph corresponding to the document to be analyzed.

[0064] In this embodiment, the target general business entity relationship knowledge graph is adjusted and updated by the entity relationship representation content to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed, thereby realizing the acquisition of the business entity relationship knowledge graph applicable to this development task.

[0065] In this embodiment, the step of identifying business entities and execution steps in the requirement development mapping document, and determining the business function nodes, business processing dependencies, and business processing flows contained in the requirement development mapping document, includes: obtaining all task execution nodes in the requirement development mapping document and the calling relationships between each task execution node; identifying the business entities based on all task execution nodes, and identifying the execution steps based on the calling relationships between each task execution node; determining the business function nodes contained in the requirement development mapping document based on all identified business entities; and determining the business processing dependencies and business processing flows contained in the requirement development mapping document based on the business entities and the execution steps.

[0066] Continue to refer to Figure 8 , Figure 8 yes Figure 2 A flowchart of a specific embodiment of step 207 shown includes: Step 801: Identify the business constraints contained in the business entity relationship knowledge graph corresponding to the document to be analyzed; Step 802: Identify the logical pointing relationships between different business entity names in the business entity relationship knowledge graph corresponding to the document to be analyzed; Specifically, the logical pointing relationship between different business entity names in the business entity relationship knowledge graph corresponding to the document to be analyzed can be identified and determined based on the directed indicator lines between different graph nodes in the business entity relationship knowledge graph.

[0067] Step 803: Determine whether the business function nodes in the requirement development mapping document meet the business constraints in terms of business processing dependencies; Step 804: Determine whether the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in the business processing flow. Step 805: If the business function nodes in the requirement development mapping document all meet the business constraints in terms of business processing dependencies, and the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in terms of business processing flow, then the requirement development mapping document does not have a logical conflict; otherwise, the requirement development mapping document has a logical conflict.

[0068] In this embodiment, the step of generating a structured document analysis report based on the detection results and feeding it back to the target receiving end includes: if the detection result indicates that the requirement development mapping document does not have logical conflicts, then the requirement development mapping document is directly structured and organized to generate a structured document analysis report, which is then fed back to the target receiving end; if the detection result indicates that the requirement development mapping document has logical conflicts, then based on the logical conflict results and combined with the business entity relationship knowledge graph corresponding to the document to be analyzed, the business processing dependencies and business processing flow of the requirement development mapping document are adjusted to generate adjustment record information, and then the adjusted requirement development mapping document is structured and organized to generate a structured document analysis report, and the document analysis report and the adjustment record information are fed back to the target receiving end together.

[0069] The speech generation method provided in this embodiment extracts information data from the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a pre-designed requirement development mapping document for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts in business function nodes in business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method realizes the rapid analysis of requirement description documents by utilizing artificial intelligence processing and general business entity relationship knowledge graphs, thereby efficiently determining the actual development tasks. Applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis processing and improve the efficiency of determining the actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0070] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0071] Foundational artificial intelligence technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0072] The speech generation method provided in this embodiment extracts information data from the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a pre-designed requirement development mapping document for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts in business function nodes in business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method realizes the rapid analysis of requirement description documents by utilizing artificial intelligence processing and general business entity relationship knowledge graphs, thereby efficiently determining the actual development tasks. Applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis processing and improve the efficiency of determining the actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0073] Further reference Figure 9 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a document analysis device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0074] like Figure 9 As shown, the document analysis device 900 described in this embodiment includes: an information data extraction module 901, a relation representation content extraction module 902, a target knowledge graph filtering module 903, a target knowledge graph adjustment module 904, a requirement development mapping document acquisition module 905, a document content recognition and determination module 906, a logical conflict detection module 907, and a detection result feedback module 908. Wherein: The information data extraction module 901 is used to extract information data contained in the document to be analyzed. The relation representation content extraction module 902 is used to input the information data into a preset entity relation extraction component and extract the entity relation representation content and business requirement representation content contained in the information data. The target knowledge graph filtering module 903 is used to filter out pre-built target general business entity relationship knowledge graphs; The target knowledge graph adjustment module 904 is used to adjust and update the target general business entity relationship knowledge graph based on the entity relationship representation content, so as to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed. The requirement development mapping document acquisition module 905 is used to acquire the requirement development mapping document pre-designed for the document to be analyzed; The document content recognition and determination module 906 is used to identify business entities and execution steps in the requirement development mapping document, and determine the business function nodes, business processing dependencies and business processing flow in the requirement development mapping document. The logical conflict detection module 907 is used to detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and to obtain the detection result. The detection result feedback module 908 is used to generate a structured document analysis report based on the detection results and feed it back to the target receiving end.

[0075] This application extracts information data from the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a pre-designed requirement development mapping document for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; based on the business entity relationship knowledge graph corresponding to the document to be analyzed, detects whether there are logical conflicts in business function nodes in business processing dependencies and business processing flows, and obtains the detection results; generates a structured document analysis report based on the detection results and feeds it back to the target recipient. This method realizes the rapid analysis of requirement description documents using artificial intelligence processing and general business entity relationship knowledge graphs, thereby efficiently determining actual development tasks. Applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis processing and improve the efficiency of determining actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0076] In this embodiment, the information data extraction module 901 includes a document input unit, a textual description unit, and an information data extraction unit. Wherein: The document to be analyzed input unit is used to input the document to be analyzed into a pre-trained multimodal information extraction model, wherein the document to be analyzed contains textual data and non-textual data; A text description unit is used to acquire text description information data output by the multimodal information extraction model for textual data and non-textual data in the document to be analyzed. The information data extraction unit is used to integrate the textual description information data corresponding to the textual data and the textual description information data corresponding to the non-textual data, as the information data extraction result of the document to be analyzed.

[0077] In this embodiment, the relationship representation content extraction module 902 includes a semantic information recognition unit, a word segmentation processing unit, a word segmentation result determination unit, an entity relationship representation content filtering unit, and a business requirement representation content filtering unit. Wherein: A semantic information recognition unit is used to identify the semantic expression contained in each sentence in the information data using the semantic information recognition sub-component; The word segmentation processing unit is used to perform word segmentation processing on all sentences in the information data according to the expressed semantics and the word segmentation processing sub-component to obtain the word segmentation processing result; The word segmentation result determination unit is used to determine, based on the word segmentation processing result, the business entity name, business constraints, logical relationships between different business entities, business functional requirement description field and business non-functional requirement description field contained in the information data. The entity relationship representation content filtering unit is used to filter out the business entity name, business constraints, and logical relationships between different business entities as the entity relationship representation content. The business requirement representation content filtering unit is used to filter out the business functional requirement description field and the business non-functional requirement description field as the business requirement representation content.

[0078] In this embodiment, the word segmentation processing unit includes a part-of-speech tagging subunit and a word segmentation processing subunit. Wherein: The part-of-speech tagging subunit is used to identify the text field content with different parts of speech in the current sentence based on the semantic expression of the current sentence. The word segmentation processing subunit is used to segment the text field content of different parts of speech in the current sentence according to the part of speech distinction, and obtain the word segmentation processing result.

[0079] In this embodiment, the target knowledge graph filtering module 903 includes a business entity name aggregation unit, a knowledge graph filtering library filtering unit, a business entity quantity statistics unit, and a comparison and determination unit. Wherein: The business entity name aggregation unit is used to aggregate all business entity names contained in the entity relationship representation content; The knowledge graph filtering unit is used to filter out a business entity relationship knowledge graph that fully contains the names of all the business entities from a preset general business entity relationship knowledge graph filtering library, using the names of all the business entities as the filtering criteria. The business entity quantity statistics unit is used to count the number of business entities in the knowledge graph of each selected business entity relationship; The comparison and determination unit is used to obtain the business entity relationship knowledge graph corresponding to the minimum number of business entities through mutual comparison as the target general business entity relationship knowledge graph.

[0080] In this embodiment, the document analysis device 900 further includes a business node name and quantity statistics module, a graph node quantity identification module, a node quantity size comparison module, and an entity relationship representation content supplementation processing module. Wherein: The business node name count module is used to count the number of business node names contained in the entity relationship representation content; The graph node count identification module is used to identify the number of graph nodes in the target general business entity relationship knowledge graph. Specifically, since the preset general business entity relationship knowledge graph screening library records all the graph nodes contained in each general business entity relationship knowledge graph, the number of graph nodes in the target general business entity relationship knowledge graph can be determined by identification within the library.

[0081] The node quantity comparison module is used to compare the relationship between the number of nodes in the graph and the number of business node names. The entity relationship representation content supplementation processing module is used to supplement the business node names contained in the entity relationship representation content according to the graph nodes in the target general business entity relationship knowledge graph if the number of graph nodes is greater than the number of business node names, and obtain the supplemented entity relationship representation content.

[0082] In this embodiment, the target knowledge graph adjustment module 904 includes a business constraint addition unit, a logical pointing relationship adjustment unit, and a target knowledge graph determination unit. Wherein: The business constraint addition unit is used to add business constraints to the target general business entity relationship knowledge graph based on the business constraints contained in the information data. The logical pointing relationship adjustment unit is used to adjust the logical pointing relationship of different business entity names in the target general business entity relationship knowledge graph according to the logical association relationship between different business entities contained in the information data. The target knowledge graph determination unit is used to obtain the business entity relationship knowledge graph after adding business constraints and adjusting logical pointing relationships as the business entity relationship knowledge graph corresponding to the document to be analyzed.

[0083] In this embodiment, the document content recognition and determination module 906 includes a task execution information acquisition unit, a task execution information recognition unit, a business function node determination unit, and a business processing information determination unit. Wherein: The task execution information acquisition unit is used to acquire all task execution nodes in the requirement development mapping document and the calling relationships between each task execution node. The task execution information identification unit is used to identify the business entity based on all task execution nodes, and to identify the execution steps based on the calling relationship between each task execution node; The business function node determination unit is used to determine the business function nodes in the requirement development mapping document based on all identified business entities. The business processing information determination unit is used to determine the business processing dependencies and business processing flow contained in the requirement development mapping document based on the business entity and the execution steps.

[0084] In this embodiment, the logical conflict detection module 907 includes a business constraint identification unit, a logical pointing relationship identification unit, a first detection and judgment unit, a second detection and judgment unit, and a logical conflict determination unit. Wherein: A business constraint identification unit is used to identify the business constraints contained in the business entity relationship knowledge graph corresponding to the document to be analyzed; The logical pointing relationship identification unit is used to identify the logical pointing relationship between different business entity names in the business entity relationship knowledge graph corresponding to the document to be analyzed; The first detection and judgment unit is used to determine whether the business function nodes in the requirement development mapping document meet the business constraints in terms of business processing dependencies; The second detection and judgment unit is used to determine whether the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in the business processing flow. The logical conflict determination unit is used to determine if the business function nodes in the requirement development mapping document meet the business constraints in terms of business processing dependencies, and if the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in terms of business processing flow, then the requirement development mapping document does not have a logical conflict; otherwise, the requirement development mapping document has a logical conflict.

[0085] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0086] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0087] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 10 , Figure 10 This is a basic structural block diagram of the computer device in this embodiment.

[0088] The computer device 10 includes a memory 10a, a processor 10b, and a network interface 10c, which are interconnected via a system bus. It should be noted that... Figure 10 Only a computer device 10 with component memory 10a, processor 10b, and network interface 10c is shown. However, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0089] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0090] The memory 10a includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10a may be an internal storage unit of the computer device 10, such as the hard disk or memory of the computer device 10. In other embodiments, the memory 10a may also be an external storage device of the computer device 10, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the memory 10a may include both internal storage units and external storage devices of the computer device 10. In this embodiment, the memory 10a is typically used to store the operating system and various application software installed on the computer device 10, such as computer-readable instructions for a document analysis method. In addition, the memory 10a can also be used to temporarily store various types of data that have been output or will be output.

[0091] In some embodiments, the processor 10b may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 10b is typically used to control the overall operation of the computer device 10. In this embodiment, the processor 10b is used to execute computer-readable instructions stored in the memory 10a or to process data, for example, to execute computer-readable instructions for the document analysis method described above.

[0092] The network interface 10c may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 10 and other electronic devices.

[0093] The computer device proposed in this embodiment belongs to the field of artificial intelligence technology and is applied in scenarios involving the generation, detection, and updating of requirement development mapping documents based on business requirement information provided by customers. This application extracts information data contained in the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a requirement development mapping document pre-designed for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts between business function nodes and business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method utilizes artificial intelligence processing and a general business entity relationship knowledge graph to quickly analyze requirement description documents, thereby efficiently determining actual development tasks. When applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis and processing, and improve the efficiency of determining actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0094] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by a processor to cause the processor to perform the steps of the document analysis method described above.

[0095] The computer-readable storage medium proposed in this embodiment belongs to the field of artificial intelligence technology and is applied in scenarios involving the generation, detection, and updating of requirement development mapping documents based on business requirement information provided by customers. This application extracts information data contained in the document to be analyzed; extracts entity relationship representations and business requirement representations from the information data; filters out a target general business entity relationship knowledge graph; adjusts and updates it to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; obtains a requirement development mapping document pre-designed for the document to be analyzed; identifies business entities and execution steps in the requirement development mapping document to determine business function nodes, business processing dependencies, and business processing flows; detects whether there are logical conflicts between business function nodes and business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtains the detection results; and generates a structured document analysis report based on the detection results and feeds it back to the target receiving end. This method utilizes artificial intelligence processing and a general business entity relationship knowledge graph to quickly analyze requirement description documents, thereby efficiently determining actual development tasks. When applied to financial business development scenarios or medical and health care business development scenarios with complex business logic processing nodes, it can significantly reduce the amount of manual requirement analysis and processing, and improve the efficiency of determining actual development tasks in financial business development scenarios or medical and health care business development scenarios.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0097] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to make the disclosure of this application more thorough and comprehensive. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application. Software tools or components not belonging to this company that appear in the embodiments of this application are merely illustrative examples and do not represent actual use.

[0098] It should be noted that if any AI model software tools or components not belonging to this company appear in the embodiments of this application, they are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application is authorized (with the knowledge and consent) by the relevant parties or fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

Claims

1. A document analysis method, characterized in that, Includes the following steps: Extract information data contained in the document to be analyzed; The information data is input into a preset entity relationship extraction component to extract the entity relationship representation content and business requirement representation content contained in the information data. Filter out the pre-built target general business entity relationship knowledge graph; Based on the entity relationship representation content, the target general business entity relationship knowledge graph is adjusted and updated to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed; Obtain the requirements development mapping document pre-designed for the document to be analyzed; The business entities and execution steps of the requirement development mapping document are identified to determine the business function nodes, business processing dependencies and business processing flow contained in the requirement development mapping document; Based on the business entity relationship knowledge graph corresponding to the document to be analyzed, detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, and obtain the detection results. A structured document analysis report is generated based on the detection results and fed back to the target receiving end.

2. The document analysis method according to claim 1, characterized in that, The step of extracting information data contained in the document to be analyzed includes: The document to be analyzed is input into a pre-trained multimodal information extraction model, wherein the document to be analyzed contains textual data and non-textual data; Obtain the textual description information data output by the multimodal information extraction model for the textual data and non-textual data in the document to be analyzed; The textual description information data corresponding to the textualized data and the textual description information data corresponding to the non-textualized data are integrated to form the information data extraction result of the document to be analyzed.

3. The document analysis method according to claim 1, characterized in that, The preset entity relationship extraction component includes a semantic information recognition subcomponent and a word segmentation processing subcomponent. The step of inputting the information data into the preset entity relationship extraction component and extracting the entity relationship representation content and business requirement representation content contained in the information data includes: Using the semantic information recognition sub-component, the semantic expression contained in each sentence in the information data is identified; Based on the expressed semantics and the word segmentation sub-component, all sentences in the information data are segmented to obtain the word segmentation result. Based on the word segmentation results, the business entity names, business constraints, logical relationships between different business entities, business functional requirement description fields, and business non-functional requirement description fields contained in the information data are determined. The business entity names, business constraints, and logical relationships between different business entities are selected as the entity relationship representation content. The functional business requirement description fields and non-functional business requirement description fields are selected as the representation content of the business requirement.

4. The document analysis method according to claim 3, characterized in that, The step of performing word segmentation on all sentences in the information data based on the expressed semantics and the word segmentation processing sub-component to obtain the word segmentation result includes: Based on the semantic expression of the current sentence, identify the text field content of different parts of speech in the current sentence; The word segmentation sub-component is used to segment the text fields of different parts of speech in the current sentence according to the part of speech distinction, and the word segmentation result is obtained.

5. The document analysis method according to claim 1, characterized in that, The step of filtering out the pre-built target general business entity relationship knowledge graph includes: Summarize all business entity names contained in the entity relationship representation content; Using the names of all the business entities as the filtering criteria, a business entity relationship knowledge graph that fully contains the names of all the business entities is filtered out from a preset general business entity relationship knowledge graph filtering library. Count the number of business entities in the knowledge graph of each selected business entity relationship; After mutual comparison, the business entity relationship knowledge graph corresponding to the minimum number of business entities is obtained as the target general business entity relationship knowledge graph. The step of adjusting and updating the target general business entity relationship knowledge graph based on the entity relationship representation content to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed includes: Based on the business constraints contained in the information data, business constraints are added to the target general business entity relationship knowledge graph. Based on the logical relationships between different business entities contained in the information data, the logical pointing relationships of different business entity names in the target general business entity relationship knowledge graph are adjusted. The business entity relationship knowledge graph obtained after adding business constraints and adjusting logical pointing relationships is used as the business entity relationship knowledge graph corresponding to the document to be analyzed.

6. The document analysis method according to claim 1, characterized in that, The step of detecting whether there are logical conflicts in the business function nodes in the requirement development mapping document regarding business processing dependencies and business processing flows based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and obtaining the detection result, includes: Identify the business constraints contained in the business entity relationship knowledge graph corresponding to the document to be analyzed, and; Identify the logical relationships between different business entity names in the business entity relationship knowledge graph corresponding to the document to be analyzed; Determine whether the business function nodes in the requirement development mapping document meet the business constraints in terms of business processing dependencies; Determine whether the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in the business processing flow; If the business function nodes in the requirement development mapping document all meet the business constraints in terms of business processing dependencies, and the business function nodes in the requirement development mapping document are consistent with the logical pointing relationship between the different business entity names in terms of business processing flow, then the requirement development mapping document does not have a logical conflict; otherwise, the requirement development mapping document has a logical conflict.

7. The document analysis method according to claim 1, characterized in that, The step of generating a structured document analysis report based on the detection results and feeding it back to the target receiver includes: If the detection result indicates that there are no logical conflicts in the requirement development mapping document, then the requirement development mapping document is directly structured and organized to generate a structured document analysis report, which is then fed back to the target receiving end. If the detection result indicates that there is a logical conflict in the requirement development mapping document, then based on the logical conflict result and combined with the business entity relationship knowledge graph corresponding to the document to be analyzed, the business processing dependencies and business processing flow of the requirement development mapping document are adjusted to generate adjustment record information. Then, the adjusted requirement development mapping document is structured and organized to generate a structured document analysis report. The document analysis report and the adjustment record information are fed back to the target receiving end.

8. A document analysis device, characterized in that, include: The information data extraction module is used to extract information data contained in the document to be analyzed. The relation representation content extraction module is used to input the information data into a preset entity relation extraction component and extract the entity relation representation content and business requirement representation content contained in the information data. The target knowledge graph filtering module is used to filter out pre-built target general business entity relationship knowledge graphs; The target knowledge graph adjustment module is used to adjust and update the target general business entity relationship knowledge graph based on the entity relationship representation content, so as to obtain the business entity relationship knowledge graph corresponding to the document to be analyzed. The requirement development mapping document acquisition module is used to acquire the requirement development mapping document pre-designed for the document to be analyzed; The document content recognition and determination module is used to identify business entities and execution steps in the requirement development mapping document, and determine the business function nodes, business processing dependencies and business processing flow in the requirement development mapping document; The logical conflict detection module is used to detect whether there are logical conflicts in the business function nodes in the requirement development mapping document in terms of business processing dependencies and business processing flow, based on the business entity relationship knowledge graph corresponding to the document to be analyzed, and to obtain the detection results. The detection result feedback module is used to generate a structured document analysis report based on the detection results and feed it back to the target receiving end.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the document analysis method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the document analysis method as described in any one of claims 1 to 7.

Images