Project file management method and device, equipment, storage medium and product

Abstract

The invention discloses a project file management method and device, equipment, a storage medium and a product, and relates to the technical field of knowledge maps. The method comprises the steps of obtaining project basic data; based on the project basic data, a project knowledge graph is constructed, and the project knowledge graph is used for reflecting a relation chain of the project; wherein the project knowledge graph comprises a responsibility relation graph, a quality traceability graph and a change citation graph, the responsibility relation graph comprises a responsibility relation chain, and the quality traceability graph comprises a quality traceability chain; the change citation map comprises a change information index; storing the project knowledge graph into a graph database; and in response to query content input by a user, performing query based on the graph database and returning a query result. Compared with the prior art, the relation chain of the project is reflected through the responsibility relation graph, the quality traceability graph and the change citation graph, and compared with manual custom management rules, the method is more convenient and higher in accuracy. In addition, the project knowledge graph is combined with the graph database, so that the responsibility relationship is clearer and more visible.

Description

Technical Field

[0001] The present application relates to the field of knowledge graph technology, and specifically to a project file management method, device, equipment, storage medium and product. Background Art

[0002] Traditional knowledge graph extraction for construction project data primarily involves manual identification and relationship extraction to generate knowledge graph data, which is then used to construct a logical framework for construction project data management. However, this approach relies on manual annotation and rule definition, which is complex and leads to poor project file management effectiveness. Summary of the Invention

[0003] In view of this, the present application provides a project file management method, device, equipment, storage medium and product, the main purpose of which is to solve the problem that the current project management system for construction engineering data has complex rule definitions and poor management effects.

[0004] In a first aspect, the present application provides a project file management method, comprising:

[0005] Acquiring basic project data, wherein the basic data includes at least one of project level data, unit data, personnel data, quality data, and change data;

[0006] Based on the project basic data, a project knowledge graph is constructed, wherein the project knowledge graph is used to reflect the relationship chain of the project; wherein the project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph, wherein the responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index;

[0007] Storing the project knowledge graph in a graph database;

[0008] In response to the query content input by the user, a query is performed based on the graph database and the query result is returned.

[0009] Optionally, the responsibility relationship diagram includes the following nodes and relationships: node type: at least one of project, unit project, division, sub-division, sub-item, participating unit, and personnel; relationship type: at least one of inclusion, construction, supervision, design, survey, general contracting, subcontracting, and affiliation.

[0010] Optionally, the quality traceability diagram includes the following nodes and relationships: node type: building materials, concrete test blocks, test reports, usage locations, classification catalogs; relationship types: inclusion, usage, and relevance.

[0011] Optionally, the change citation diagram includes the following nodes and relationships: node type: change order, drawing, meeting minutes, approval document, project part; relationship type: change, association, reference.

[0012] Optionally, in response to the query content input by the user, querying based on the graph database and returning the query result includes: converting the query content into a query statement of the graph database through a large language model, and generating a query result after executing the query.

[0013] Optionally, the graph database includes one of TuGraph, Neo4j, JanusGraph or HugeGraph.

[0014] In a second aspect, the present application provides a project file management device, comprising:

[0015] an acquisition unit configured to acquire basic project data, wherein the basic data includes at least one of project data, unit data, personnel data, quality data, and change data;

[0016] A construction unit is configured to construct a project knowledge graph based on the project basic data, wherein the project knowledge graph is used to reflect the relationship chain of the project; wherein the project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph, wherein the responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index;

[0017] A storage unit, configured to store the project knowledge graph in a graph database;

[0018] The query unit is configured to perform a query based on the graph database in response to the query content input by the user and return the query result.

[0019] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the project file management method described in the first aspect.

[0020] In a fourth aspect, the present application provides an electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the project file management method described in the first aspect when executing the computer program.

[0021] In a fifth aspect, the present application provides a computer program product having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the project file management method described in the first aspect is implemented.

[0022] By means of the above technical solution, the present application provides a project file management method, device, equipment, storage medium and product, which first obtains the basic data of the project, and the basic data includes at least one of project hierarchical data, unit data, personnel data, quality data and change data. Then, based on the basic data of the project, a project knowledge graph is constructed, where the project knowledge graph is used to reflect the relationship chain of the project; wherein, the project knowledge graph includes a responsibility relationship graph, a quality traceability graph and a change citation graph, the responsibility relationship graph includes a responsibility relationship chain, the quality traceability graph includes a quality traceability chain; the change citation graph includes a change information index; the project knowledge graph is stored in a graph database; in response to the query content input by the user, a query is performed based on the graph database and the query results are returned. The traditional knowledge graph construction requires word segmentation, extraction, decomposition and other processes, and all require human participation in understanding and definition. The rule definition for knowledge graph construction is complex and the management effect is poor. In comparison, this application uses responsibility relationship diagrams, quality traceability diagrams, and change citation diagrams to reflect the relationship chain in complex engineering projects, more clearly and intuitively reflecting the relationships in project details; and then combining with graph databases, combining project knowledge graphs with graph databases, making the responsibility relationships clearer and more visual.

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 A schematic diagram of a project file management method provided in an embodiment of the present application is shown;

[0027] Figure 2 A schematic diagram illustrating a process of another project file management method provided in an embodiment of the present application is shown;

[0028] Figure 3 It shows a knowledge graph construction diagram of responsibility relationships in another project file management method provided by an embodiment of the present application;

[0029] Figure 4 It shows a quality traceability knowledge graph construction diagram in another project file management method provided by an embodiment of the present application;

[0030] Figure 5 It shows a diagram for constructing a change citation knowledge graph in another project file management method provided by an embodiment of the present application;

[0031] Figure 6 A diagram showing a directory list of files included in project data extraction in another project file management method provided by an embodiment of the present application is shown;

[0032] Figure 7 A schematic diagram of the structure of a project file management device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to more clearly understand the above-mentioned objectives, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0034] A project file management method proposed in this embodiment is applied to a project file management device or electronic device. The device or electronic device can be installed or integrated into some file management systems and can execute any of the project file management methods mentioned below during operation.

[0035] First, the technical terms used in the explanation of this embodiment are explained, including:

[0036] Knowledge Graph: A structured semantic network used to represent and organize knowledge. It represents entities (such as people, places, events, concepts, etc.) and the relationships between them in the form of a graph, thereby achieving efficient storage, management, and reasoning of knowledge.

[0037] Large Language Model (LLM): An artificial intelligence model built based on deep learning technology, mainly used to process natural language related tasks such as text generation, language understanding, translation, question answering, etc.

[0038] Graph Database: A database management system specifically designed for storing and querying graph-structured data. It uses nodes, relationships, and properties as its core data model and can efficiently represent and process complex relationships and network structures.

[0039] Cypher is a declarative graph query language specifically designed for interacting with graph databases such as Neo4j. It allows users to query, update, and manipulate nodes, relationships, and their properties in graph data through a concise and intuitive syntax.

[0040] TuGraph: A graph database with powerful graph storage, graph computing, graph learning, and graph R&D capabilities.

[0041] Data cleaning is the process of preprocessing data to remove errors, duplications, inconsistencies, or incomplete records, thereby improving data quality. Data cleaning is a key step in fields such as data analysis, data mining, and machine learning. High-quality data can significantly improve model performance and the accuracy of analytical results.

[0042] In order to improve the current construction project data project management system construction process rules definition is complex and the management effect is poor. This embodiment proposes a project file management method, such as Figure 1 As shown, the method includes:

[0043] S101, obtaining basic project data;

[0044] The basic project data mainly refers to electronic files in the system that need to be managed, such as a project in the project file library of a construction project electronic archive platform. The basic project data includes at least one of project level data, unit data, personnel data, quality data and change data. In the case where the files that need to be managed are not stored in the system but are paper files, the basic project data can be obtained by scanning the paper files and identifying them through OCR technology, and then extracting the data. Among them, OCR (Optical Character Recognition) technology is a technology that converts the text content in an image into editable and searchable text.

[0045] S102, build a project knowledge graph based on project basic data;

[0046] A knowledge graph is a structured semantic network used to represent and organize knowledge. It represents entities (such as people, places, events, and concepts) and their relationships in a graph format, enabling efficient storage, management, and reasoning of knowledge. The project knowledge graph is used to reflect the project's chain of relationships; it includes a responsibility relationship graph, a quality traceability graph, and a change citation graph. The responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index.

[0047] Specifically, based on the basic project data, the steps of building a project knowledge graph may include:

[0048] Engineering entity recognition uses a rule engine and NLP models to identify engineering terms in text (electronic documents). For example, if the general contractor is xx Group, it will be identified as name: xx Group; type: general contractor.

[0049] Then, using a large language model, we analyze and establish relationships based on the semantics of engineering documents (this can be a conventional semantic recognition dictionary or a domain dictionary containing key terms from the construction engineering field to improve semantic recognition accuracy). Finally, we use these relationships to construct a project knowledge graph. For example, a responsibility relationship graph might include relationships such as construction unit-subcontractor-subcontractor, supervision unit-construction-unit project, and so on. This construction method transforms discrete engineering data into a reasonable and traceable knowledge network, thereby improving data connectivity and traceability.

[0050] S103, storing the project knowledge graph in a graph database;

[0051] A graph database is a database management system specifically designed for storing and querying graph-structured data. It uses nodes, relationships, and properties as its core data model, enabling efficient representation and processing of complex relationships and network structures. For example, a graph database might be TuGraph, Neo4j, JanusGraph, or HugeGraph.

[0052] S104: In response to the query content input by the user, a query is performed based on the graph database and the query result is returned.

[0053] Specifically, the query content can be converted into a query statement for the graph database through a large language model, and the query results are generated after the query is executed. Furthermore, the query statement for the graph database can optionally be a Cypher statement, which is a declarative graph query language specifically designed for interacting with graph databases (such as Neo 4j). It allows users to query, update, and manipulate nodes (Node), relationships (Relationship), and their properties (Property) in graph data through a concise and intuitive syntax. This also echoes the established project knowledge graph, and by querying the various relationships and nodes in the extracted construction project, project information can be clearly and intuitively obtained.

[0054] Traditional knowledge graph extraction from construction project data primarily involves manually creating and generating knowledge graph data for construction project data, and then using this knowledge graph data to construct a logical framework for construction project data management. In this embodiment, basic project data is first acquired. Basic data includes at least one of project hierarchical data, unit data, personnel data, quality data, and change data. Based on this basic project data, a project knowledge graph is then constructed. The project knowledge graph is used to reflect the project's relationship chain. The project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph. The responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index. The project knowledge graph is then stored in a graph database. In response to user-entered queries, queries are performed based on the graph database and query results are returned. The responsibility relationship graph, quality traceability graph, and change citation graph are used to reflect the relationship chain within complex engineering projects, more clearly and intuitively displaying the relationships within project details. Furthermore, the project knowledge graph is integrated with the graph database to make responsibility relationships more clearly visible.

[0055] Optionally, the responsibility relationship diagram includes the following nodes and relationships: node type: at least one of project, unit project, division, sub-division, sub-item, participating unit, and personnel; relationship type: at least one of inclusion, construction, supervision, design, survey, general contracting, subcontracting, and affiliation.

[0056] In this embodiment, when constructing a knowledge graph centered on responsibility relationships, node types and relationship types can be integrated and organized to clearly demonstrate the associations and responsibilities between different entities. In this way, the associations and responsibilities between different entities can be clearly demonstrated, providing strong support for project management, quality control, and responsibility tracing. Specifically, the node types include:

[0057] 1. Project: Represents a complete construction project or engineering project and is the top-level node in the knowledge graph. It includes multiple unit projects and is the object of overall responsibility and management.

[0058] 2. Unit Project: A subset of a project, usually representing an independent building or engineering section. It can be further divided into sub-projects.

[0059] 3. Division: A component of a unit project, such as foundation engineering, main structure engineering, etc. It can be further divided into sub-division projects.

[0060] 4. Sub-division: A more detailed division under the sub-division project, such as concrete structure sub-division, masonry structure sub-division, etc. It can be subdivided into sub-projects.

[0061] 5. Sub-item: Specific construction items under the sub-division project, such as formwork installation, steel bar binding, etc. It is the smallest responsible unit in the construction process.

[0062] 6. Participating Units: Units involved in project construction, including construction units, supervision units, design units, and survey units. They are connected to project and unit project nodes through relationship types, indicating their roles and responsibilities in the project.

[0063] 7. Personnel: Specific personnel involved in project construction, such as project managers, supervision engineers, designers, etc. They are usually affiliated with a participating unit and have specific responsibilities in the project.

[0064] Relationship types include:

[0065] 1. Include: Indicates that a project includes unit projects, which in turn include sub-projects, and so on. This is used to show the hierarchical relationship between different levels.

[0066] 2. Construction: This indicates that a construction unit is carrying out construction on a specific section, subsection, or project. It connects the construction unit to the specific construction project.

[0067] 3. Supervision: This indicates that the supervision unit supervises a specific division, sub-division, or project. It connects the supervision unit to the specific supervision object.

[0068] 4. Design: Indicates that the design unit is responsible for the design of a unit project, division, or sub-division. It connects the design unit with the specific design object.

[0069] 5. Survey: This indicates that the survey unit conducts geological surveys and other work on the project. Connect the survey unit to nodes such as the project or unit project.

[0070] 6. General Contractor: This indicates that a construction company is the general contractor for the entire project or a specific unit project. This connects the general contractor to the project or unit project nodes.

[0071] 7. Subcontract: This indicates that a construction participant acts as a subcontractor, responsible for a specific division, sub-division, or sub-project under the general contractor. It connects the subcontractor to the specific subcontracted object.

[0072] 8. Affiliation: Indicates that the personnel belongs to a certain construction unit. Connect the personnel and construction unit nodes.

[0073] Optionally, the quality traceability diagram includes the following nodes and relationships: node type: building materials, concrete test blocks, test reports, usage locations, classification catalogs; relationship types: inclusion, usage, and related.

[0074] In this embodiment, when constructing a knowledge graph centered on quality traceability, the node types (building materials, concrete test blocks, test reports, usage locations, classification catalogs) and relationship types (include, use, related) mentioned above can be integrated and organized. In this way, the entire process of building materials from procurement, testing to use, as well as the quality associations and traceability paths between each link, can be clearly displayed. Specifically, the node types include:

[0075] 1. Building materials: These represent the various raw materials or components used in the project, such as cement, steel bars, sand and gravel. They are the starting point for quality traceability, and all subsequent quality information and traceability paths revolve around building materials.

[0076] 2. Concrete test blocks: These are specimens made of building materials (especially cement, sand, and gravel) used to test the strength and other properties of concrete. They are an important indicator of building material quality, and their test results directly impact the assessment of building material quality.

[0077] 3. Test Report: This is a formal document issued after quality testing of building materials or concrete test blocks, containing test data, conclusions, and other information. It is key evidence for quality traceability and is used to prove the quality of building materials or concrete test blocks.

[0078] 4. Location of use: The specific location where the building materials or concrete test blocks are used in the project, such as columns and beams on a certain floor. This is used to track the actual use of building materials in the project so that quality issues can be quickly identified when they arise.

[0079] 5. Classification catalog: A catalog or standard for classifying building materials, concrete test blocks, etc., such as by material type, specification, manufacturer, etc. It is used to organize and manage quality traceability information for quick retrieval and query.

[0080] Relationship types include:

[0081] 1. Include: Indicates that a category contains a specific building material or concrete test block. This is used to display the location of the building material or concrete test block within the category, facilitating management and traceability by category.

[0082] 2. Use: Indicates that a building material or concrete block is used in a specific location. Connect the building material, concrete block, and location nodes to show the actual usage path of the building material in the project.

[0083] 3. Correlation: Indicates a correlation between building materials, concrete test blocks, and test reports. Typically, one building material or concrete test block corresponds to one or more test reports, which provide important information about the quality of the building material or concrete test block.

[0084] Optionally, the change citation diagram includes the following nodes and relationships: node type: change order, drawing, meeting minutes, approval document, project part; relationship type: change, association, reference.

[0085] In this embodiment, when constructing a knowledge graph with change citation as the core, information can be organized according to given node types (change orders, drawings, meeting minutes, approval documents, project parts) and relationship types (change, association, reference) to clearly display the source, basis, approval process of the project change, and the project parts affected by the change. In this way, the source (such as meeting minutes), basis (such as drawings), approval process (such as approval documents), and project parts affected by the change of the project change can be clearly displayed. Specifically, the node types include:

[0086] 1. Change Order: This is a formal document representing a project change, recording key information such as the content, reason, and time of the change. It is the core node in the Change Citation Knowledge Graph, and all change-related information revolves around it.

[0087] 2. Drawings: These are the design drawings of the project, showing the original design intent and structural layout of the project. During the change process, the drawings may need to be modified or updated due to the changes.

[0088] 3. Meeting Minutes: Record the content, discussion results, and decisions of meetings related to project changes. They are an important basis for the change decision-making process and reflect the background and considerations of the change.

[0089] 4. Approval Documents: Formal documents for approving change orders, which may include internal approval processes, approval opinions from the owner or supervisor, etc. They prove the legality and validity of the change and are a prerequisite for implementation.

[0090] 5. Project Location: A specific location or area within a project, such as a floor, room, or structural component. Changes may be made to specific project locations, making them important nodes in the change citation knowledge graph.

[0091] Relationship types include:

[0092] 1. Change: This indicates that a change order has modified a drawing, project part, or other node. Connect the change order to the drawing, project part, or other node to display the specific content and impact of the change.

[0093] 2. Association: This indicates the relationship between nodes such as meeting minutes and approval documents and the change order. For example, meeting minutes may record the discussion process of the change, and approval documents may contain the approval opinions of the change. These associations help understand the background and decision-making process of the change.

[0094] 3. Reference: This indicates that a node, such as a drawing or meeting minutes, is referenced in a change order as the basis or reference for the change. For example, a change order might reference a section in a drawing as the starting point for a change, or a decision in a meeting minute as the justification for the change. Reference relationships help verify the rationality and accuracy of changes.

[0095] Optionally, in response to the query content input by the user, a query is performed based on the graph database and the query result is returned, including: converting the query content into a query statement of the graph database through a large language model, and generating a query result after executing the query.

[0096] In this embodiment, a graph database is a database system specifically used to store, manage, and query graph-structured data. Graph-structured data consists of nodes (representing entities) and edges (representing relationships between entities), and is very suitable for representing and querying data with complex relationships, such as social networks, recommendation systems, knowledge graphs, etc. Users make query requests in the form of natural language, and a large language model is used to parse and understand the user's natural language query. The model converts the natural language query into a query language specific to the graph database, such as Cypher for TuGraph. The converted query statement is sent to the graph database for execution. The graph database traverses the nodes and relationships based on the query statement to find data that meets the conditions. After executing the query, the graph database returns a set of matching results. These results may be in the form of nodes, relationships, or paths, depending on the type of query and the structure of the database. The query results are returned to the user.

[0097] Optionally, the graph database includes one of TuGraph, Neo4j, JanusGraph or HugeGraph.

[0098] In this embodiment, TuGraph has powerful graph computing capabilities and efficient data processing capabilities, supports the storage and query of large-scale graph data, and is suitable for a variety of scenarios. Neo 4j is one of the popular open source graph databases, known for its ease of use, high performance and rich functionality. It supports ACID transactions, provides a powerful graph query language Cypher, and is widely used in social networks, recommendation systems, network management and other fields. JanusGraph is an open source distributed graph database that supports the storage and query of large-scale graph data. It provides flexible storage backend and indexing options, can be integrated with a variety of big data technologies (such as Hadoop, Spark), and is suitable for scenarios that need to process massive graph data. HugeGraph is a high-performance graph database that supports fast storage and query of hundreds of billions of vertices and edges. It provides a wealth of graph algorithms and graph analysis capabilities, suitable for scenarios such as knowledge graphs, anti-fraud, and recommendation systems.

[0099] Furthermore, the project file management method used in this embodiment is introduced. Figure 2 FIG. 1 is a flow chart showing another project file management method proposed in this embodiment.

[0100] First, we start with the parsing of electronic files. The electronic files here can be obtained through project files in the electronic archive management platform, or by scanning and identifying paper documents. Then, the generated knowledge graph can be stored in the graph database through data processing of the large language model. The data processing process here includes steps such as engineering entity recognition as mentioned above, recognition through rule engines and NLP models, semantic generation and relationship establishment, and finally generation of knowledge graphs based on relationships. On the other hand, database tables refer to data files related to projects stored in the electronic archive management platform, such as quality acceptance record forms, qualification application forms, engineering material lists, management personnel registration forms, test reports, material strength summary tables, etc. This type of database table can also generate relationships and construct knowledge graphs through data extraction and entity recognition. When a user asks a question, the system queries the relevant data from the graph database, and then the large language model generates a summary reply, which is finally fed back to the user. The details are as follows:

[0101] 1. Electronic document analysis

[0102] Input: In this embodiment, the electronic file input is a file carrier of a certain electronic archive platform, mainly a native electronic file.

[0103] Processing: Parsing electronic documents and converting their content into a format that can be understood by large language models.

[0104] Output: The parsed content is passed to the large language model.

[0105] 2. Large Language Model Data Processing

[0106] Input: parsed electronic file content.

[0107] Processing: The large language model processes the input content, including engineering entity recognition, identification through rule engines and NLP models, semantic generation and relationship establishment, and finally generating a knowledge graph based on the relationships.

[0108] Output: The generated data processing results are passed to the graph database.

[0109] 3. Data processing and storage

[0110] Input: Data processing results from a large language model.

[0111] Data extraction: Understand and store entity information from the knowledge graph in the data processing results.

[0112] 4. Graph Database Query

[0113] Input: The processed data is stored in a graph database.

[0114] Processing: Generate query statements to query the graph database based on subsequent requirements.

[0115] Output: The query result is passed to the large language model.

[0116] 5. Large language model generates summary responses

[0117] Input: Query results of the graph database.

[0118] Processing: The large language model analyzes and summarizes the query results and generates responses that are easy for users to understand.

[0119] Output: Summary reply delivered to the user.

[0120] 6. User Interaction

[0121] Input: A question or request from the user.

[0122] Processing: The user's question triggers the entire process, and the final summary reply generated by the large language model serves as a response to the user's question.

[0123] Output: User receives summary response.

[0124] Specifically, the implementation steps are as follows:

[0125] 1. Knowledge graph construction

[0126] After extracting entity information, three knowledge graphs are created based on the three dimensions of “responsibility relationship”, “quality traceability” and “change citation”. Figures 3 to 5 shown.

[0127] Specifically, the metadata of the responsibility relationship diagram is as follows: Table 1 and Table 2:

[0128] Table 1. Node types of responsibility relationship knowledge graph

[0129]

[0130]

[0131] Table 2 Responsibility relationship knowledge graph relationship types

[0132] side constraint property Include Project → Unit Project, Unit Project → Division, Division → Sub-division, Sub-division → Sub-item - Construction Unit→Project - construction Unit→Unit Project, Unit→Division, Unit→Subdivision, Unit→Sub-item - Supervision Unit→Unit Project - design Unit→Unit Project, Unit→Division - Survey Unit→Unit Project - General Contractor Unit→Unit Project, Unit→Division, Unit→Subdivision, Unit→Sub-item - Subcontracting Unit→Unit Project, Unit→Division, Unit→Subdivision, Unit→Sub-item name Serve Unit→Project - Supervision Unit→Project - Construction Unit→Project - Affiliation Personnel → Unit - supply Supplier→Unit -

[0133] The quality traceability metadata are shown in Tables 3 and 4 below:

[0134] Table 3 Node types of quality traceability knowledge graph

[0135]

[0136]

[0137] Table 4. Relationship types in the quality traceability knowledge graph

[0138] side constraint property Include Project → Unit Project, Unit Project → Division - use Unit project → classification, division → classification - Related Classification → Materials, Classification → Concrete -

[0139] The changed citation metadata are shown in Tables 5 and 6 below:

[0140] Table 5 Change citation knowledge graph node types

[0141]

[0142]

[0143] Table 6 Change citation knowledge graph relationship types

[0144] side constraint property Include Project → Unit Project, Unit Project → Division, Division → Sub-item - change Division → Change - association Change → File -

[0145] 2. Data processing

[0146] (1) Project data

[0147] First, extract the list of directories containing files from the project data, such as Figure 6 As shown in the figure, the relationship: project → unit project → division → sub-division → item is obtained, and Cypher statements are generated. After executing the Cypher statements, the data can be written to the graph database. Based on the extracted data structure, corresponding Cypher statements (the query language of the Neo4j graph database) are generated. After executing these statements, the project data will be written to the graph database, forming a queryable graph structure.

[0148] (2) Unit data

[0149] Extract information about the main construction units from the project information on the electronic archive platform. In some embodiments, information about the main construction units can be extracted from a database; related relationships can be extracted from quality acceptance records; subcontractor data can be extracted from the "Subcontractor Qualification Review Form"; and supplier data can be extracted from the "Finished Product and Semi-finished Product Supplier Qualification Application Form."

[0150] (3) Personnel data

[0151] The "Registration Form for Key Construction Management Personnel of Engineering Projects" obtains a list of construction unit management personnel, and the list of personnel who have applied for electronic signatures is obtained from the seal roster in the database. The data from the management personnel registration form and the list of signature personnel can be combined with the knowledge graph for data traceability, making the traceability relationship clearer.

[0152] (4) Quality traceability is mainly extracted from material data

[0153] The material data is obtained from the Engineering Material List, and the corresponding test report information is obtained according to the report number in the summary table.

[0154] (5) Change of citation data

[0155] Obtain change records from change notices; obtain associated documents by change order number; and use related drawing numbers to ensure the integrity and traceability of change information.

[0156] 3. Knowledge Graph Utilization

[0157] (1) Web page visualization display graph data

[0158] (2) With information data as the core, a conversational search engine based on the electronic archive corpus is established in combination with a large language model, and related data and files are displayed in a visual form of the data resource chain, effectively improving the efficiency of data resource retrieval and enabling construction project management.

[0159] (3) In the query results, nodes are associated with files. Clicking on the title link will jump to view the file details.

[0160] For example, the interaction prompt words with the large language model are as follows:

[0161] You are a graph database expert, responsible for converting user questions into Cypher queries. The database schema is as follows: {graph metadata}

[0162] Please follow the requirements below:

[0163] 1. Please generate a Cypher statement to query TuGraph. Just return the code without explanation.

[0164] 2. The current project ID is: {project ID}, the project name is: {project name}, and the main project name is the same as the project name.

[0165] 3. The labels of nodes and edges are all in Chinese and do not need to be converted to English.

[0166] 4. TuGraph does not support multiple matches. If multiple matches are required, please add a WITH statement.

[0167] 5. Please check whether there are any problems with the output Cypher statement. If there are any problems, please correct them.

[0168] When answering questions about different projects and different graphs, replace {graph metadata}, {project ID}, and {project name}.

[0169] Execute a graph query based on the Cypher statement returned by the big model. Then, interact with the query results with the big model, allowing the big model to summarize the answer in natural language. The prompt words are as follows:

[0170] User question: {question}

[0171] Query results: {query results}

[0172] Please generate a natural language answer based on the results.

[0173] Based on the above embodiment, by constructing a project knowledge graph for reflecting the relationship chain of the project, including a responsibility relationship graph, a quality traceability graph and a change citation graph, the relationship chain in complex engineering projects is clearly reflected, and the relationship in the project details is more clearly and intuitively reflected; and then combined with the graph database, the project knowledge graph is combined with the graph database, so that the responsibility relationship is clearer and more visual, which is convenient for user query.

[0174] Further, as Figures 1 to 6 The specific implementation of the method shown in this embodiment provides a project file management device, such as Figure 7 As shown, the device includes: an acquisition unit 701, a construction unit 702, a storage unit 703 and a query unit 704.

[0175] An acquisition unit 701 is configured to acquire basic project data, where the basic data includes at least one of project data, unit data, personnel data, quality data, and change data;

[0176] The construction unit 702 is configured to construct a project knowledge graph based on the project basic data, wherein the project knowledge graph is used to reflect the relationship chain of the project; wherein the project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph, wherein the responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index;

[0177] The storage unit 703 is configured to store the project knowledge graph in a graph database;

[0178] The query unit 704 is configured to perform a query based on the graph database in response to the query content input by the user and return the query result.

[0179] In a specific application scenario, the query unit 704 is further configured to convert the query content into a query statement of the graph database through a large language model, and generate a query result after executing the query.

[0180] In a specific application scenario, the storage unit 703 is further configured as a graph database including one of TuGraph, Neo4j, JanusGraph or HugeGraph.

[0181] It should be noted that for other corresponding descriptions of the functional units involved in the project file management device provided in this embodiment, please refer to Figures 1 to 6 The corresponding description in will not be repeated here.

[0182] Based on the above Figures 1 to 6 The method shown in FIG. 1 is a method for performing the above-mentioned steps. Accordingly, this embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program can realize the above-mentioned steps. Figures 1 to 6 The method shown.

[0183] Based on the above Figures 1 to 6 The method shown in FIG. 1 is a method for performing the above-mentioned operations. Accordingly, this embodiment further provides a computer program product having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned Figures 1 to 6 The method shown.

[0184] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0185] Based on the above Figures 1 to 6 The method shown, and Figure 7In order to achieve the above-mentioned purpose, the embodiment of the present application further provides an electronic device that can be configured on a computer terminal, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figures 1 to 6 The method shown.

[0186] Based on the above Figures 1 to 6 The method shown, and Figure 7 In order to achieve the above-mentioned purpose, the embodiment of the virtual device shown in the embodiment of the present application further provides a chip, including one or more interface circuits and one or more processors; the interface circuit is used to receive a signal from the memory of the electronic device and send the signal to the processor, the signal including the computer instruction stored in the memory; when the processor executes the computer instruction, the electronic device executes the above-mentioned Figures 1 to 6 The method shown.

[0187] Optionally, the physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a Wi-Fi module, and the like. The user interface may include a display, an input unit such as a keyboard, and the like. The optional user interface may also include a USB interface, a card reader interface, and the like. The network interface may optionally include a standard wired interface, a wireless interface (such as a Wi-Fi interface), and the like.

[0188] Those skilled in the art will understand that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0189] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device, supporting the execution of information processing programs and other software and / or programs. The network communication module is used to enable communication between components within the storage medium, as well as with other hardware and software within the physical information processing device.

[0190] Through the description of the above implementation methods, those skilled in the art can clearly understand that this application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the solution of this embodiment, compared with related technologies, the relationship chain in complex engineering projects is reflected through responsibility relationship diagrams, quality traceability diagrams, and change citation diagrams, which more clearly and intuitively reflects the relationship in project details; and then combined with the graph database, the project knowledge graph is combined with the graph database, making the responsibility relationship clearer and more visible.

[0191] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0192] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand and implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments described herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A project file management method, characterized in that: include: Acquiring basic project data, wherein the basic data includes at least one of project level data, unit data, personnel data, quality data, and change data; Based on the project basic data, a project knowledge graph is constructed, wherein the project knowledge graph is used to reflect the relationship chain of the project; wherein the project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph, wherein the responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index; Storing the project knowledge graph in a graph database; In response to the query content input by the user, a query is performed based on the graph database and the query result is returned.

2. The method according to claim 1, characterized in that The responsibility relationship diagram includes the following nodes and relationships: Node type: at least one of project, unit project, division, sub-division, sub-item, construction unit, and personnel; Relationship type: at least one of: inclusion, construction, supervision, design, survey, general contracting, subcontracting, and affiliation.

3. The method according to claim 1, characterized in that The quality traceability diagram includes the following nodes and relationships: Node type: building materials, concrete test blocks, test reports, usage locations, classification catalogs; Relationship type: contains, uses, relates to.

4. The method according to claim 1, wherein The change citation graph includes the following nodes and relationships: Node type: change order, drawing, meeting minutes, approval document, project part; Relationship type: change, association, reference.

5. The method according to claim 1, wherein The step of querying the graph database in response to the query content input by the user and returning the query result includes: The query content is converted into a query statement of the graph database through a large language model, and a query result is generated after the query is executed.

6. The method according to claim 1, characterized in that The graph database includes one of TuGraph, Neo4j, JanusGraph or HugeGraph.

7. A project file management device, characterized in that: include: an acquisition unit configured to acquire basic project data, wherein the basic data includes at least one of project data, unit data, personnel data, quality data, and change data; A construction unit is configured to construct a project knowledge graph based on the project basic data, wherein the project knowledge graph is used to reflect the relationship chain of the project; wherein the project knowledge graph includes a responsibility relationship graph, a quality traceability graph, and a change citation graph, wherein the responsibility relationship graph includes the responsibility relationship chain, the quality traceability graph includes the quality traceability chain, and the change citation graph includes a change information index; A storage unit, configured to store the project knowledge graph in a graph database; The query unit is configured to perform a query based on the graph database in response to the query content input by the user and return the query result.

8. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images