Nuclear power item data intelligent question and answer method and system based on graph database

Abstract

The invention relates to the technical field of nuclear power plant equipment intelligent question answering, and provides a nuclear power item data intelligent question answering method and system based on a graph database. The method comprises the steps of extracting nuclear power item data and relation data between nuclear power items and parts based on a text of a nuclear power equipment purchase contract; based on the supplier basic data, extracting supplier basic information; based on nuclear power item data, relation data of nuclear power items and parts and supplier basic information, entity data including the nuclear power item data, the part data and the supplier basic information are created as nodes, the relation between the nodes is defined, and the nodes and the relation are stored in a graph database; wherein the nodes comprise related attribute information; acquiring an input natural language query, and analyzing the input natural language query by adopting a natural language understanding technology to generate a query language; and querying the graph database based on the query language to obtain an output result.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent question and answer of nuclear power plant equipment, and in particular to an intelligent question and answer method and system for nuclear power item data based on a graph database. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The nuclear power field involves a wide range of areas, including not only the design, production, construction and operation of nuclear island equipment, but also nuclear power plants and their supporting civilian conventional industrial products. These processes involve a large number of different types of items: from large equipment such as reactors and steam generators to small components such as bolts and pipe joints. In addition, there are complex triple relationships between items. For example, complete equipment contains parts, parts include several consumables, and consumables include raw materials. Each item is also associated with a variety of information such as design parameters and operating procedures. This information needs to be updated over time, such as records after replacing parts and status updates after maintenance.

[0004] The traditional way of storing item data mainly relies on relational databases, such as MySQL. This method has the following problems: First, the fixed mode of relational databases limits their flexibility. Nuclear power items involve components of various types and levels. Each component may have different attributes and related information. It is necessary to predefine the table structure for each item type, and complex schema migration is required when the schema changes, making management and maintenance difficult. Secondly, relational databases are less efficient when processing complex relationships and hierarchical queries. The hierarchical relationships and multiple associations between nuclear power items require frequent queries and operations. Multi-table join (JOIN) operations will cause a significant decrease in query efficiency when the data volume is large, affecting system performance and user experience.

[0005] In addition, in the implementation of intelligent question-answering systems, traditional methods rely on NLP algorithms such as named entity recognition. When processing user queries, these methods first perform intent recognition and entity recognition, then use NLP models or codes to construct the corresponding intents and entities into query statements for the knowledge graph, and finally query the graph database and construct answers. This method requires the definition of rules and templates, which is complex and difficult to adapt to the changing natural language input. Summary of the invention

[0006] In order to solve the technical problems existing in the above background technology, the present invention provides a method and system for intelligent question answering of nuclear power item data based on a graph database. The graph database used in the present invention can flexibly represent items and their complex relationships, and can be easily expanded and adjusted as the item data increases. This flexibility and scalability enables the system to adapt to the diversity and dynamic changes of data in nuclear power item management, and improves the efficiency of data management.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] The first aspect of the present invention provides an intelligent question-answering method for nuclear power item data based on a graph database.

[0009] A method for intelligent question answering of nuclear power item data based on a graph database, comprising:

[0010] Based on the text of nuclear power equipment procurement contracts, extract nuclear power item data and the relationship data between nuclear power items and components; based on the supplier basic data, extract the supplier's basic information;

[0011] Based on nuclear power item data, relationship data between nuclear power items and parts, and basic supplier information, entity data including nuclear power item data, parts data, and basic supplier information are created as nodes, relationships between nodes are defined, and nodes and relationships are stored in a graph database; wherein the nodes contain relevant attribute information;

[0012] Obtain input natural language query, use natural language understanding technology to parse the input natural language query, and generate query language; based on the query language, query the graph database to obtain output results.

[0013] Furthermore, the method for extracting nuclear power item data and relationship data between nuclear power items and parts based on the text of the nuclear power equipment procurement contract includes: extracting the text of the nuclear power equipment procurement contract using OCR to obtain OCR recognition results; introducing a nuclear power custom dictionary to process the OCR recognition results, correcting recognition errors of proper nouns and equipment names, and obtaining nuclear power item data and relationship data between nuclear power items and parts.

[0014] Furthermore, before creating the graph database, the following steps are performed: cleaning the node data, deleting redundant spaces and characteristic characters in the node data; and automatically identifying the node type and creating edge data relationships.

[0015] Furthermore, the graph database supports data insertion, data update and data deletion, wherein data insertion is the insertion of new item data, component data or supplier information, data update is the update of item data, component data or supplier information, and data deletion is the data after deleting an item or changing a supplier.

[0016] Furthermore, the nuclear power item data includes: complete equipment data, parts data and supplier data, and the relationship data between the nuclear power items and parts includes: the relationship between the complete equipment and parts, the relationship between the complete equipment and suppliers, and the relationship between parts and suppliers.

[0017] Furthermore, the basic information of the supplier includes: company name, company type, whether it is listed, registration status and legal representative.

[0018] Furthermore, the output results include all parts of the searched data, all corresponding suppliers and their locations.

[0019] The second aspect of the present invention provides an intelligent question-answering system for nuclear power item data based on a graph database.

[0020] An intelligent question-answering system for nuclear power item data based on a graph database, comprising:

[0021] An extraction module is configured to: extract nuclear power item data and relationship data between nuclear power items and components based on the text of the nuclear power equipment procurement contract; extract basic supplier information based on supplier basic data;

[0022] The graph database module is configured to: based on the nuclear power item data, the relationship data between the nuclear power item and the parts, and the basic information of the supplier, create the entity data including the nuclear power item data, the parts data, and the basic information of the supplier as nodes, define the relationship between the nodes, and store the nodes and the relationship in the graph database; wherein the nodes contain relevant attribute information;

[0023] The query module is configured to: obtain an input natural language query, parse the input natural language query using natural language understanding technology, and generate a query language; based on the query language, query the graph database to obtain an output result.

[0024] A third aspect of the present invention provides a computer-readable storage medium.

[0025] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for intelligent question and answer of nuclear power item data based on a graph database as described in the first aspect above.

[0026] A fourth aspect of the present invention provides a computer device.

[0027] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for intelligent question and answer of nuclear power item data based on a graph database as described in the first aspect above are implemented.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention uses a graph database to store nuclear power item data. Graph data items and their relationships do not require pre-defined fixed patterns, and are particularly suitable for storing nuclear power items of various types with complex associations. Graph databases are efficient in processing multi-level and multi-relationship queries, and the structure of their nodes and edges is closer to real-world items and their relationships, making them easier to understand and operate. At the same time, graph databases have good scalability and can be easily expanded and adjusted as item data increases. Through edge connections, graph databases can easily realize multiple associations and path analysis between items, which is very useful for tracing item history and conducting complex association analysis. Using a graph database to store nuclear power item data can effectively cope with the complexity and dynamism in nuclear power item management and improve the efficiency of data management and query.

[0030] The present invention adopts Text2Cypher technology based on a large model, eliminating the steps of defining rules and templates. The large model can directly generate corresponding Cypher query statements from natural language to query the graph database. Compared with traditional methods, this method is more concise and efficient, can more accurately understand and process users' natural language queries, and improve the response speed and accuracy of the intelligent question-answering system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0032] Figure 1 It is a flow chart of the method for intelligent question and answer of nuclear power item data based on graph database shown in the present invention;

[0033] Figure 2 It is a schematic diagram of a graph database constructed according to the present invention;

[0034] Figure 3 is a schematic diagram of the node types shown in the present invention;

[0035] Figure 4 It is a schematic diagram of the edge types shown in the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0039] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and systems according to various embodiments of the present disclosure. It should be noted that each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of a code may include one or more executable instructions for implementing the logical functions specified in each embodiment. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram can be implemented using a dedicated hardware-based system that performs a specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0040] Embodiment 1

[0041] This embodiment provides an intelligent question-and-answer method for nuclear power item data based on a graph database. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal, a server, and a server, and is implemented through the interaction between the terminal and the server. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communications, middleware services, domain name services, security services CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in this application. In this embodiment, the method includes the following steps:

[0042] Based on the text of nuclear power equipment procurement contracts, extract nuclear power item data and the relationship data between nuclear power items and components; based on the supplier basic data, extract the supplier's basic information;

[0043] Based on nuclear power item data, relationship data between nuclear power items and parts, and basic supplier information, entity data including nuclear power item data, parts data, and basic supplier information are created as nodes, relationships between nodes are defined, and nodes and relationships are stored in a graph database; wherein the nodes contain relevant attribute information;

[0044] Obtain input natural language query, use natural language understanding technology to parse the input natural language query, and generate query language; based on the query language, query the graph database to obtain output results.

[0045] The present invention proposes a method for intelligent question-answering of nuclear power item data based on a graph database. First, the data of items, parts, and suppliers in the contract text are automatically extracted from the contract management system, and the node table and relationship table are batch constructed in combination with the basic information of suppliers obtained from the outside, and stored in the graph database. The intelligent question-answering system based on the graph database can realize the functions of complex relationship query and analysis of item data, semantic retrieval, path retrieval, etc. The overall process is as follows: Figure 1 As shown. This invention significantly improves the efficiency and intelligence level of nuclear power item data management by utilizing the flexibility, efficient query and intuitive association representation of the graph database. At the same time, the invention introduces an intelligent question-and-answer system based on a large model, which changes the original interactive mode of data query, lowers the threshold for use, and enables non-technical users to easily use the system.

[0046] The present embodiment is described in detail below:

[0047] 1. Data extraction

[0048] Automatically extract the data of complete equipment, parts, and suppliers in the contract text from the contract management system, as well as the relationship between complete equipment and parts, and between complete equipment / parts and suppliers. The extracted complete equipment / parts data fields include item ID, item name, supplier name, type, etc. At the same time, combined with the basic information of suppliers obtained externally (company name, company type, whether listed, registration status, legal representative, etc.), ensure the comprehensiveness and accuracy of the data. The extraction rules are as follows: Figure 3 , Figure 4 , as shown in Table 1.

[0049] Table 1 Advance rules

[0050]

[0051]

[0052]

[0053]

[0054] The present invention automatically extracts data on items, parts, and suppliers in the contract text from the contract management system, and combines it with basic supplier information obtained from the outside to batch build node tables and relationship tables, and stores them in the graph database. This automated data extraction and update mechanism ensures the accuracy and timeliness of the data, reduces the need for manual intervention, and improves work efficiency.

[0055] The OCR technology is mainly used to extract information from the contract text. OCR (Optical Character Recognition) is a technology that converts printed or handwritten text into machine-encoded text. Considering that some historical contract texts are scanned PDF files with low OCR recognition rates, the present invention introduces a nuclear power custom dictionary to post-process the OCR recognition results, correct the recognition errors of proper nouns and equipment names, improve the OCR recognition efficiency and accuracy of the contract text, and ensure the reliability and integrity of data extraction.

[0056] When processing contract texts, the present invention uses OCR technology for text recognition, and especially introduces a nuclear power custom dictionary to post-process the OCR recognition results to correct recognition errors of proper nouns and equipment names, thereby improving recognition efficiency and accuracy.

[0057] 2. Build a graph database

[0058] The extracted data is constructed into node tables and relationship tables and stored in the graph database. The specific steps include:

[0059] ①Node creation: create entities such as items, parts, suppliers, etc. as nodes, each of which contains relevant attribute information; ②Relationship creation: define the relationship between nodes, such as the supply relationship between items and suppliers, the composition relationship between parts and complete equipment, etc.; ③Graph database storage: store the above nodes and relationships in the graph database. The constructed graph database example is as follows: Figure 2 shown.

[0060] The graph database is mainly created through Cypher statements. Considering that the data of nuclear power items is huge and the relationships are complex, the method of creating through Cypher statements is inefficient and not conducive to automatic updating of data. Therefore, the present invention adopts a batch creation method to create a graph database. The batch creation method has specific requirements on the format of the data (edge ​​data must be nested in double lists), so it is necessary to process the acquired node and edge data. The processing logic is shown in Table 2.

[0061] Table 2 Processing logic

[0062]

[0063]

[0064] 3. Data storage and update

[0065] By taking advantage of the flexibility and scalability of the graph database, new contract information is obtained from the contract management system on a regular basis (every quarter), and various associated information and hierarchical relationships of items are dynamically updated. Specifically, it includes:

[0066] ① Data insertion: insertion of new items, parts or supplier information; ② Data update: update of item status, supplier basic information, etc.; ③ Data deletion: deletion of data after elimination of items or replacement of suppliers.

[0067] The following are examples of dynamic updates:

[0068] Step 1: Add a new supplier "Supplier Y" to the contract management system. It is located in Shanghai and provides a key component of equipment X.

[0069] Step 2: The system automatically extracts the newly added supplier information and updates the nodes and relationships in the graph database.

[0070] Step 3: User: Query all suppliers of device X and their locations.

[0071] System (generates and executes query): MATCH (e: equipment {name: "equipment X"})-[:contains]->(p:subcomponent)-[:supply]->(s:supplier) RETURN s, s.city. The query results include the newly added "supplier Y" and its location in Shanghai.

[0072] The graph database designed by the present invention can flexibly represent items and their complex relationships, and can be easily expanded and adjusted as the item data increases. This flexibility and scalability enables the system to adapt to the diversity and dynamic changes of data in nuclear power item management, and improves the efficiency of data management.

[0073] 4. Intelligent question answering based on graph database

[0074] Unlike the tabular form of relational databases, graph databases directly display the associations between entities. This storage method is naturally suitable for expressing complex associations. The retrieval of traditional graph databases requires querying through Cypher statements, which is highly professional and may require additional learning time for users without SQL background. The present invention introduces an intelligent question-answering system based on large models (such as GPT-3) and Text2Cypher technology. GPT-3 is a powerful natural language processing model that can understand and generate human-like language text. Text2Cypher technology can parse the user's natural language input into Cypher query statements. The combination of these two technologies allows users to interact directly with the system through natural language, and they can obtain the required data without learning complex query languages.

[0075] Users can query data in a conversational way, and support context. For example, users can refine the query conditions step by step: "Show all suppliers.", "Show only suppliers in Beijing.", "What parts do these suppliers provide?". The system uses advanced natural language understanding (NLU) technology to parse the natural language queries entered by users, accurately understand the user's intentions and generate the corresponding query language of the graph database (such as Cypher query). For example, the user enters "query all sub-components of a certain device", and the system automatically generates the corresponding Cypher query statement after parsing and returns the query results. The retrieval results are displayed in the form of a relationship network diagram. Users can view detailed information by clicking on the node, and further expand or collapse the node to explore the hierarchical structure and association relationship of the data. The query example is as follows.

[0076] Example 1:

[0077] User: Query all parts and suppliers of equipment X.

[0078] System (generates Cypher query after parsing): MATCH (e: equipment {name: "equipment X"})-[:contains]->(p:subcomponent)-[:supply]->(s:supplier) RETURN p, s. The query result displays all parts of equipment X and its supplier information in the form of a knowledge graph.

[0079] Example 2:

[0080] User: Display all suppliers in Beijing.

[0081] System: OK, wait a minute. Do you need to filter certain types of suppliers as well?

[0082] User: Any supplier who provides reactor pressure vessel parts.

[0083] System (generates and executes query): MATCH(s:supplier{city:"Beijing"})-[:supply]->(p:subcomponent)-[:belongs to]->(e:equipment{type:"reactor pressure vessel"}) RETURN s, p, e, the query results display qualified suppliers and their supplied reactor pressure vessel parts in the form of a knowledge graph.

[0084] This invention introduces an intelligent question-answering method based on large models (such as GPT-3) and Text2Cypher technology, so that users can obtain the required data through natural language description without learning complex query languages. The system uses natural language understanding technology to parse user input, generate the corresponding graph database query language, and display the query results in the form of a relationship network diagram, so that users can intuitively view the data and conduct further exploration.

[0085] The present invention supports complex relationship query and analysis, semantic retrieval, path retrieval and other functions. Users can gradually refine the query conditions through dialogue, and the system can accurately understand the user's intention and return the corresponding results. This advanced query function greatly facilitates the user's retrieval and analysis of nuclear power item data.

[0086] Embodiment 2

[0087] This embodiment provides an intelligent question-answering system for nuclear power item data based on a graph database.

[0088] An intelligent question-answering system for nuclear power item data based on a graph database, comprising:

[0089] An extraction module is configured to: extract nuclear power item data and relationship data between nuclear power items and components based on the text of the nuclear power equipment procurement contract; extract basic supplier information based on supplier basic data;

[0090] The graph database module is configured to: based on the nuclear power item data, the relationship data between the nuclear power item and the parts, and the basic information of the supplier, create the entity data including the nuclear power item data, the parts data, and the basic information of the supplier as nodes, define the relationship between the nodes, and store the nodes and the relationship in the graph database; wherein the nodes contain relevant attribute information;

[0091] The query module is configured to: obtain an input natural language query, parse the input natural language query using natural language understanding technology, and generate a query language; based on the query language, query the graph database to obtain an output result.

[0092] The present invention automatically extracts the data of complete equipment, parts, and suppliers in the contract text from the contract management system, as well as the relationship between the complete equipment and parts, and between the complete equipment / parts and suppliers, and combines the basic information of suppliers obtained from the outside to batch build node tables and relationship tables, and store them in the graph database. This automated data extraction and construction mechanism ensures the accuracy and timeliness of the data, reduces the need for manual intervention, and improves work efficiency.

[0093] In some embodiments, the extraction module is further configured to: use OCR to extract the text of the nuclear power equipment procurement contract to obtain OCR recognition results; introduce a nuclear power custom dictionary to process the OCR recognition results, correct recognition errors of proper nouns and equipment names, and obtain nuclear power item data and relationship data between nuclear power items and components.

[0094] When processing contract texts, the present invention uses OCR technology for text recognition, and especially introduces a nuclear power custom dictionary to post-process the OCR recognition results to correct recognition errors of proper nouns and equipment names, thereby improving recognition efficiency and accuracy.

[0095] In some embodiments, the graph database module is further configured to: before creating the graph database, include: cleaning the node data, deleting redundant spaces and characteristic characters in the node data; and creating edge data relationships by automatically identifying node types.

[0096] In some embodiments, the graph database supports data insertion, data update and data deletion, wherein data insertion is the insertion of new item data, component data or supplier information, data update is the update of item data, component data or supplier information, and data deletion is the data after deleting an item or changing a supplier.

[0097] The present invention utilizes the flexibility and scalability of the graph database to regularly obtain new contract information from the contract management system and dynamically update various associated information and hierarchical relationships of items, including data insertion, insertion of new items, parts or supplier information, data update, item status, supplier basic information update, data deletion, data deletion after eliminating items or changing suppliers.

[0098] In some embodiments, the nuclear power item data includes: complete equipment data, component data and supplier data, and the relationship data between the nuclear power item and the components includes: the relationship between the complete equipment and the components, the relationship between the complete equipment and the supplier, and the relationship between the components and the supplier. The basic information of the supplier includes: company name, company type, whether it is listed, registration status and legal representative.

[0099] The present invention uses a graph database to store and manage nuclear power item data. The graph database can flexibly represent various items and their complex relationships without pre-defining fixed patterns. It is particularly suitable for storing multiple types of nuclear power item data with complex relationships. Compared with traditional relational databases, graph databases are more efficient in processing multi-level and multi-relationship queries and can better reflect the actual relationship between items.

[0100] In some embodiments, the output results include all parts of the queried data, all corresponding suppliers and their locations.

[0101] This invention introduces an intelligent question-answering system based on large models (such as GPT-3) and Text2Cypher technology, so that users can obtain the required data through natural language description without learning complex query languages. The system uses natural language understanding technology to parse user input, generate the corresponding graph database query language, and display the query results in the form of a relationship network diagram, so that users can intuitively view the data and conduct further exploration.

[0102] Embodiment 3

[0103] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the intelligent question-and-answer method for nuclear power item data based on a graph database as described in the first embodiment above are implemented.

[0104] Embodiment 4

[0105] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the intelligent question-and-answer method for nuclear power item data based on a graph database as described in the first embodiment above are implemented.

[0106] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0107] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0110] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent question-answering method for nuclear power item data based on a graph database, characterized in that: include: Based on the text of nuclear power equipment procurement contracts, extract nuclear power item data and the relationship data between nuclear power items and components; Extract basic information of suppliers based on supplier basic data; Based on nuclear power item data, relationship data between nuclear power items and parts, and basic supplier information, entity data including nuclear power item data, parts data, and basic supplier information are created as nodes, relationships between nodes are defined, and nodes and relationships are stored in a graph database; wherein the nodes contain relevant attribute information; Obtain input natural language query, use natural language understanding technology to parse the input natural language query, and generate query language; based on the query language, query the graph database to obtain output results.

2. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: The method for extracting nuclear power item data and relationship data between nuclear power items and parts based on the text of the nuclear power equipment procurement contract includes: extracting the text of the nuclear power equipment procurement contract using OCR to obtain OCR recognition results; introducing a nuclear power custom dictionary to process the OCR recognition results, correcting recognition errors of proper nouns and equipment names, and obtaining nuclear power item data and relationship data between nuclear power items and parts.

3. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: Before creating a graph database, the following steps are performed: cleaning the node data, deleting extra spaces and characteristic characters in the node data; and automatically identifying the node type and creating edge data relationships.

4. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: The graph database supports data insertion, data update and data deletion. The data insertion is the insertion of new item data, component data or supplier information. The data update is the update of item data, component data or supplier information. The data deletion is the data after deleting an item or changing a supplier.

5. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: The nuclear power item data include: complete equipment data, parts data and supplier data, and the relationship data between nuclear power items and parts include: the relationship between complete equipment and parts, the relationship between complete equipment and suppliers, and the relationship between parts and suppliers.

6. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: The basic information of the supplier includes: company name, company type, whether it is listed, registration status and legal representative.

7. The intelligent question-answering method for nuclear power item data based on graph database according to claim 1 is characterized in that: The output results include all parts of the searched data, all corresponding suppliers and their locations.

8. An intelligent question-answering system for nuclear power item data based on a graph database, characterized in that: include: An extraction module is configured to: extract nuclear power item data and relationship data between nuclear power items and components based on the text of the nuclear power equipment procurement contract; Extract basic information of suppliers based on supplier basic data; The graph database module is configured to: based on the nuclear power item data, the relationship data between the nuclear power item and the parts, and the basic information of the supplier, create the entity data including the nuclear power item data, the parts data, and the basic information of the supplier as nodes, define the relationship between the nodes, and store the nodes and the relationship in the graph database; wherein the nodes contain relevant attribute information; The query module is configured to: obtain an input natural language query, parse the input natural language query using natural language understanding technology, and generate a query language; based on the query language, query the graph database to obtain an output result.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the intelligent question-answering method for nuclear power item data based on a graph database as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the intelligent question-answering method for nuclear power item data based on a graph database as described in any one of claims 1 to 7 are implemented.

Images