Railway domain map construction method and system

Abstract

The invention provides a railway domain graph construction method and system. The method comprises the steps that a railway construction energy consumption graph is constructed based on an ontology mode, a knowledge graph ontology model is constructed, and graph data is generated after the graph ontology model and an entity are mapped; constructing a graph based on a natural language algorithm mode, selecting a data set, creating a railway construction energy consumption control factor list, and constructing a construction energy-saving knowledge graph according to the control factor list; by systematically analyzing and integrating the railway construction energy consumption data and combining the natural language processing technology and the strict ontology construction process, the highly accurate, comprehensive and practical construction energy-saving knowledge graph can be constructed, and powerful data support and decision assistance are provided for the railway construction energy-saving field.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge graph construction, and in particular to a method and system for constructing a graph in the railway field. Background Art

[0002] As an important national infrastructure and a major artery of the national economy, railways play an irreplaceable and overall supporting role in social, economic and cultural development.

[0003] Energy conservation and carbon reduction in railway construction is an important part of the railway construction process, which directly affects the overall environmental protection effect. In the context of advocating green development, energy conservation and emission reduction, it occupies a very important position in the field of civil engineering. However, energy conservation and carbon reduction measures in engineering construction are often affected and restricted by multiple factors such as the natural conditions, technical factors and economic conditions of the region. For example, in complex mountainous areas, factors such as poor geology, sudden mud and water, climate differences, geographical location, and lack of infrastructure will greatly affect the implementation of energy conservation and carbon reduction measures, making it difficult to implement energy conservation and carbon reduction measures. The implementation of energy conservation and carbon reduction in railway construction is essentially to achieve a balance between engineering construction and control factors, and to obtain the optimal solution under all environmental protection, economic and construction period constraints. Therefore, the treatment of control factors directly affects the difficulty of implementing the construction plan, the construction cost of the project and the subsequent maintenance costs. This is also a difficult problem that needs to be solved in the energy conservation and carbon reduction work of railway construction.

[0004] However, the current problem of energy conservation and carbon reduction in railway construction is the inefficiency of manual data processing and low data quality and accuracy. The field of railway construction energy consumption involves a large amount of structured and unstructured data, and the data often has data quality and accuracy problems, such as incorrect labeling, missing information and inconsistent data formats. This leads to errors and incompleteness in the entities and relationships in the graph, affecting the accuracy of subsequent analysis and decision-making.

[0005] Therefore, there is an urgent need for a railway field graph construction method and system to solve the problems existing in the existing technology. Summary of the invention

[0006] The present invention provides a railway field map construction method and system, which are used to solve the defects of low efficiency, low data quality and accuracy in the prior art of manual data processing.

[0007] In one aspect, the present invention provides a method for constructing a railway field graph, comprising:

[0008] A method for constructing a railway field graph, characterized by comprising:

[0009] Based on the ontology method, the railway construction energy consumption map is constructed, the knowledge map ontology model is constructed, and the map ontology model is mapped with the entity to generate the map data, including:

[0010] S1, obtain railway construction energy consumption data, analyze data resources, divide them into structured data and heterogeneous data, and build a knowledge graph ontology model;

[0011] S2, based on the correspondence between the ontology model and the entities of the relational database, correspond the ontology model attributes and the database fields to obtain the data mapping relationship;

[0012] S3, based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph;

[0013] Build a graph based on natural language algorithm, select data sets, create a list of energy consumption control factors for railway construction, and build a construction energy-saving knowledge graph based on the list of control factors.

[0014] According to the railway field graph construction method provided by the present invention, the railway construction energy consumption data is obtained, the data resources are analyzed, divided into structured data and text data, and a knowledge graph ontology model is constructed, including:

[0015] Identify structured data in the mechanical energy consumption data that conforms to the constructed ontology data schema, and determine a first ontology according to the constructed ontology data schema and the structured data;

[0016] Extracting ontology data schema based on heterogeneous data in the mechanical energy consumption data that does not conform to the constructed ontology data schema, and determining a second ontology according to the extracted ontology data schema and the heterogeneous data;

[0017] The first ontology and the second ontology are merged to obtain a knowledge graph ontology model.

[0018] According to the railway field graph construction method provided by the present invention, the first ontology and the second ontology are merged to obtain a knowledge graph ontology model, including:

[0019] Based on the structure, concepts and relationships of the first ontology and the second ontology, the similarities and differences between the two are analyzed, the parts that need to be merged are determined, and the analysis results are generated;

[0020] Establish mapping rules based on the analysis results and perform matching;

[0021] During the mapping process, resolve naming conflicts, semantic inconsistencies, and ensure that the merged ontology is semantically and logically consistent;

[0022] According to the mapping rules, the concepts, attributes and relationships in the two ontologies are integrated to form a comprehensive ontology model. During the integration process, repeated concepts and relationships are screened, and normalized and standardized to obtain a knowledge graph ontology model.

[0023] Verify the merged ontology model to ensure that the merged knowledge graph ontology model meets the expected logical and semantic requirements.

[0024] According to the railway field graph construction method provided by the present invention, the correspondence between the ontology model and the entities of the relational database is based on the correspondence between the ontology model attributes and the database fields to obtain the data mapping relationship, including:

[0025] Analyze the concepts, attributes, and relationships in the ontology model, determine the attributes that need to be mapped to the relational database, and understand their data types and constraints;

[0026] Review the structure and table design of the target relational database to ensure that the database has appropriate entities and relationships to store the information in the ontology model;

[0027] Establish corresponding relationships based on the attributes of the ontology model and the fields of the relational database;

[0028] Perform data type matching, constraint matching, multi-valued attribute processing and relationship establishment on the relational database, organize the data mapping relationship into documents, and record the correspondence between the ontology model attributes and the relational database fields.

[0029] According to the railway field graph construction method provided by the present invention, based on the data mapping relationship, data is extracted into a graph database, graph data is generated and a data graph is obtained, including:

[0030] According to the data mapping relationship, the corresponding data is extracted from the relational database, and the format of the extracted data is converted;

[0031] Create nodes and edges in the graph database based on data mapping relationships;

[0032] Import the converted data into the graph database and create indexes for the nodes and edges in the graph database.

[0033] According to the railway field graph construction method provided by the present invention, the graph is constructed based on a natural language algorithm, a data set is selected, a list of railway construction energy consumption control factors is created, and a construction energy-saving knowledge graph is constructed according to the list of control factors, including:

[0034] Based on historical railway construction and machinery configuration experience, data related to railway machinery energy consumption are extracted as basic data for building a construction energy-saving knowledge graph to generate a data set;

[0035] Summarize the historical factors that affect railway construction efficiency and machinery configuration and their corresponding treatment measures, and form a list of railway construction energy consumption control factors;

[0036] Quantify the control factors and their disposal measures sorted out in the control factor list;

[0037] Parsing the data set using natural language processing technology to extract entities, attributes and relationships related to the control factor list;

[0038] Organize the extracted information into a structured construction energy-saving knowledge graph;

[0039] Users can query the construction energy-saving knowledge graph based on the list of railway construction energy consumption control factors to obtain guidance and suggestions related to railway construction and machinery configuration.

[0040] According to the railway field graph construction method provided by the present invention, the extracted information is organized into a structured energy-saving knowledge graph, including:

[0041] Coding the control factors on the list of control factors for railway construction energy consumption;

[0042] The quantitative values ​​of the treatment measures are dimensionless processed to construct a knowledge template of the control factors and their corresponding treatment measures;

[0043] The control factors, disposal measures and quantitative values ​​are classified into levels and entities are extracted therefrom. The relationships between entities are established based on the classified levels, and the control factor disposal domain knowledge ontology is constructed based on the knowledge template.

[0044] Set unique search terms for all control factors and treatment measures in the control factor treatment domain knowledge ontology, and construct a search term sequence list.

[0045] On the other hand, the present invention also provides a railway field atlas construction system, comprising:

[0046] Ontology construction module: construct railway construction energy consumption graph based on ontology, build knowledge graph ontology model, and generate graph data after mapping graph ontology model with entities;

[0047] Natural language construction module: Build a graph based on the natural language algorithm, select the data set, create a list of energy consumption control factors for railway construction, and build a construction energy-saving knowledge graph based on the list of control factors.

[0048] According to the railway domain graph construction system provided by the present invention, the ontology construction module includes:

[0049] Construction unit: obtain railway machinery energy consumption data, analyze data resources, and build a knowledge graph ontology model;

[0050] Mapping unit: Based on the correspondence between the ontology model and the entities of the relational database, the ontology model attributes and the database fields are matched to obtain the data mapping relationship;

[0051] Extraction unit: Based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph.

[0052] The present invention provides a method and system for constructing a railway field graph, the method comprising constructing a railway construction energy consumption graph based on an ontology, constructing a knowledge graph ontology model, mapping the graph ontology model with entities and generating graph data; constructing a graph based on a natural language algorithm, selecting a data set, creating a list of railway construction energy consumption control factors, and constructing a construction energy-saving knowledge graph based on the list of control factors;

[0053] The railway domain graph construction method has the following significant beneficial effects:

[0054] 1. Comprehensive and sophisticated data analysis and modeling: By distinguishing between structured data and heterogeneous (or unstructured) data, this method can analyze railway construction energy consumption data in more detail, ensuring that all types of data are fully utilized, thereby building a more complete and accurate knowledge graph ontology model.

[0055] 2. Flexible ontology model construction and integration: By identifying structured data that conforms to predefined ontology patterns and extracting new ontology patterns from heterogeneous data, this method can not only utilize the existing knowledge framework, but also expand and adapt to newly emerging data patterns, so that the knowledge graph can evolve dynamically and adapt to the development and changes of the railway industry.

[0056] 3. Efficient data mapping and graph generation: Based on the mapping mechanism between the ontology model and the relational database, this method can effectively convert data resources into graph data while ensuring the consistency and integrity of the data, facilitating subsequent query and analysis.

[0057] 4. Natural language processing enhanced graph construction: By combining natural language processing technology, this method can automatically parse text data, extract key information and build a knowledge graph, which greatly improves the degree of automation of data processing and reduces the need for human intervention.

[0058] 5. Strengthen decision-making support capabilities: By creating a list of energy consumption control factors for railway construction and a construction energy-saving knowledge map based on this list, this method can provide guidance and suggestions based on historical data for railway construction and machinery configuration, thereby improving the scientificity and efficiency of decision-making.

[0059] 6. Standardization and normalization: In the process of ontology model construction and data mapping, standardization and normalization are implemented to ensure the consistency and readability of the knowledge graph and facilitate sharing and interoperability across systems.

[0060] 7. Verifiability and reliability: Finally, by verifying the merged knowledge graph ontology model, its logical and semantic correctness is ensured, the reliability and effectiveness of the graph are enhanced, and a solid foundation is provided for knowledge management and application in the railway field.

[0061] In summary, this method can construct a highly accurate, comprehensive and practical knowledge graph by systematically analyzing and integrating railway construction energy consumption data, combining natural language processing technology and a strict ontology construction process, and provide strong data support and decision-making assistance for the railway industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 It is a flow chart of a method for constructing a railway field graph provided by an embodiment of the present invention;

[0064] Figure 2 It is a structural diagram of a railway field graph construction system provided by an embodiment of the present invention;

[0065] Figure 3 It is a flowchart of constructing a knowledge graph ontology model of a railway field graph construction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Figure 1 It is a flow chart of a method for constructing a railway field graph provided by an embodiment of the present invention.

[0068] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a railway field graph, and the method mainly includes the following steps:

[0069] 101. Construct the railway construction energy consumption map based on the ontology method, build the knowledge map ontology model, and generate the map data after mapping the map ontology model with the entity.

[0070] S1, obtain railway construction energy consumption data, analyze data resources, divide them into structured data and heterogeneous data, and build a knowledge graph ontology model;

[0071] S2, based on the correspondence between the ontology model and the entities of the relational database, correspond the ontology model attributes and the database fields to obtain the data mapping relationship;

[0072] S3, based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph;

[0073] Among them, Figure 3 As shown, railway machinery energy consumption data is obtained, data resources are analyzed, divided into structured data and heterogeneous data, and a knowledge graph ontology model is constructed, including: identifying structured data in the machinery energy consumption data that conforms to the constructed ontology data pattern, and determining a first ontology based on the constructed ontology data pattern and the structured data; extracting an ontology data pattern based on the heterogeneous data in the machinery energy consumption data that does not conform to the constructed ontology data pattern, and determining a second ontology based on the extracted ontology data pattern and the heterogeneous data; merging the first ontology and the second ontology to obtain a knowledge graph ontology model.

[0074] The first ontology is the initial version of the ontology determined based on the constructed ontology data schema and the structured data that matches it. The ontology model is created based on the existing knowledge structure and the data that has been identified and classified. The first ontology can be regarded as a preliminary representation of the existing knowledge and the starting point for building the knowledge graph.

[0075] The second ontology is determined by the new ontology data schema extracted from the mechanical energy consumption data that does not match the constructed ontology data schema. In other words, the second ontology is an ontology model created based on data that cannot be described by the existing ontology data schema, that is, representing text data.

[0076] This means that the second ontology can capture domain knowledge or concepts that cannot be represented by the first ontology. By analyzing and mining heterogeneous data, new concepts, relationships, and attributes can be discovered, thereby enriching and expanding the original ontology model.

[0077] After merging the first ontology and the second ontology, a more complete and comprehensive knowledge graph ontology model is obtained, which contains descriptions of various concepts, relationships and attributes obtained from structured data and heterogeneous data. This comprehensive ontology model can be used to more comprehensively understand and represent knowledge in related fields.

[0078] Merging the first ontology and the second ontology to obtain a knowledge graph ontology model includes: understanding the structures, concepts and relationships of the first and second ontologies in detail, determining the similarities and differences between them, and the parts that need to be merged; establishing mapping rules to match them by identifying the common concepts and relationships in the two ontologies; in the mapping process, resolving naming conflicts and semantic inconsistencies, and ensuring that the merged ontology is semantically and logically consistent; integrating the concepts, attributes and relationships in the two ontologies according to the mapping rules to form a comprehensive ontology model, screening duplicate concepts and relationships during the integration process, and normalizing and standardizing them to obtain a knowledge graph ontology model; verifying the merged ontology model to ensure that the merged knowledge graph ontology model meets the expected logical and semantic requirements.

[0079] Based on the correspondence between the ontology model and the entities in the relational database, the ontology model attributes and database fields are matched to obtain the data mapping relationship, including: analyzing the concepts, attributes and relationships in the ontology model, determining the attributes that need to be mapped to the relational database, and understanding their data types and constraints; reviewing the structure and table design of the target relational database so that there are appropriate entities and relationships in the database to store the information in the ontology model; establishing a correspondence based on the attributes of the ontology model and the fields of the relational database; matching data types, constraints, multi-valued attributes and establishing relationships for the relational database, organizing the data mapping relationship into a document, and recording the correspondence between the ontology model attributes and the relational database fields.

[0080] Among them, data type matching refers to ensuring that the data types of attributes and fields match between the ontology model and the relational database. For example, mapping the text attribute in the ontology model to the character field in the relational database.

[0081] Constraint matching means that if the ontology model defines constraints on attributes (such as minimum value, maximum value, uniqueness, etc.), ensure that the corresponding fields in the relational database also have corresponding constraints.

[0082] Multi-valued attribute processing means that if the attributes in the ontology model allow multiple values, but the table structure in the relational database cannot directly represent the multi-valued attributes, you can consider using additional tables or split fields to store the multi-valued attributes.

[0083] Relationship establishment means that if there are relationships in the ontology model, corresponding tables and foreign key constraints need to be established in the relational database to represent these relationships.

[0084] Based on the data mapping relationship, the data is extracted into the graph database to generate graph data and obtain a data graph, including: according to the data mapping relationship, the corresponding data is extracted from the relational database, and the format of the extracted data is converted to conform to the data model of the graph database; according to the data mapping relationship, the nodes and edges in the graph database are created to construct the basic structure of the data graph; the converted data is imported into the graph database, and the nodes and edges in the graph database are indexed to speed up the indexing speed.

[0085] Among them, according to the data mapping relationship, the corresponding data is extracted from the relational database. By identifying and understanding the relationships and dependencies between the data, the data related to the graph database in the relational database is selectively extracted. The extracted data is formatted to conform to the data model of the graph database. Due to the different data models between the relational database and the graph database, the extracted data needs to be properly converted and adjusted so that it can conform to the data model (such as nodes and edges) adopted by the graph database. According to the data mapping relationship, the nodes and edges in the graph database are created to build the basic structure of the data map. According to the extracted data and the defined data mapping relationship, the corresponding nodes and edges are created in the graph database. Nodes represent entities or concepts, and edges represent the relationship or connection between entities. The converted data is imported into the graph database. The format-converted data is loaded into the graph database to create a data map. This involves inserting the information of nodes and edges into the corresponding data structure of the graph database.

[0086] Indexing nodes and edges in the graph database can speed up indexing. In order to improve the retrieval efficiency of the data graph, you can index the nodes and edges in the graph database. Indexing can quickly locate and access related nodes and edges based on specific attributes or labels, speeding up data query and navigation operations.

[0087] 102. Build a graph based on natural language algorithm, select data sets, create a list of energy consumption control factors for railway construction, and build a construction energy-saving knowledge graph based on the list of control factors.

[0088] Based on the natural language algorithm, a graph is constructed, a data set is selected, a list of control factors for railway construction energy consumption is created, and a construction energy-saving knowledge graph is constructed based on the list of control factors, including:

[0089] Based on historical railway construction and machinery configuration experience, data related to railway machinery energy consumption is extracted as the basic data for building a knowledge graph and generating a data set;

[0090] Summarize the historical factors that affect railway construction efficiency and machinery configuration and their corresponding treatment measures, and form a list of railway construction energy consumption control factors;

[0091] Quantify the control factors and their disposal measures sorted out in the control factor list;

[0092] Analyzing the data set using natural language processing technology to extract entities, attributes and relationships related to the list of railway construction energy consumption control factors;

[0093] Organize the extracted information into a structured knowledge graph;

[0094] Users can query the construction energy-saving knowledge graph based on the list of railway construction energy consumption control factors to obtain guidance and suggestions related to railway construction and machinery configuration.

[0095] Among them, historical construction and machinery configuration experience is used to assist in the analysis of railway machinery energy consumption data. Historical construction and machinery configuration experience can include previous machinery planning and optimization results, as well as expert knowledge in related fields. These experiences can help us better understand the patterns and trends in railway machinery energy consumption data and provide targeted suggestions and decision support.

[0096] According to the list of railway construction energy consumption control factors, a construction energy-saving knowledge map is constructed, including:

[0097] The control factors on the list of railway construction energy consumption control factors are encoded; the quantitative values ​​of the disposal measures are dimensionless, and a knowledge template of the control factors and their corresponding disposal measures is constructed; the control factors, disposal measures and quantitative values ​​are graded and entities are extracted from them, the relationship between the entities is established based on the graded levels, and a control factor disposal domain knowledge ontology is constructed based on the knowledge template; unique search terms are set for all control factors and disposal measures in the control factor disposal domain knowledge ontology, and a search term sequence list is constructed.

[0098] Among them, coding the control factors on the list of railway construction energy consumption control factors is to convert these factors into a unified identification or number to facilitate processing and management in the system. The purpose of coding is to more conveniently represent and reference control factors, as well as to achieve their classification, association and query.

[0099] Based on the same general inventive concept, the present invention also protects a railway field map construction system. The railway field map construction system provided by the present invention is described below. The railway field map construction system described below and the railway field map construction method described above can be referenced to each other.

[0100] like Figure 2As shown, an embodiment of the present invention provides a railway field graph construction system, the system mainly includes the following modules:

[0101] Ontology construction module: construct railway construction energy consumption graph based on ontology, build knowledge graph ontology model, and generate graph data after mapping graph ontology model with entities;

[0102] Natural language construction module: Build a graph based on the natural language algorithm, select the data set, create a list of control factors for railway construction energy consumption, and build a knowledge graph based on the list of control factors.

[0103] Among them, the ontology building module includes:

[0104] Construction unit: obtain railway machinery energy consumption data, analyze data resources, and build a knowledge graph ontology model;

[0105] Mapping unit: Based on the correspondence between the ontology model and the entities of the relational database, the ontology model attributes and the database fields are matched to obtain the data mapping relationship;

[0106] Extraction unit: Based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph.

[0107] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a railway domain graph, characterized in that: include: Based on the ontology method, the railway construction energy consumption map is constructed, the knowledge map ontology model is constructed, and the map ontology model is mapped with the entity to generate the map data, including: S1, obtain railway construction energy consumption data, analyze data resources, divide them into structured data and heterogeneous data, and build a knowledge graph ontology model; S2, based on the correspondence between the ontology model and the entities of the relational database, correspond the ontology model attributes and the database fields to obtain the data mapping relationship; S3, based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph; Build a graph based on natural language algorithm, select data sets, create a list of energy consumption control factors for railway construction, and build a construction energy-saving knowledge graph based on the list of control factors.

2. The railway field graph construction method according to claim 1, characterized in that: The method of obtaining railway construction energy consumption data, analyzing data resources, dividing them into structured data and text data, and constructing a knowledge graph ontology model includes: Identify structured data in the mechanical energy consumption data that conforms to the constructed ontology data schema, and determine a first ontology according to the constructed ontology data schema and the structured data; Extracting ontology data schema based on heterogeneous data in the mechanical energy consumption data that does not conform to the constructed ontology data schema, and determining a second ontology according to the extracted ontology data schema and the heterogeneous data; The first ontology and the second ontology are merged to obtain a knowledge graph ontology model.

3. The railway field graph construction method according to claim 2, characterized in that: The merging of the first ontology and the second ontology to obtain a knowledge graph ontology model includes: Based on the structure, concepts and relationships of the first ontology and the second ontology, the similarities and differences between the two are analyzed, the parts that need to be merged are determined, and the analysis results are generated; Establish mapping rules based on the analysis results and perform matching; During the mapping process, resolve naming conflicts, semantic inconsistencies, and ensure that the merged ontology is semantically and logically consistent; According to the mapping rules, the concepts, attributes and relationships in the two ontologies are integrated to form a comprehensive ontology model. During the integration process, repeated concepts and relationships are screened and normalized to obtain a knowledge graph ontology model. Verify the merged ontology model to ensure that the merged knowledge graph ontology model meets the expected logical and semantic requirements.

4. The railway field graph construction method according to claim 1, characterized in that: Based on the correspondence between the ontology model and the entities of the relational database, the ontology model attributes and the database fields are corresponded to obtain the data mapping relationship, including: Analyze the concepts, attributes, and relationships in the ontology model, determine the attributes that need to be mapped to the relational database, and understand their data types and constraints; Review the structure and table design of the target relational database to ensure that the database has appropriate entities and relationships to store the information in the ontology model; Establish corresponding relationships based on the attributes of the ontology model and the fields of the relational database; Perform data type matching, constraint matching, multi-valued attribute processing and relationship establishment on the relational database, organize the data mapping relationship into documents, and record the correspondence between the ontology model attributes and the relational database fields.

5. The railway field graph construction method according to claim 1, characterized in that: Based on the data mapping relationship, the data is extracted into the graph database, the graph data is generated and the data graph is obtained, including: According to the data mapping relationship, the corresponding data is extracted from the relational database, and the format of the extracted data is converted; Create nodes and edges in the graph database based on data mapping relationships; Import the converted data into the graph database and create indexes for the nodes and edges in the graph database.

6. The railway field graph construction method according to claim 1, characterized in that: The method of constructing a graph based on a natural language algorithm, selecting a data set, creating a list of control factors for railway construction energy consumption, and constructing a construction energy-saving knowledge graph based on the list of control factors includes: Based on historical railway construction and machinery configuration experience, data related to railway machinery energy consumption are extracted as basic data for building a construction energy-saving knowledge graph to generate a data set; Summarize the historical factors that affect railway construction efficiency and machinery configuration and their corresponding treatment measures, and form a list of railway construction energy consumption control factors; Quantify the control factors and their disposal measures sorted out in the control factor list; Parsing the data set using natural language processing technology to extract entities, attributes and relationships related to the control factor list; Organize the extracted information into a structured construction energy-saving knowledge graph; Users can query the construction energy-saving knowledge graph based on the list of railway construction energy consumption control factors to obtain guidance and suggestions related to railway construction and machinery configuration.

7. The railway field graph construction method according to claim 6, characterized in that: The extracted information is organized into a structured construction energy-saving knowledge graph, including: Coding the control factors on the list of control factors for railway construction energy consumption; The quantitative values ​​of the treatment measures are dimensionless processed to construct a knowledge template of the control factors and their corresponding treatment measures; The control factors, disposal measures and quantitative values ​​are classified into levels and entities are extracted therefrom. The relationship between entities is established based on the classified levels, and the control factor disposal domain knowledge ontology is constructed based on the knowledge template. Set unique search terms for all control factors and treatment measures in the control factor treatment domain knowledge ontology, and construct a search term sequence list.

8. A railway field graph construction system, characterized in that: include: Ontology construction module: construct railway construction energy consumption graph based on ontology, build knowledge graph ontology model, and generate graph data after mapping graph ontology model with entities; Natural language construction module: Build a graph based on the natural language algorithm, select the data set, create a list of energy consumption control factors for railway construction, and build a construction energy-saving knowledge graph based on the list of control factors.

9. The railway domain graph construction system according to claim 8, characterized in that: The ontology building module comprises: Construction unit: obtain railway machinery energy consumption data, analyze data resources, and build a knowledge graph ontology model; Mapping unit: Based on the correspondence between the ontology model and the entities of the relational database, the ontology model attributes and the database fields are matched to obtain the data mapping relationship; Extraction unit: Based on the data mapping relationship, extract the data into the graph database, generate graph data and obtain the data graph.

Images