Railway domain knowledge graph construction method and device

Abstract

The invention discloses a railway field knowledge graph construction method and device, and the method comprises the steps: obtaining a railway field knowledge text, carrying out the preprocessing of the railway field knowledge text, selecting railway knowledge from the preprocessed railway field knowledge text, screening out a railway knowledge entity, analyzing the features of the railway knowledge entity, and carrying out the construction of a railway field knowledge graph. A railway knowledge entity recognition model is constructed and trained based on railway knowledge entities and features thereof, the railway knowledge entities in a railway domain knowledge base are recognized through the model, and the relation of the corresponding railway knowledge entities is extracted and recognized from a railway domain knowledge text. The identified railway knowledge entities and the relations thereof are expressed by triads, the triads are fused and stored in a graph database, and a railway domain knowledge graph is constructed; according to the method, the processing and management efficiency of the railway field knowledge can be improved, automatic railway knowledge entity recognition and relation extraction are realized, a structured railway field knowledge graph is constructed, and powerful support is provided for application and decision-making of the railway field.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and device for constructing a knowledge graph in the railway field. Background Art

[0002] With the explosive growth of Internet data, a large amount of railway knowledge data has been generated. However, how to manage and store this data and facilitate the retrieval of knowledge data is an important issue. One way to solve the existing problem is to build a knowledge graph in the railway field. The construction of the railway knowledge graph is based on the technical practice of knowledge graph and graph database. The knowledge graph is a knowledge representation method that represents and stores entities, attributes and relationships in the form of a graph. In addition, in the railway field, the construction of the knowledge graph has important practical significance. By building a knowledge graph in the railway field, these entities and relationships can be represented and managed in a structured way, thereby supporting more efficient and accurate knowledge query, reasoning and application. Therefore, how to build a railway knowledge graph is the main problem that needs to be solved at present. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a method and device for constructing a knowledge graph in the railway field, including:

[0004] Acquire railway domain knowledge text, and preprocess the railway domain knowledge text;

[0005] Selecting railway knowledge from the preprocessed railway domain knowledge text, and screening railway knowledge entities from the railway knowledge;

[0006] Analyze the characteristics of the railway knowledge entity, and construct and train a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics;

[0007] The railway knowledge entities in the railway domain knowledge base are identified through the trained railway knowledge entity recognition model;

[0008] Extracting and identifying the relationship between corresponding railway knowledge entities from the railway domain knowledge text, and representing the identified railway knowledge entities and their relationships with triples;

[0009] The triples are integrated and saved into a graph database to construct a railway domain knowledge graph.

[0010] Furthermore, the obtaining of railway domain knowledge text and preprocessing of the railway domain knowledge text include:

[0011] Acquire railway domain knowledge data on the Internet, and process the railway domain knowledge data into a text form of pure text by a multimodal data processing method to obtain railway domain knowledge text;

[0012] The railway domain knowledge text is preprocessed, and the preprocessing includes word segmentation, stop word removal, part-of-speech tagging and syntactic analysis.

[0013] Furthermore, the selecting of railway knowledge from the preprocessed railway domain knowledge text and screening out railway knowledge entities from the railway knowledge includes:

[0014] Divide the preprocessed railway domain knowledge text into multiple sentences, and select noun phrases, verbs, and verb phrases from the sentences as candidate terms;

[0015] Using the railway field keyword list to perform keyword matching on each of the candidate terms, selecting candidate terms that reach a preset matching degree, and locating the sentences where the candidate terms that reach the preset matching degree are located, and using them as railway knowledge;

[0016] Railway experts in the field of railways score and evaluate the characters, words and phrases in the railway knowledge, and filter out the characters, words and phrases with evaluation scores exceeding the preset scores to obtain railway knowledge entities.

[0017] Furthermore, the analyzing the characteristics of the railway knowledge entity, and constructing and training a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics, includes:

[0018] Acquire the multidimensional features of the railway knowledge entity, evaluate and analyze the multidimensional features, and select the features that meet the requirements;

[0019] Constructing a railway knowledge entity recognition model based on the railway knowledge entity and its characteristics;

[0020] The railway knowledge entity and its characteristics are used as model training data to train the railway knowledge entity recognition model until the railway knowledge entity recognition model meets preset requirements.

[0021] Furthermore, the extraction and identification of the relationship between corresponding railway knowledge entities from the railway domain knowledge text, and the identification of railway knowledge entities and their relationship represented by triples, include:

[0022] Calculating the cosine similarity between two railway knowledge entities in sequence, and selecting two railway knowledge entities whose cosine similarity is greater than a preset value for matching as entity pairs;

[0023] Calculating the distance between the two railway knowledge entities in the entity pair, and selecting entity pairs whose distance between the two railway knowledge entities is within a preset range;

[0024] Taking the entity pair as the cluster center, calculating the cosine similarity between each verb or verb phrase around the entity pair and the cluster center;

[0025] According to the cosine similarity, each verb or verb phrase is merged with the cluster center, and a new cluster center is recalculated;

[0026] Calculating the difference between the new cluster center and the cluster center, taking the verbs or verb phrases whose difference is less than a preset difference threshold as extraction results, and obtaining the relationship between railway knowledge entities;

[0027] The identified railway knowledge entities and their relationships are represented by triples.

[0028] Furthermore, the identified railway knowledge entities and their relationships are represented by triples, including:

[0029] The identified railway knowledge entities and their relationships are matched with each other, and after successful matching, multiple triples are formed in the form of subject-predicate-object.

[0030] Furthermore, the fusion and storage of the triples into a graph database to construct a railway field knowledge graph includes:

[0031] Analyze the quantity scale of the railway knowledge entities and their relationships, and select the type of graph database according to the quantity scale of the railway knowledge entities and their relationships;

[0032] In the graph database, the railway knowledge entities are used as nodes, and the relationships between the railway knowledge entities are used as edges to construct a graph model of the graph database;

[0033] The triples are fused according to the graph pattern and saved into the graph database to construct a knowledge graph in the railway field.

[0034] The present invention also provides a railway field knowledge graph construction device, comprising:

[0035] An acquisition module, used to acquire railway domain knowledge text and preprocess the railway domain knowledge text;

[0036] A screening module is used to select railway knowledge from the preprocessed railway domain knowledge text and screen out railway knowledge entities from the railway knowledge;

[0037] A modeling module, used for analyzing the characteristics of the railway knowledge entity, and constructing and training a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics;

[0038] A recognition module is used to recognize railway knowledge entities in a railway domain knowledge base through a trained railway knowledge entity recognition model;

[0039] An extraction module is used to extract and identify the relationship of corresponding railway knowledge entities from the railway domain knowledge text, and represent the identified railway knowledge entities and their relationships as triples;

[0040] A construction module is used to merge and save the triples into a graph database to construct a knowledge graph in the railway field.

[0041] Compared with the prior art, the method and device for constructing a railway knowledge graph in the embodiment of the present invention have the following beneficial effects:

[0042] The present invention can clean and standardize text data by preprocessing railway field knowledge text, thereby improving the accuracy of subsequent entity recognition and relationship extraction;

[0043] The present invention can automatically identify entities in the railway field by training a railway knowledge entity recognition model, thereby reducing the workload of manual labeling and improving the efficiency and accuracy of entity recognition;

[0044] By analyzing the characteristics of railway knowledge entities, the present invention can understand the types and attribute characteristics of entities, providing a basis for subsequent knowledge graph construction and application;

[0045] The present invention uses the relationship extraction technology to extract the relationship between entities from the railway knowledge text, help establish the connection between entities, and form the edge of the knowledge graph;

[0046] The present invention represents the extracted railway knowledge entities and relationships in the form of triples and saves them in a graph database, which can construct a knowledge graph in the railway field to provide efficient storage and query capabilities and support complex knowledge graph query and reasoning;

[0047] In summary, the present invention can improve the processing and management efficiency of railway knowledge, realize automated railway knowledge entity recognition and relationship extraction, construct a structured railway knowledge graph, and provide strong support for railway applications and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the process structure of the method for constructing a knowledge graph in the railway field in an embodiment of the present invention;

[0049] Figure 2 It is a schematic diagram of the composition of the railway field knowledge graph construction device in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0051] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0052] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0053] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0054] like Figure 1 As shown, in an embodiment of the present application, a method for constructing a railway domain knowledge graph is provided, including: S100: obtaining a railway domain knowledge text and preprocessing the railway domain knowledge text; S200: selecting railway knowledge from the preprocessed railway domain knowledge text, and screening out railway knowledge entities from the railway knowledge; S300: analyzing the characteristics of the railway knowledge entities, and constructing and training a railway knowledge entity recognition model based on the railway knowledge entities and the characteristics; S400: identifying railway knowledge entities in a railway domain knowledge base through the trained railway knowledge entity recognition model; S500: extracting and identifying the relationships of corresponding railway knowledge entities from the railway domain knowledge text, and representing the identified railway knowledge entities and their relationships with triples; S600: fusing and saving the triples into a graph database to construct a railway domain knowledge graph.

[0055] Specifically, knowledge texts in the railway field are collected from various sources (such as railway official websites, railway regulations, news reports, etc.); the acquired railway field knowledge texts are preprocessed, including word segmentation, stop word removal, part-of-speech tagging and syntactic analysis, so as to facilitate subsequent entity recognition and relationship extraction; from the preprocessed railway field knowledge texts, according to the characteristics and needs of the domain knowledge, the knowledge related to the railway is selected, and the railway knowledge texts are subjected to entity recognition to identify the railway knowledge entities; the identified railway knowledge entities are subjected to feature analysis to facilitate the subsequent construction and training of entity recognition models; based on the features of the railway knowledge entities, the An entity recognition model is constructed using machine learning or deep learning methods, and the preprocessed railway domain knowledge text is used for model training. The trained railway knowledge entity recognition model is used to perform entity recognition on the text in the railway domain knowledge base to identify the railway knowledge entities in the text. Based on the identified railway knowledge entities, a relationship extraction method is used to extract the relationship between entities from the preprocessed railway domain knowledge text, and represent it in the form of triples. The extracted triple information is fused and saved in a graph database to construct a knowledge graph in the railway field. A suitable graph database (such as Neo4j, Amazon Neptune, etc.) is selected, and the triple data is imported into the graph database to support knowledge storage, query, and reasoning.

[0056] Furthermore, the present invention can improve the processing and management efficiency of railway knowledge, realize automated railway knowledge entity recognition and relationship extraction, construct a structured railway knowledge graph, and provide strong support for railway applications and decision-making.

[0057] In an embodiment of the present application, a method for constructing a railway domain knowledge graph is provided, wherein the obtaining of railway domain knowledge text and preprocessing of the railway domain knowledge text include: obtaining railway domain knowledge data on the Internet, processing the railway domain knowledge data into a pure text form through a multimodal data processing method, and obtaining railway domain knowledge text; and preprocessing the railway domain knowledge text, wherein the preprocessing includes word segmentation, removal of stop words, part-of-speech tagging, and syntactic analysis.

[0058] Specifically, a web crawler program is written to capture knowledge data in the railway field according to relevant websites or data sources in the railway field. Libraries in the Python programming language, such as Beautiful Soup or Scrapy, can be used to implement the web crawler function. If the captured knowledge data in the railway field contains multiple media types (such as text, images, audio, video, etc.), it needs to be processed into a text form of pure text. For image, audio, and video data, corresponding processing methods, such as image recognition and audio-to-text technology, can be used to convert them into text form. The preprocessing of the obtained railway field knowledge text includes the following steps: Word segmentation: The text is segmented into a sequence of words. Chinese word segmentation tools such as jieba or English word segmentation tools such as NLTK or spaCy can be used. Stop word removal: Common words without practical meaning, such as "de", "le", "shi", etc., are removed. A predefined stop word list or a custom stop word list according to the characteristics of the specific field can be used. Part-of-speech tagging: A part-of-speech tag is added to each word. Part-of-speech tagging tools such as NLTK or spaCy can be used to associate each word with its corresponding part of speech. Syntactic analysis: Syntactic analysis is performed on the text to analyze the structure of the sentence and the relationship between components. Syntactic analysis tools such as Stanford Parser or spaCy can be used to generate a syntactic tree or a dependency graph.

[0059] In an embodiment of the present application, a method for constructing a railway field knowledge graph is provided. Selecting railway knowledge from the preprocessed railway field knowledge text and screening out railway knowledge entities from the railway knowledge includes: dividing the preprocessed railway field knowledge text into multiple sentences, and selecting noun phrases, verbs, and verb phrases from the sentences as candidate terms; using a railway field keyword list to perform keyword matching on each candidate term, selecting the candidate terms that reach the preset matching degree, and locating the sentences where the candidate terms that reach the preset matching degree are located, and taking them as railway knowledge; scoring and evaluating the characters, words, and phrases in the railway knowledge by railway field experts, and screening out the characters, words, and phrases whose evaluation scores exceed the preset score to obtain railway knowledge entities.

[0060] Specifically, sentence segmentation tools (such as NLTK or spaCy) are used to divide the preprocessed railway domain knowledge text into multiple sentences; from each sentence, noun phrases, verbs and verb phrases are selected as candidate terms, and part-of-speech tagging tools (such as NLTK or spaCy) can be used to annotate the part of speech of each word, and candidate terms are selected according to predefined part-of-speech rules; a keyword list in the railway field is used to perform keyword matching on each candidate term, and a string matching algorithm (such as regular expressions or algorithms based on string similarity) can be used to match the candidate terms with the keyword list; according to a preset matching threshold, candidate terms with a preset matching degree are selected, and they can be screened according to the matching degree calculation method and threshold; the sentences containing the candidate terms with the preset matching degree are regarded as railway knowledge, and the location information of the sentences is recorded for subsequent evaluation and screening; the characters, words and phrases in the railway knowledge are scored and evaluated by railway experts, and the scoring criteria and preset scores are defined, and the characters, words and phrases with evaluation scores exceeding the preset scores are screened out according to the expert scoring results.

[0061] In an embodiment of the present application, a method for constructing a knowledge graph in the railway field is provided, wherein the characteristics of the railway knowledge entity are analyzed, and a railway knowledge entity recognition model is constructed and trained based on the railway knowledge entity and the characteristics, including: obtaining multidimensional characteristics of the railway knowledge entity, and evaluating and analyzing the multidimensional characteristics to screen out characteristics that meet the requirements; constructing a railway knowledge entity recognition model based on the railway knowledge entity and its characteristics; and using the railway knowledge entity and its characteristics as model training data to train the railway knowledge entity recognition model until the railway knowledge entity recognition model meets preset requirements.

[0062] Specifically, for each railway knowledge entity, multidimensional features are extracted from the text, which may include lexical features (such as word frequency, part of speech), syntactic features (such as syntactic tree structure, dependency relationship), contextual features (such as context words, sentence position), semantic features (such as word vector representation), etc.; the obtained multidimensional features are evaluated and analyzed, and statistical methods, machine learning methods or the knowledge of domain experts can be used to evaluate the importance and discrimination of each feature. According to the evaluation results, the features that meet the requirements are screened out for subsequent model construction; a suitable machine learning algorithm (such as support vector machine, random forest, deep learning model, etc.) is selected to construct a railway knowledge entity recognition model, and a suitable model architecture and parameter settings are designed according to the selected algorithm; the obtained railway knowledge entities and their features are used as training data to train the railway knowledge entity recognition model, and the training data includes labeled railway knowledge entity samples and corresponding features. Through an iterative training process, the model parameters are continuously adjusted until the model meets the preset requirements.

[0063] In an embodiment of the present application, a method for constructing a railway domain knowledge graph is provided, wherein the method extracts and identifies the relationship between corresponding railway knowledge entities from the railway domain knowledge text, and represents the identified railway knowledge entities and their relationship with triples, including: calculating the cosine similarity between two railway knowledge entities in turn, and selecting two railway knowledge entities whose cosine similarity is greater than a preset value for matching as entity pairs; calculating the distance between two railway knowledge entities in the entity pair, and screening out entity pairs whose distance between the two railway knowledge entities is within a preset range; using the entity pair as a clustering center, calculating the cosine similarity between each verb or verb phrase around the entity pair and the clustering center; merging each verb or verb phrase with the clustering center according to the cosine similarity, and recalculating a new clustering center; calculating the difference between the new clustering center and the clustering center, and taking the verb or verb phrase whose difference is less than a preset difference threshold as the extraction result to obtain the relationship between the railway knowledge entities; and representing the identified railway knowledge entities and their relationship with triples.

[0064] Specifically, for each pair of railway knowledge entities, the cosine similarity between them is calculated. Word vector representation (such as Word2Vec, G loVe, etc.) can be used to represent the entities, and then the cosine similarity between them is calculated; entity pairs with cosine similarity greater than a preset value are screened out as matching entity pairs; the distance between two entities in the selected entity pairs is calculated, and entity pairs with distances within a preset range are screened out; the selected entity pairs are used as cluster centers, and the cosine similarity between each verb or verb phrase and the cluster center is calculated; based on the cosine similarity, the verbs or verb phrases with similarities higher than a preset threshold are merged with the cluster center, and a new cluster center is recalculated; the difference between the new cluster center and the original cluster center is calculated, and the verbs or verb phrases with a difference less than a preset difference threshold are used as extraction results to represent the relationship between the railway knowledge entities; the identified railway knowledge entities and relationships are represented as triples, in which the subject is an entity, the predicate is a verb or verb phrase representing the relationship, and the object is another entity.

[0065] In an embodiment of the present application, a method for constructing a knowledge graph in the railway field is provided, wherein the identified railway knowledge entities and their relationships are represented by triples, including: matching the identified railway knowledge entities and their relationships with each other, and forming multiple triples in the form of subject-predicate-object after successful matching.

[0066] In an embodiment of the present application, a method for constructing a railway domain knowledge graph is provided, wherein the fusion and storage of the triples into a graph database to construct a railway domain knowledge graph comprises: analyzing the quantity scale of the railway knowledge entities and their relationships, and selecting the type of graph database according to the quantity scale of the railway knowledge entities and their relationships; in the graph database, taking the railway knowledge entities as nodes and the relationships between the railway knowledge entities as edges to construct a graph pattern of the graph database; and fusing the triples according to the graph pattern and storing them into the graph database to construct a railway domain knowledge graph.

[0067] Specifically, the number and scale of railway knowledge entities and their relationships can be analyzed by counting the number of entities and relationships in the preprocessed text, so as to select a suitable graph database type, such as Neo4j, JanusGraph, etc., and a graph computing engine, such as Apache G i raph, Apache F link, etc.; in the selected graph database, define the graph mode, which specifies the types of entities and relationships and the connection methods between them. According to the knowledge structure and relationships in the railway field, design a suitable graph mode. For example, the entity types can be defined as "railway station", "railway line", etc., and the relationship types can be defined as "connection", "passing", etc.; according to the graph mode, the previously extracted triples are fused and stored in the selected graph database, with railway knowledge entities as nodes and the relationships between railway knowledge entities as edges, to build a graph of the graph database. Each entity and relationship has appropriate attributes and identifiers, which can be queried and analyzed in the graph database; by fusing and storing triples, you will build a knowledge graph in the railway field, providing a structured and queryable knowledge base for storing and retrieving knowledge in the railway field.

[0068] like Figure 2 As shown, in an embodiment of the present application, a railway domain knowledge graph construction device is provided, including: an acquisition module, used to acquire railway domain knowledge text and preprocess the railway domain knowledge text; a screening module, used to select railway knowledge from the preprocessed railway domain knowledge text, and screen out railway knowledge entities from the railway knowledge; a modeling module, used to analyze the characteristics of the railway knowledge entity, and construct and train a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics; an identification module, used to identify the railway knowledge entities in the railway domain knowledge base through the trained railway knowledge entity recognition model; an extraction module, used to extract and identify the relationship between the corresponding railway knowledge entities from the railway domain knowledge text, and represent the identified railway knowledge entities and their relationships with triples; a construction module, used to merge and save the triples into a graph database to construct a railway domain knowledge graph.

[0069] In summary, the embodiment of the present invention provides a method and device for constructing a railway field knowledge graph, which includes: obtaining railway field knowledge text, preprocessing it, selecting railway knowledge from the preprocessed railway field knowledge text, and screening out railway knowledge entities, analyzing the characteristics of the railway knowledge entities, constructing and training a railway knowledge entity recognition model based on the railway knowledge entities and their characteristics, identifying railway knowledge entities in the railway field knowledge base through the model, extracting and identifying the relationships of the corresponding railway knowledge entities from the railway field knowledge text, and representing the identified railway knowledge entities and their relationships with triples, fusing and saving the triples to a graph database, and constructing a railway field knowledge graph; the present invention can improve the processing and management efficiency of railway field knowledge, realize automated railway knowledge entity recognition and relationship extraction, construct a structured railway field knowledge graph, and provide strong support for applications and decision-making in the railway field.

[0070] Finally, it should be noted that it is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0071] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0072] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0073] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for constructing a knowledge graph in the railway field, characterized in that: include: Acquire railway domain knowledge text, and preprocess the railway domain knowledge text; Selecting railway knowledge from the preprocessed railway domain knowledge text, and screening railway knowledge entities from the railway knowledge; Analyze the characteristics of the railway knowledge entity, and construct and train a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics; The railway knowledge entities in the railway domain knowledge base are identified through the trained railway knowledge entity recognition model; Extracting and identifying the relationship between corresponding railway knowledge entities from the railway domain knowledge text, and representing the identified railway knowledge entities and their relationships with triples; The triples are integrated and saved into a graph database to construct a railway domain knowledge graph.

2. A method for constructing a railway domain knowledge graph according to claim 1, characterized in that: The obtaining of railway domain knowledge text and preprocessing of the railway domain knowledge text include: Acquire railway domain knowledge data on the Internet, and process the railway domain knowledge data into a text form of pure text by a multimodal data processing method to obtain railway domain knowledge text; The railway domain knowledge text is preprocessed, and the preprocessing includes word segmentation, stop word removal, part-of-speech tagging and syntactic analysis.

3. A method for constructing a railway domain knowledge graph according to claim 1, characterized in that: The selecting railway knowledge from the preprocessed railway domain knowledge text and screening out railway knowledge entities from the railway knowledge includes: Divide the preprocessed railway domain knowledge text into multiple sentences, and select noun phrases, verbs, and verb phrases from the sentences as candidate terms; Using the railway field keyword list to perform keyword matching on each of the candidate terms, selecting candidate terms that reach a preset matching degree, and locating the sentences where the candidate terms that reach the preset matching degree are located, and using them as railway knowledge; Railway experts in the field of railways score and evaluate the characters, words and phrases in the railway knowledge, and filter out the characters, words and phrases with evaluation scores exceeding the preset scores to obtain railway knowledge entities.

4. A method for constructing a railway domain knowledge graph according to claim 1, characterized in that: The analyzing the characteristics of the railway knowledge entity and constructing and training a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics includes: Acquire the multidimensional features of the railway knowledge entity, evaluate and analyze the multidimensional features, and select the features that meet the requirements; Constructing a railway knowledge entity recognition model based on the railway knowledge entity and its characteristics; The railway knowledge entity and its characteristics are used as model training data to train the railway knowledge entity recognition model until the railway knowledge entity recognition model meets preset requirements.

5. A method for constructing a railway domain knowledge graph according to claim 1, characterized in that: The extracting and identifying the relationship of the corresponding railway knowledge entity from the railway domain knowledge text, and representing the identified railway knowledge entity and its relationship with a triple, includes: Calculating the cosine similarity between two railway knowledge entities in sequence, and selecting two railway knowledge entities whose cosine similarity is greater than a preset value for matching as entity pairs; Calculating the distance between the two railway knowledge entities in the entity pair, and selecting entity pairs whose distance between the two railway knowledge entities is within a preset range; Taking the entity pair as the cluster center, calculating the cosine similarity between each verb or verb phrase around the entity pair and the cluster center; According to the cosine similarity, each verb or verb phrase is merged with the cluster center, and a new cluster center is recalculated; Calculating the difference between the new cluster center and the cluster center, taking the verbs or verb phrases whose difference is less than a preset difference threshold as extraction results, and obtaining the relationship between railway knowledge entities; The identified railway knowledge entities and their relationships are represented by triples.

6. A method for constructing a railway domain knowledge graph according to claim 5, characterized in that: The identified railway knowledge entities and their relationships are represented by triples, including: The identified railway knowledge entities and their relationships are matched with each other, and after successful matching, multiple triples are formed in the form of subject-predicate-object.

7. The method for constructing a railway domain knowledge graph according to claim 1, characterized in that: The step of fusing and saving the triples into a graph database to construct a railway domain knowledge graph includes: Analyze the quantity scale of the railway knowledge entities and their relationships, and select the type of graph database according to the quantity scale of the railway knowledge entities and their relationships; In the graph database, the railway knowledge entities are used as nodes, and the relationships between the railway knowledge entities are used as edges to construct a graph model of the graph database; The triples are fused according to the graph pattern and saved into the graph database to construct a knowledge graph in the railway field.

8. A railway field knowledge graph construction device, characterized in that: include: An acquisition module, used to acquire railway domain knowledge text and preprocess the railway domain knowledge text; A screening module is used to select railway knowledge from the preprocessed railway domain knowledge text and screen out railway knowledge entities from the railway knowledge; A modeling module, used for analyzing the characteristics of the railway knowledge entity, and constructing and training a railway knowledge entity recognition model based on the railway knowledge entity and the characteristics; A recognition module is used to recognize railway knowledge entities in a railway domain knowledge base through a trained railway knowledge entity recognition model; An extraction module is used to extract and identify the relationship of corresponding railway knowledge entities from the railway domain knowledge text, and represent the identified railway knowledge entities and their relationships as triples; A construction module is used to merge and save the triples into a graph database to construct a knowledge graph in the railway field.

Images