Knowledge Fusion-Driven Construction Method of Emergency Inspection Knowledge Base

Abstract

The present invention discloses a method for constructing an emergency inspection knowledge base driven by knowledge fusion, belonging to the fields of emergency management and information technology. Specifically, it includes: collecting and preprocessing emergency inspection data from different data sources, extracting and representing emergency inspection knowledge using relation extraction methods and semantic web technologies, and constructing an emergency inspection knowledge graph through knowledge fusion strategies; classifying and coding the knowledge in the emergency inspection knowledge graph according to emergency inspection requirements, and formulating a classification vocabulary; conducting knowledge reasoning based on the emergency inspection knowledge graph, constructing an intelligent question-answering system and an emergency inspection process, and forming an emergency inspection knowledge base; optimizing and improving the knowledge base through functional testing, performance testing, and user feedback; the present invention improves the efficiency and accuracy of emergency inspections.

Description

Technical Field

[0001] The present invention belongs to the field of emergency management and information technology, and specifically relates to a method for constructing an emergency inspection knowledge base driven by knowledge fusion. Background Art

[0002] In emergency inspection work, the knowledge base plays a crucial role in guiding inspectors to carry out work accurately and efficiently. However, the existing knowledge base construction methods have the following problems. On the one hand, the knowledge sources are scattered, including various types such as laws and regulations, standards and specifications, enterprise safety risk data, and hidden danger data, and the integration is difficult. On the other hand, traditional methods lack effective knowledge fusion means and cannot fully explore the associations between different knowledge, resulting in insufficient capabilities of the knowledge base in dealing with complex emergency scenarios and unable to provide comprehensive and accurate knowledge support for emergency inspection. In addition, the representation and update mechanism of knowledge is not flexible enough to adapt to the characteristics of the rapid change of knowledge in the emergency field, which affects the application effect of the knowledge base in actual emergency inspection.

[0003] For example, the Chinese patent with the authorization announcement number CN111143448B discloses a knowledge base construction method, including: determining data sources; obtaining ontology data according to the data sources; generating data to be processed by scraping ontology data according to the data sources; determining whether the data to be processed is semi-structured data; if the data to be processed is not semi-structured data, performing knowledge information extraction on the data to be processed to obtain result data; if the data to be processed is semi-structured data, performing unified processing on the data to be processed to obtain uniformly processed data; performing knowledge information extraction on the uniformly processed data to obtain result data; if the data to be processed is not semi-structured data, performing knowledge information extraction on the data to be processed to obtain result data; and adding the result data to the knowledge base.

[0004] For example, the Chinese patent with the authorization announcement number CN111782825B discloses a knowledge base construction method and device, including: obtaining review information and review requirements, where the review requirements correspond to multiple review fields; grouping the review information according to a preset grouping rule to generate multiple review data groups; constructing a review field knowledge graph corresponding to each review field according to the multiple review data groups and the review requirements; and generating a review knowledge base according to each review field knowledge graph. The knowledge base construction method provided by this technical solution can create multiple review field knowledge graphs in multiple review fields according to the review information and review requirements, and then generate a review knowledge base from the multiple review field knowledge graphs, so as to timely and effectively obtain various review information and facilitate making correct and reasonable changes in a timely manner.

[0005] The above existing technologies all have the following problems: In CN111143448B, the knowledge information extraction method is ambiguous, and there is a lack of knowledge fusion and the construction of knowledge graphs; it does not involve the classification and coding of knowledge, which may make it difficult to effectively retrieve and utilize the knowledge in the knowledge base; there is a lack of intelligent applications; in CN111782825B, it is mentioned that an audit domain knowledge graph is constructed according to the audit data group and audit requirements, but the method of knowledge extraction and the form of knowledge representation are not specifically described; the process of knowledge fusion is not mentioned, that is, how to identify and merge duplicate entities, and how to optimize the knowledge set; there is a lack of knowledge classification and coding. Summary of the Invention

[0006] In view of the deficiencies of the existing technologies, the present invention proposes a method for constructing an emergency inspection knowledge base driven by knowledge fusion, which collects and preprocesses emergency inspection data from different data sources, extracts and represents emergency inspection knowledge using relation extraction methods and semantic web technologies, and constructs an emergency inspection knowledge graph through knowledge fusion strategies; classifies and codes the knowledge in the emergency inspection knowledge graph according to emergency inspection requirements, and formulates a classification vocabulary; conducts knowledge reasoning based on the emergency inspection knowledge graph, constructs an intelligent question-answering system and an emergency inspection process, and forms an emergency inspection knowledge base; through functional testing, performance testing and user feedback, optimizes and improves the knowledge base, and the present invention improves the efficiency and accuracy of emergency inspections.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for constructing an emergency inspection knowledge base driven by knowledge fusion, comprising:

[0009] Step S1: Collect emergency inspection data from structured, semi-structured and unstructured data sources, and perform preprocessing to obtain emergency inspection text data;

[0010] Step S2: Use relation extraction methods combined with emergency inspection specifications to extract emergency inspection knowledge from the emergency inspection text data, and use a knowledge representation method based on the semantic web to represent the extracted emergency inspection knowledge in the form of subject-predicate-object triples, forming an emergency inspection knowledge set;

[0011] Step S3: Use knowledge fusion strategies to identify and merge duplicate entities in the emergency inspection knowledge set. At the same time, use a rule engine to optimize the merged emergency inspection knowledge set, and construct an emergency inspection knowledge graph on the basis of knowledge fusion, and store the knowledge in the form of a graph structure;

[0012] Step S4: Classify the knowledge in the emergency inspection knowledge graph according to the requirements and domain characteristics of emergency inspections, and establish a unique code for the emergency inspection knowledge under each classification to obtain a classified emergency inspection knowledge graph;

[0013] Step S5: Using natural language processing technology and the classified emergency inspection knowledge graph, construct a question-answering system, and based on the classified emergency inspection knowledge graph and the question-answering system, construct an emergency inspection process to form an emergency inspection knowledge base;

[0014] Step S6: Conduct functional testing and performance testing on the emergency inspection knowledge base. At the same time, collect users' feedback opinions, and optimize and improve the emergency inspection knowledge base according to the feedback.

[0015] Specifically, the specific steps of the said step S2 include:

[0016] S2.1: According to the emergency inspection specifications, clarify the types and scopes of the knowledge to be extracted;

[0017] S2.2: Obtain emergency inspection text data , and extract emergency inspection features from , where represents the nth emergency inspection text data, and n represents the number of emergency inspection text data;

[0018] S2.3: Load the pre-built machine learning model, and use the extracted emergency inspection features to train and evaluate the pre-built machine learning model to generate a relation extraction model;

[0019] S2.4: Input into the relation extraction model to identify entities and relationships, and obtain the entities and the relationships between entities in the emergency inspection text, generating emergency inspection knowledge , where K represents the generated emergency inspection knowledge, represents the relation extraction model, E represents the entities identified in the emergency inspection text, R represents the set of relationships between entities in the emergency inspection text, represents the mapping relationship;

[0020] S2.5: According to the generated emergency inspection knowledge K, identify all entities and their corresponding relationships, and construct subject-predicate-object triples based on the identified entities and their corresponding relationships. The subject-predicate-object triple is , where and respectively represent two different entities, represents and interact or are related to each other.

[0021] Specifically, the specific steps of the said step S2 further include:

[0022] S2.6: Verify the constructed subject-predicate-object triples;

[0023] If , then the constructed subject-predicate-object triple is incorrect and reconstruction is performed;

[0024] If , then judge whether it describes and the interaction or connection between them;

[0025] If is inconsistent with the actual connection between and , then the constructed subject-predicate-object triple is incorrect and reconstruction is performed;

[0026] If is consistent with the actual connection between and , then judge whether it belongs to the set of relationships between entities in the emergency inspection text;

[0027] If , then judge whether it conflicts in R;

[0028] If there is a conflict, use standard data in the field for screening;

[0029] If there is no conflict, retain the constructed subject-predicate-object triple;

[0030] S2.7: Combine multiple constructed subject-predicate-object triples to form an emergency inspection knowledge set;

[0031] S2.8: Use the semantic web method to represent the integrated emergency inspection knowledge set as a structured semantic network and store the structured semantic network.

[0032] Specifically, the specific steps of step S3 include:

[0033] S3.1: Obtain the emergency inspection knowledge set and perform preprocessing;

[0034] S3.2: Use the entity alignment algorithm to identify duplicate entities in the preprocessed emergency inspection knowledge set and perform a merging operation on the identified duplicate entities;

[0035] S3.3: Use the rule engine to optimize the merged emergency inspection knowledge set;

[0036] S3.4: Based on the optimized emergency inspection knowledge set, construct an emergency inspection knowledge graph and store the constructed emergency inspection knowledge graph in a database.

[0037] Specifically, the specific steps of S3.2 include:

[0038] S3.21: Obtain the preprocessed emergency inspection knowledge set B, identify and extract the named entities in B ; where represents the i-th named entity in B, and m represents the number of named entities in B;

[0039] S3.22: Extract the features of each entity, and according to the extracted features, use the entity alignment algorithm to calculate the similarity between entities. The formula is:

[0040] ;

[0041] where represents the similarity between two different entities and in B, and respectively represent and the neighbor entity sets of, C represents the damping coefficient, and , represents the weight of the j-th neighbor of entity , represents the weight of the l-th neighbor of entity , represents the similarity based on neighbor entities, and respectively represent the j-th neighbor entity of and the l-th neighbor entity of, represents the attribute similarity of entities and themselves;

[0042] S3.23: Set the similarity threshold h;

[0043] If , it means that the corresponding entities and are duplicate entities;

[0044] S3.24: Merge the duplicate entities and output the list of duplicate entities.

[0045] Specifically, the specific steps of step S4 include:

[0046] S4.1: Obtain the emergency inspection knowledge graph, set the mutually exclusive classification principle according to the needs of emergency inspection, and construct a preliminary knowledge classification system according to the set mutually exclusive classification principle;

[0047] S4.2: Refine and label the preliminary knowledge classification system to generate a knowledge classification system, and classify the knowledge in the emergency inspection knowledge graph according to the knowledge classification system;

[0048] S4.3: Design a unique code for the emergency inspection knowledge under each classification, add the designed unique code to the corresponding position of each emergency inspection knowledge in the emergency inspection knowledge graph, and at the same time, update the emergency inspection knowledge graph.

[0049] Specifically, the specific steps of step S5 include:

[0050] S5.1: Design the overall architecture of the question-answering system. The overall architecture of the question-answering system includes a user interface, a preprocessing module, a semantic understanding module, a knowledge retrieval module, an answer generation module, and a post-processing module;

[0051] S5.2: Connect the classified emergency inspection knowledge graph to the question-answering system as the basis for knowledge retrieval and answer generation;

[0052] S5.3: Design an emergency inspection process according to the functions of the emergency inspection knowledge graph and the question-answering system, and integrate the emergency inspection process into the management system;

[0053] S5.4: Optimize and adjust the emergency inspection process according to the actual usage situation;

[0054] S5.5: Integrate the classified emergency inspection knowledge graph, the question-answering system, and the optimized and adjusted emergency inspection process to form an emergency inspection knowledge base.

[0055] Specifically, the principle of mutually exclusive classification in S4.1 means that the classifications do not overlap.

[0056] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion.

[0057] A computer-readable storage medium stores computer instructions, and when the computer instructions run, they execute the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] 1. The present invention proposes a method for constructing an emergency inspection knowledge base driven by knowledge fusion. By collecting and preprocessing data from diverse data sources, and then using natural language processing and semantic web technologies to extract and structurally represent knowledge, it effectively integrates a wide range of information in the field of emergency inspection. The knowledge fusion strategy and the construction of the knowledge graph further ensure the uniqueness and accuracy of the data.

[0060] 2. The present invention proposes a method for constructing an emergency inspection knowledge base driven by knowledge fusion, which also improves the intelligent level of emergency inspections. By classifying and coding knowledge, knowledge reasoning, and constructing an intelligent question-and-answer system and inspection process, it not only improves the speed of emergency response but also makes the inspection process more scientific and standardized. At the same time, continuous functional testing, performance testing, and user feedback collection ensure the continuous optimization and improvement of the emergency inspection knowledge base, so as to better serve emergency management work. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the method for constructing an emergency inspection knowledge base driven by knowledge fusion of the present invention;

[0062] Figure 2 It is a principle flow chart of the method for constructing an emergency inspection knowledge base driven by knowledge fusion of the present invention;

[0063] Figure 3 It is a flow chart for realizing the emergency inspection knowledge set of the method for constructing an emergency inspection knowledge base driven by knowledge fusion of the present invention;

[0064] Figure 4 It is a flow chart for realizing the emergency inspection knowledge graph of the method for constructing an emergency inspection knowledge base driven by knowledge fusion of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] Embodiment 1

[0066] Please refer to Figure 1 and Figure 2 The present invention provides an embodiment: a method for constructing an emergency inspection knowledge base driven by knowledge fusion, including the following steps:

[0067] Step S1: Collect emergency inspection data from structured, semi-structured, and unstructured data sources, and perform preprocessing to obtain emergency inspection text data;

[0068] Among them, the collected emergency inspection data is collected in the form of text, including plain text, documents, and web page content, which is text data; structured data sources include databases, tables, etc.; semi-structured data sources include web pages, logs, etc.; unstructured data sources include text files, images, videos, etc.

[0069] Furthermore, the preprocessing process includes:

[0070] (1) Clean the collected emergency inspection data to remove irrelevant information, advertisements, tags, HTML, JS and other codes and comments;

[0071] (2) Tokenize the text, breaking it down into smaller language units for subsequent processing;

[0072] (3) Perform part-of-speech tagging, assigning part-of-speech labels such as adjectives, verbs, nouns, etc. to each word or phrase to incorporate more useful language information;

[0073] (4) Remove stop words, i.e., words that do not contribute to the text features, such as punctuation marks, modal particles, etc.

[0074] Step S2: Use the relation extraction method to extract emergency inspection knowledge from the emergency inspection text data in combination with the emergency inspection specifications, and use the knowledge representation method based on the semantic web to represent the extracted emergency inspection knowledge in the form of subject-predicate-object triples to form an emergency inspection knowledge set;

[0075] Step S3: Use the knowledge fusion strategy to identify and merge duplicate entities in the emergency inspection knowledge set. At the same time, use the rule engine to optimize the merged emergency inspection knowledge set, and build an emergency inspection knowledge graph on the basis of knowledge fusion to store the knowledge in the form of a graph structure;

[0076] Step S4: Classify the knowledge in the emergency inspection knowledge graph according to the requirements and domain characteristics of the emergency inspection, and establish a unique code for the emergency inspection knowledge under each classification to obtain the classified emergency inspection knowledge graph;

[0077] Step S5: Utilize natural language processing techniques and the classified emergency inspection knowledge graph to build a question-answering system, and build an emergency inspection process based on the classified emergency inspection knowledge graph and the question-answering system to form an emergency inspection knowledge base;

[0078] Step S6: Conduct functional testing and performance testing on the emergency inspection knowledge base. At the same time, collect user feedback and optimize and improve the emergency inspection knowledge base according to the feedback.

[0079] Embodiment 2

[0080] Please refer to Figure 3 and Figure 4 In this embodiment, the specific steps of step S2 include:

[0081] S2.1: According to the emergency inspection specifications, clarify the types and scopes of knowledge to be extracted;

[0082] S2.2: Obtain the emergency inspection text data and extract the emergency inspection features from where represents the nth emergency inspection text data, and n represents the number of emergency inspection text data;

[0083] S2.3: Load the pre - built machine learning model, and use the extracted emergency inspection features to train and evaluate the pre - built machine learning model to generate a relation extraction model. The machine learning model is the prior art content in this field and not the creative solution of this application, so it will not be elaborated here;

[0084] S2.4: Input into the relation extraction model to identify entities and relationships, obtain the entities and the relationships between entities in the emergency inspection text, and generate emergency inspection knowledge , where K represents the generated emergency inspection knowledge, represents the relation extraction model, E represents the entities in the identified emergency inspection text, R represents the set of relationships between entities in the emergency inspection text, represents the mapping relationship;

[0085] It should be noted that the expression describes a relation extraction process. In this process, the relation extraction model M extracts entities E and relationships R from the input emergency inspection text data X, and finally generates structured emergency inspection knowledge K.

[0086] S2.5: According to the generated emergency inspection knowledge K, identify all entities and their corresponding relationships, and construct subject - verb - object triples based on the identified entities and their corresponding relationships. The subject - verb - object triples are , where and respectively represent two different entities, represents and the interaction or connection between them;

[0087] S2.6: Verify the constructed subject - verb - object triples;

[0088] If , the constructed subject - verb - object triples are incorrect and need to be reconstructed;

[0089] If , then determine whether describes and the interaction or connection between them;

[0090] If does not match the actual connection between and , the constructed subject - verb - object triples are incorrect and need to be reconstructed;

[0091] If matches the actual connection between and , then determine Whether it belongs to the set of relationships between entities in the emergency inspection text;

[0092] If , then judge Whether there is a conflict in R;

[0093] If there is a conflict, use the standard data in the field for screening;

[0094] If there is no conflict, retain the constructed subject-predicate-object triple;

[0095] S2.7: Combine multiple constructed subject-predicate-object triples to form an emergency inspection knowledge set;

[0096] S2.8: Use the semantic web method to represent the integrated emergency inspection knowledge set as a structured semantic network and store the structured semantic network.

[0097] Furthermore, the specific steps of S2.8 include:

[0098] (1) Obtain the emergency inspection knowledge set and perform preprocessing;

[0099] (2) Define a semantic model according to the characteristics and requirements of the emergency inspection knowledge. Among them, the semantic model includes elements such as entities, attributes, relationships, etc., as well as their hierarchical structures and relationship networks. At the same time, in the semantic model, entities can represent key elements in emergency inspections such as equipment, personnel, locations, etc.; attributes can describe the characteristics or states of entities; relationships are used to represent the interactions or connections between entities;

[0100] (3) Use the entities, attributes, and relationships in the semantic model to construct a structured semantic network. This network is usually represented in the form of a graph, where nodes represent entities or attributes, and edges represent relationships. At the same time, when constructing the semantic network, it is necessary to ensure that each entity and relationship has a clear definition and description for subsequent storage and query;

[0101] (4) Convert the data in the semantic network into the storage format of a graph database and store it in the corresponding storage medium;

[0102] (5) Verify the stored semantic network to ensure the accuracy and integrity of the data, and optimize the semantic network according to the verification results, such as correcting incorrect data and improving missing information.

[0103] The specific steps of step S3 include:

[0104] S3.1: Obtain the emergency inspection knowledge set and perform preprocessing;

[0105] S3.2: Identify duplicate entities in the preprocessed emergency inspection knowledge set using entity alignment algorithms, and perform merging operations on the identified duplicate entities;

[0106] S3.3: Optimize the merged emergency inspection knowledge set using a rule engine. The rule engine is prior art content in this field and not a creative solution of this application, so it will not be elaborated here;

[0107] S3.4: Based on the optimized emergency inspection knowledge set, construct an emergency inspection knowledge graph and store the constructed emergency inspection knowledge graph in a database.

[0108] Further, the specific steps of S3.4 include:

[0109] (1) Based on the application attributes, knowledge characteristics, and actual requirements of emergency inspections, conduct business abstraction and business modeling according to the schema of the knowledge graph, mainly including entity definition and relationship definition;

[0110] (2) Obtain the optimized emergency inspection knowledge set to ensure the accuracy, integrity, and consistency of the knowledge;

[0111] (3) According to the characteristics and requirements of the optimized emergency inspection knowledge, design the basic architecture of the emergency inspection knowledge graph, including the definition of entities, relationships, attributes, and the association methods between them;

[0112] (4) Knowledge extraction: Extract structured information such as entities, relationships, and attributes from the optimized emergency inspection knowledge set;

[0113] (5) Entity extraction: Identify and extract key entities in the emergency inspection knowledge set, such as equipment, fault types, and inspection standards;

[0114] (6) Relationship extraction: Determine the relationships between entities, such as the correspondence between equipment and fault types, and the association between equipment and inspection standards;

[0115] (7) Attribute extraction: Extract the attribute information of entities, such as the model of equipment, the description of fault types, and the specific content of inspection standards;

[0116] (8) Knowledge fusion: Integrate and fuse the extracted knowledge to eliminate contradictions and ambiguities and form a unified knowledge system;

[0117] (9) Knowledge storage: Store the constructed emergency inspection knowledge graph in a database for subsequent query and application.

[0118] The specific steps of S3.2 include:

[0119] S3.21: Obtain the preprocessed emergency inspection knowledge set B, and identify and extract the named entities in B ; where represents the i-th named entity in B, and m represents the number of named entities in B;

[0120] S3.22: Extract the features of each entity, and use the entity alignment algorithm to calculate the similarity between entities based on the extracted features. The formula is:

[0121] ;

[0122] where represents the similarity between two different entities and in B, and respectively represent and 's neighbor entity sets, C represents the damping coefficient, and , represents the weight of the j-th neighbor of entity , represents the weight of the l-th neighbor of entity , represents the similarity based on neighbor entities, and respectively represent 's j-th neighbor entity and 's l-th neighbor entity, represents the attribute similarity between entities and themselves;

[0123] It should be noted that the formula in the present invention makes the similarity calculation more accurate and comprehensive by introducing weights and combining neighborhood similarity and attribute similarity, and can more precisely reflect the complex relationship between two objects.

[0124] S3.23: Set the similarity threshold h;

[0125] If , it means that 's corresponding entities and are duplicate entities;

[0126] S3.24: Merge the duplicate entities and output the list of duplicate entities.

[0127] The specific steps of S4 include:

[0128] S4.1: Obtain the emergency inspection knowledge graph, set the mutually exclusive classification principle according to the requirements of emergency inspection, and construct a preliminary knowledge classification system based on the set mutually exclusive classification principle;

[0129] Among them, the mutually exclusive classification principle means that the classifications do not overlap.

[0130] S4.2: Refine and label the preliminary knowledge classification system to generate a knowledge classification system, and classify the knowledge in the emergency inspection knowledge graph according to the knowledge classification system;

[0131] Furthermore, the specific steps of S4.2 include:

[0132] (1) Obtain the preliminary knowledge classification system, add necessary sub-classifications to the preliminary classification according to the domain characteristics and user requirements to refine the classification system, and ensure that the logical relationship between the sub-classifications and the superior classifications is clear and accurate;

[0133] (2) Adjust the classification structure according to the analysis results, such as merging duplicate classifications and splitting overly general classifications, to ensure that the classification system has hierarchy, logic, and integrity;

[0134] (3) Design clear, concise, and easy-to-understand labels for each classification and sub-classification. Among them, the labels should be able to accurately reflect the content and characteristics of the classification, facilitating user identification and retrieval;

[0135] (4) Organize the designed labels according to the classification system to form a label system. At the same time, ensure that the label system is consistent with the knowledge classification system for subsequent knowledge classification and retrieval;

[0136] (5) Combine the refined classification system and the label system to generate a knowledge classification system. Among them, the knowledge classification system should be able to comprehensively cover the knowledge in the domain and be convenient for users to retrieve and use;

[0137] (6) Obtain the emergency inspection knowledge graph, classify the knowledge in the emergency inspection knowledge graph according to the generated knowledge classification system, classify each knowledge entity into the corresponding classification or sub-classification, and label it with the corresponding label;

[0138] (7) Verify the classification results to ensure the accuracy and reasonableness of the classification, and identify and correct existing classification errors or omissions.

[0139] S4.3: Design a unique code for the emergency inspection knowledge under each classification, add the designed unique code to the corresponding position of each emergency inspection knowledge in the emergency inspection knowledge graph, and update the emergency inspection knowledge graph.

[0140] Furthermore, the specific steps of S4.3 include:

[0141] (1) Design a reasonable coding rule according to the classification system, knowledge characteristics, and management requirements of emergency inspection knowledge. Among them, the coding rule should ensure that each piece of emergency inspection knowledge under each classification can obtain a unique code.

[0142] (2) Assign a unique coding range to each classification to avoid coding conflicts.

[0143] (3) Generate a unique code for each piece of emergency inspection knowledge according to the designed coding rule and the assigned coding range. The code contains elements such as classification information, knowledge serial number, timestamp, etc.

[0144] (4) Use the coding management system to verify whether the generated code is unique. If there is a duplicate code, it needs to be regenerated until it is ensured that each code is unique.

[0145] (5) Find the corresponding position of each piece of emergency inspection knowledge in the emergency inspection knowledge graph through a local traversal method, and add the generated unique code to the metadata or attributes of the corresponding emergency inspection knowledge. At the same time, ensure that the addition of the code does not damage the structure and integrity of the knowledge graph. Among them, the local traversal method is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here.

[0146] (6) After adding the code, verify the emergency inspection knowledge graph to ensure that the addition of the code does not introduce errors or omissions, and publish the updated emergency inspection knowledge graph to the corresponding storage system or service platform to ensure that users can access the latest version of the emergency inspection knowledge graph.

[0147] Exemplarily, assume that D is the set of emergency inspection knowledge, Q is the set of classifications, and G is the set of codes;

[0148] For each piece of emergency inspection knowledge , there exists a classification , and a unique code ;

[0149] Coding generation function Generate a unique code g according to the emergency inspection knowledge d and the classification q;

[0150] Coding addition function Add the generated code g to the metadata or attributes of the emergency inspection knowledge d.

[0151] The specific steps of step S5 include:

[0152] S5.1: Design the overall architecture of the question-and-answer system. The overall architecture of the question-and-answer system includes a user interface, a preprocessing module, a semantic understanding module, a knowledge retrieval module, an answer generation module, and a postprocessing module;

[0153] Further, the steps for designing the overall architecture of the question-and-answer system include:

[0154] (1) User interface: Design a simple and clear user interface to facilitate users to input questions and view results;

[0155] (2) Question processing: Determine how the question-and-answer system processes the questions input by users, including steps such as word segmentation, semantic understanding, knowledge retrieval, and answer generation;

[0156] (3) Result feedback: Design the way for the question-and-answer system to feedback results to users, including various forms such as text, charts, and voice.

[0157] S5.2: Connect the classified emergency inspection knowledge graph to the question-and-answer system as the basis for knowledge retrieval and answer generation;

[0158] S5.3: Design an emergency inspection process according to the emergency inspection knowledge graph and the functions of the question-and-answer system, and integrate the emergency inspection process into the management system;

[0159] Further, the specific steps for designing the emergency inspection process include:

[0160] (1) Use the question-and-answer system to quickly obtain the basic knowledge of emergency inspection, such as inspection standards, methods, and precautions, and determine the key points and priorities of the inspection according to the relationships in the emergency inspection knowledge graph;

[0161] (2) Conduct a detailed on-site inspection according to the determined key points and priorities. During the inspection process, use the question-and-answer system to obtain relevant information in real time and answer questions, and based on the inspection results, use the relationships in the emergency inspection knowledge graph to reason and analyze to determine potential risks and problems;

[0162] (3) For the discovered problems, use the question-and-answer system to obtain solutions and suggestions, and according to the solutions and suggestions, formulate specific rectification measures and schedules. At the same time, record the rectification measures and schedules in the knowledge graph for subsequent tracking and verification;

[0163] (4) Use computer technology to automate the above emergency inspection steps to form a complete emergency inspection process, and optimize and adjust the emergency inspection process according to the actual application situation to improve its efficiency and accuracy.

[0164] S5.4: Optimize and adjust the emergency inspection process according to the actual usage situation;

[0165] S5.5: Integrate the classified emergency inspection knowledge graph, question - answering system, and the optimized and adjusted emergency inspection process to form an emergency inspection knowledge base.

[0166] Embodiment 3

[0167] An electronic device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it implements the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion. For details, refer to the above - mentioned method embodiments and will not be elaborated here.

[0168] A computer - readable storage medium stores computer instructions. When the computer instructions run, they execute the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion. Here, the storage medium can be a volatile or non - volatile computer - readable storage medium.

[0169] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above - mentioned specific embodiments. The above - mentioned specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make changes, modifications, substitutions, and variations to the above - mentioned embodiments without departing from the purpose and scope of the present invention. All of these fall within the protection scope of the present invention.

[0170] If the technical solution of this disclosure involves personal information, before the product applying the technical solution of this disclosure processes personal information, it has clearly informed the personal information processing rules and obtained the individual's autonomous consent. If the technical solution of this disclosure involves sensitive personal information, before the product applying the technical solution of this disclosure processes sensitive personal information, it has obtained the individual's separate consent and at the same time meets the requirement of "express consent". For example, at a personal information collection device such as a camera, a clear and prominent sign is set to inform that the personal information collection range has been entered and personal information will be collected. If an individual voluntarily enters the collection range, it is regarded as consenting to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are informed by obvious signs / information, personal authorization is obtained through pop - up messages or by asking the individual to upload their personal information themselves, etc. Among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. A method for constructing an emergency inspection knowledge base driven by knowledge fusion, characterized in that Including: Step S1: Collect emergency inspection data from structured, semi-structured, and unstructured data sources, and perform preprocessing to obtain emergency inspection text data; Step S2: Use the relation extraction method to extract emergency inspection knowledge from the emergency inspection text data in combination with the emergency inspection specifications, and use the knowledge representation method based on the semantic web to represent the extracted emergency inspection knowledge in the form of subject-predicate-object triples, forming an emergency inspection knowledge set; Step S3: Use the knowledge fusion strategy to identify and merge duplicate entities in the emergency inspection knowledge set. At the same time, use the rule engine to optimize the merged emergency inspection knowledge set, and build an emergency inspection knowledge graph on the basis of knowledge fusion, and store the knowledge in the form of a graph structure; Step S4: Classify the knowledge in the emergency inspection knowledge graph according to the requirements and domain characteristics of emergency inspection, and establish a unique code for the emergency inspection knowledge under each classification to obtain the classified emergency inspection knowledge graph; Step S5: Use natural language processing technology and the classified emergency inspection knowledge graph to build a question-answering system, and build an emergency inspection process based on the classified emergency inspection knowledge graph and the question-answering system to form an emergency inspection knowledge base; Step S6: Conduct functional testing and performance testing on the emergency inspection knowledge base. At the same time, collect the feedback from users, and optimize and improve the emergency inspection knowledge base according to the feedback; The specific steps of the said Step S2 include: S2.1: According to the emergency inspection specifications, clarify the types and scopes of the extracted knowledge; S2.2: Obtain emergency inspection text data , and extract emergency inspection features from , where represents the nth emergency inspection text data, and n represents the quantity of emergency inspection text data; S2.3: Load the pre-built machine learning model, and use the extracted emergency inspection features to train and evaluate the pre-built machine learning model to generate a relation extraction model; S2.4: Input into the relation extraction model to identify entities and relations, obtain the entities and the relations between entities in the emergency inspection text, and generate emergency inspection knowledge , where K represents the generated emergency inspection knowledge, represents the relation extraction model, E represents the entities identified in the emergency inspection text, and R represents the set of relations between entities in the emergency inspection text, represents the mapping relation; S2.5: According to the generated emergency inspection knowledge K, identify all entities and their corresponding relationships, and construct subject-predicate-object triples based on the identified entities and their corresponding relationships. The subject-predicate-object triples are , where and respectively represent two different entities, represents and interact or are related to each other; The specific steps of the said Step S2 also include: S2.6: Verify the constructed subject-predicate-object triples; If , the constructed subject-predicate-object triple is incorrect and reconstruction is performed again; If , then determine whether describes the interaction or relationship between and ; If is inconsistent with the actual connection with and then the constructed subject-predicate-object triple is incorrect and reconstruction is performed again; If is consistent with the actual connection between and , then it is determined whether belongs to the set of relationships between entities in the emergency inspection text; If , then determine whether there is a conflict in R; If there is a conflict, use the standard data in the field for screening; If there is no conflict, retain the constructed subject-predicate-object triples; S2.7: Combine multiple constructed subject-predicate-object triples to form an emergency inspection knowledge set; S2.8: Use the semantic web method to represent the integrated emergency inspection knowledge set as a structured semantic network, and store the structured semantic network.

2. The method for constructing an emergency inspection knowledge base driven by knowledge fusion as claimed in claim 1, wherein The specific steps of the said Step S3 include: S3.1: Obtain the emergency inspection knowledge set and perform preprocessing; S3.2: Use the entity alignment algorithm to identify duplicate entities in the preprocessed emergency inspection knowledge set, and perform a merging operation on the identified duplicate entities; S3.3: Use the rule engine to optimize the merged emergency inspection knowledge set; S3.4: Based on the optimized emergency inspection knowledge set, build an emergency inspection knowledge graph, and store the built emergency inspection knowledge graph in the database.

3. The method for constructing an emergency inspection knowledge base driven by knowledge fusion according to claim 2, wherein The specific steps of the said S3.2 include: S3.21: Obtain the preprocessed emergency inspection knowledge set B, and identify and extract the named entities in B ; where represents the i-th named entity in B, and m represents the number of named entities in B; S3.22: Extract the features of each entity, and use the entity alignment algorithm to calculate the similarity between entities according to the extracted features. The formula is: ； Among them, represents the similarity between two different entities in B and ; and respectively represent and 's neighbor entity sets. C represents the damping coefficient, and , represents the weight of the j-th neighbor of entity ; represents the weight of the l-th neighbor of entity ; represents the similarity based on neighbor entities, and respectively represent 's j-th neighbor entity and 's l-th neighbor entity, represents the attribute similarity between entities and themselves; S3.23: Set the similarity threshold h; If , it means that the corresponding entity and are duplicate entities; S3.24: Merge the duplicate entities and output the list of duplicate entities.

4. The method for constructing an emergency inspection knowledge base driven by knowledge fusion as claimed in claim 3, wherein The specific steps of the said Step S4 include: S4.1: Obtain an emergency inspection knowledge graph, set mutually exclusive classification principles according to the requirements of emergency inspections, and construct a preliminary knowledge classification system based on the set mutually exclusive classification principles; S4.2: Refine and label the preliminary knowledge classification system to generate a knowledge classification system, and classify the knowledge in the emergency inspection knowledge graph according to the knowledge classification system; S4.3: Design a unique code for the emergency inspection knowledge under each classification, add the designed unique code to the corresponding position of each emergency inspection knowledge in the emergency inspection knowledge graph, and at the same time, update the emergency inspection knowledge graph.

5. The method for constructing an emergency inspection knowledge base driven by knowledge fusion as claimed in claim 4, wherein The specific steps of step S5 include: S5.1: Design the overall architecture of the question-and-answer system. The overall architecture of the question-and-answer system includes a user interface, a preprocessing module, a semantic understanding module, a knowledge retrieval module, an answer generation module, and a post-processing module; S5.2: Connect the classified emergency inspection knowledge graph to the question-and-answer system as the basis for knowledge retrieval and answer generation; S5.3: Design an emergency inspection process according to the functions of the emergency inspection knowledge graph and the question-and-answer system, and integrate the emergency inspection process into the management system; S5.4: Optimize and adjust the emergency inspection process according to the actual usage situation; S5.5: Integrate the classified emergency inspection knowledge graph, the question-and-answer system, and the optimized and adjusted emergency inspection process to form an emergency inspection knowledge base.

6. The method for constructing an emergency inspection knowledge base driven by knowledge fusion as claimed in claim 5, wherein The mutually exclusive classification principle in S4.1 means that the classifications do not overlap.

7. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, Stored thereon are computer instructions, and when the computer instructions run, they execute the steps of the method for constructing an emergency inspection knowledge base driven by knowledge fusion according to any one of claims 1-6.

Images