Urban rail transit intelligent operation and maintenance system based on knowledge graph

Abstract

The invention discloses an urban rail transit intelligent operation and maintenance system based on a knowledge graph, and the system comprises a rail transit fault collection module which is used for collecting the fault report information of each fault generated in the operation process of an urban rail transit system in real time; a fault element extraction module which is in communication connection with the rail transit fault acquisition module and is used for receiving the fault report information and carrying out element extraction on the fault report information one by one so as to obtain fault element information capable of comprehensively covering each fault in the fault report information; the fault matching module is used for matching the fault element information of each fault with a knowledge graph of historical faults and outputting a matching result; and the operation and maintenance module is used for evaluating the plurality of faults according to the matching result matched and output by the fault matching module and providing maintenance plan information. According to the invention, rapid identification, accurate positioning, efficient processing and intelligent operation and maintenance management of faults are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban rail transit operation and maintenance, and relates to an urban rail transit intelligent operation and maintenance system based on a knowledge graph. Background Art

[0002] With the continuous development and expansion of urban rail transit systems, a large amount of operational production data and equipment maintenance data has been generated. However, traditional discrete data forms are difficult to support large-scale intelligent applications, which poses a great challenge to the digital transformation of rail transit. At the same time, problems such as large workload of equipment maintenance, limited time windows, high maintenance costs, and lack of timeliness are becoming increasingly prominent. Traditional maintenance and repair strategies, daily maintenance production organization, and fault diagnosis levels are difficult to adapt to the ever-increasing demand for operational safety services, resulting in an increasing number of failures of facilities and equipment. In order to overcome these limitations, this application is therefore filed. Summary of the invention

[0003] An object of the present invention is to solve at least the above problems and / or disadvantages and to provide at least the advantages which will be described hereinafter.

[0004] Another object of the present invention is to provide an intelligent operation and maintenance system for urban rail transit based on knowledge graph.

[0005] To this end, the technical solution provided by the present invention is: An urban rail transit intelligent operation and maintenance system based on knowledge graph includes the following steps: Rail transit fault collection module, which is used to collect fault report information of each fault generated during the operation of the urban rail transit system in real time; A fault element extraction module, which is in communication connection with the rail transit fault collection module and is used to receive fault report information and extract elements of the fault report information one by one, so as to obtain fault element information in the fault report information that can fully cover each of the faults; A fault matching module is used to match the fault factor information of each fault with the knowledge graph of historical faults and output the matching result; The operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module and provides maintenance plan information.

[0006] Preferably, the urban rail transit intelligent operation and maintenance system based on knowledge graph further includes: A knowledge graph construction module is used to construct the knowledge graph of the historical faults. The knowledge graph construction module extracts relevant entities, attributes and relationships of the historical faults to form nodes and edges of the knowledge graph.

[0007] Preferably, in the urban rail transit intelligent operation and maintenance system based on knowledge graph, the process of constructing the knowledge graph by the knowledge graph construction module includes: Collect data sources for building knowledge graphs, including existing knowledge bases; Extract entity attributes and relationships from data sources; Fuse the extracted new knowledge with the existing knowledge in the existing knowledge base; First, define the data structure for the knowledge graph, and then add the entities to the knowledge base. The nodes of the constructed data structure include fault information, fault factors, equipment type, equipment failure, possible causes of failure, tools, processing steps, and historical fault solutions. The knowledge after knowledge fusion is added to the knowledge base to construct a complete knowledge graph.

[0008] Preferably, the urban rail transit intelligent operation and maintenance system based on knowledge graph further includes: An update module is communicatively connected to the operation and maintenance module, and is used to extract knowledge from the acquired new fault assessment results and maintenance plan information, and integrate them into the knowledge graph.

[0009] Preferably, the urban rail transit intelligent operation and maintenance system based on knowledge graph further includes: A skill level management module is used to record maintenance personnel and their corresponding maintenance skill levels. The skill level management module is communicatively connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to maintenance personnel based on the results of multiple fault assessments and maintenance skill levels.

[0010] Preferably, the urban rail transit intelligent operation and maintenance system based on knowledge graph further includes: An intelligent machine management module is used to record intelligent machines and their corresponding intelligent maintenance technology types. The intelligent machine management module is communicated with the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to each intelligent machine based on the results of multiple fault assessments and the types of intelligent maintenance technologies.

[0011] Preferably, the urban rail transit intelligent operation and maintenance system based on knowledge graph further includes: The interactive module is used to receive demand information input by the user and display maintenance plan information.

[0012] The present invention has at least the following beneficial effects: 1) Improve operation and maintenance efficiency: Through automated collection of fault information, intelligent matching of fault solutions, and automatic generation of maintenance plans, the system can significantly improve operation and maintenance efficiency and reduce operation and maintenance costs.

[0013] 2) Improve safety: By real-time monitoring of the operating status and fault information of the urban rail transit system, the system can promptly detect and handle potential safety hazards and improve the overall safety of the system.

[0014] 3) Optimize resource allocation: Through reasonable task allocation and intelligent machine management, the system can optimize resource allocation and improve resource utilization efficiency.

[0015] 4) Improve user experience: Through a friendly user interface and interactive design, the system can facilitate users to query fault handling progress and submit demand information, thereby improving user experience.

[0016] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with embodiments so that those skilled in the art can implement the invention with reference to the description.

[0018] It should be understood that terms such as “having”, “including” and “comprising” used herein do not specify the existence or addition of one or more other elements or combinations thereof.

[0019] The present invention aims to build an intelligent operation and maintenance system for urban rail transit equipment based on knowledge graph technology, transform the historical fault data of facilities and equipment into valuable knowledge, realize the effective accumulation and organization of fault knowledge, and assist maintenance personnel to discover and eliminate faults more quickly and efficiently, so as to realize rapid identification, accurate positioning, efficient processing and intelligent operation and maintenance management of faults.

[0020] The present invention provides an urban rail transit intelligent operation and maintenance system based on a knowledge graph, comprising: Rail transit fault collection module, which is used to collect fault report information of each fault generated during the operation of the urban rail transit system in real time; This module is responsible for collecting fault report information of each fault generated during the operation of the urban rail transit system in real time. Optionally, this information includes but is not limited to key data such as the time, location, type, and impact range of the fault. Through the arrangement and technical means such as sensor network and video monitoring, it is possible to achieve comprehensive monitoring of the operation of the urban rail transit system and ensure timely collection and accurate recording of fault information.

[0021] A fault element extraction module is communicatively connected to the rail transit fault collection module and is used to receive fault report information and extract elements of the fault report information one by one to obtain fault element information in the fault report information that can comprehensively cover each of the faults; optionally, the fault element extraction module uses natural language processing and data mining to extract fault element information that can comprehensively cover each fault from the fault report information, including fault phenomenon, fault location, fault level, etc., to provide key data support for subsequent fault matching.

[0022] A fault matching module is used to match the fault factor information of each fault with the knowledge graph of historical faults and output the matching result; more preferably, the fault matching module is based on a pre-built and continuously updated historical fault knowledge graph library, which contains a wealth of fault cases, fault solutions and fault handling experience. The fault matching module accurately matches the fault factor information of each fault, compares and analyzes it with historical fault cases, and quickly outputs the matching result, including possible causes of the fault, historical solutions and success rates, relevant expert advice and other information, and provides a matching score to assist operation and maintenance personnel in quickly locating problems; The operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module and provides maintenance plan information. More preferably, the operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module, including the severity of the faults, the scope of impact, the processing priority, etc. Based on the evaluation results, the operation and maintenance module automatically generates maintenance plan information, including maintenance tasks, required resources, estimated completion time, etc. At the same time, the operation and maintenance module also has a dynamic adjustment function, which can automatically adjust the maintenance plan according to the real-time feedback during the fault handling process to ensure the flexibility and efficiency of the operation and maintenance work.

[0023] In one embodiment of the present invention, preferably, it further comprises: A knowledge graph construction module is used to construct the knowledge graph of the historical faults. The knowledge graph construction module extracts the relevant entities, attributes and relationships of the historical faults to form nodes and edges of the knowledge graph. Optionally, the knowledge graph construction process includes multiple steps such as data preprocessing, entity recognition, relationship extraction, and graph construction. By continuously optimizing and improving the knowledge graph, the accuracy and timeliness of the knowledge graph can be ensured, providing a reliable data foundation for subsequent fault matching.

[0024] In one of the solutions of the present invention, preferably, the process of constructing the knowledge graph by the knowledge graph construction module includes: Collect data sources for building knowledge graphs, including existing knowledge bases; Extract entity attributes and relationships from data sources; Fuse the extracted new knowledge with the structured data of the existing knowledge base; First, define the data structure for the knowledge graph, then add the entities to the knowledge base. The nodes of the constructed data structure include fault information, fault factors, equipment type, equipment fault, possible fault causes, tools, processing steps, and historical fault solutions. The knowledge after knowledge fusion is added to the knowledge base to build a complete knowledge graph. Specifically, it includes: 1) Data collection: Collect data sources used to build knowledge graphs, including structured data (such as records in databases), machine-readable open ontologies or dictionaries, open linked data and open knowledge bases, industry knowledge bases and industry vertical websites, online encyclopedias (such as Wikipedia, Hudong Baike, etc.) and text data, etc. Collection methods such as open linked data collection, encyclopedia collection, and text information collection (using web crawlers and subject crawlers) can be used.

[0025] 2) Knowledge Representation: Knowledge representation level: Logical layer: Use logical storage solutions such as RDF, WIDETABLE, Property Graph, etc., and map them to each other. Storage layer: Use serialized file exchange formats such as JSON-LD, N-TRIPLE, EXCEL / CSV, etc. Computational layer: Involves explicit (entity relationship network) and implicit (distributed representation) knowledge association and reasoning.

[0026] 3) Knowledge extraction and fusion Knowledge extraction: Automatically identify named entities (including names of people, places, institutions, proper nouns, etc.) from data elements, which is called entity extraction or named entity recognition (NER). Extracting term pairs that represent the same concept, entity, or attribute is called synonymous relationship extraction. Automatically identify the information pair relationship consisting of entities, attributes, and attribute values, which is called entity attribute extraction. Extracting the association relationship between entities from related corpus is called relationship extraction.

[0027] Knowledge fusion: Integrate the extracted new knowledge with the existing knowledge in the knowledge base, process and integrate duplicate, similar, and erroneous knowledge accordingly, and achieve knowledge disambiguation and fusion. The RDF graph model can be used to integrate knowledge from different fields, structures, and formats.

[0028] 4) Knowledge graph construction Construction method: Use the top-down method: first define the data structure for the knowledge graph, and then add the entity to the knowledge base. The constructed data structure includes nodes such as fault information, fault factors, equipment type, equipment fault, possible fault causes, tools, processing steps, and historical fault solutions. Extract knowledge from the collected data to form a network knowledge structure. Perform knowledge fusion to eliminate redundancy and ambiguity between knowledge. Store the integrated knowledge in the knowledge base to build a complete knowledge graph.

[0029] In one embodiment of the present invention, preferably, it further comprises: An update module is connected to the operation and maintenance module. The update module is used to extract knowledge from the acquired new fault assessment results and maintenance plan information and integrate them into the knowledge graph. The update module continuously updates the knowledge graph, which can ensure the timeliness and accuracy of the knowledge graph and improve the accuracy and efficiency of subsequent fault matching.

[0030] In one embodiment of the present invention, preferably, it further comprises: The skill level management module is used to record maintenance personnel and their corresponding maintenance skill levels. The skill level management module is connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to maintenance personnel based on the results of multiple fault assessments and maintenance skill levels. It is in the processing step node of the knowledge graph. Through reasonable task allocation, this module can ensure the smooth progress of maintenance work and improve maintenance efficiency and quality.

[0031] In one embodiment of the present invention, preferably, it further comprises: The intelligent machine management module is used to record intelligent machines and their corresponding intelligent maintenance technology types. The intelligent machine management module is connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to each intelligent machine based on the results of multiple fault assessments and the types of intelligent maintenance technologies. It is located in the tool node of the knowledge graph. By introducing intelligent machines and intelligent maintenance technologies, this module can further improve the intelligence level and efficiency of operation and maintenance work.

[0032] In one embodiment of the present invention, preferably, it further comprises: The interactive module is used to receive the demand information input by the user and display the maintenance plan information. Through the friendly user interface and interactive design, this module can facilitate users to query the progress of fault handling, submit demand information and other operations. At the same time, this module can also display the maintenance plan information in real time to help users understand the overall situation and schedule of operation and maintenance work.

[0033] The urban rail transit intelligent operation and maintenance system of the present invention, based on the knowledge graph, realizes rapid identification, accurate positioning, efficient processing and intelligent operation and maintenance management of faults.

[0034] In order to enable those skilled in the art to better understand the technical solution of the present invention, the following embodiments are provided for further explanation: The present invention provides an urban rail transit intelligent operation and maintenance system based on a knowledge graph, comprising: Rail transit fault collection module, which is used to collect fault report information of each fault generated during the operation of the urban rail transit system in real time; This module is responsible for collecting fault report information of each fault generated during the operation of the urban rail transit system in real time. Optionally, this information includes but is not limited to key data such as the time, location, type, and impact range of the fault. Through the arrangement and technical means such as sensor network and video monitoring, it is possible to achieve comprehensive monitoring of the operation of the urban rail transit system and ensure timely collection and accurate recording of fault information.

[0035] A fault element extraction module is communicatively connected to the rail transit fault collection module and is used to receive fault report information and extract elements of the fault report information one by one to obtain fault element information in the fault report information that can comprehensively cover each of the faults; optionally, the fault element extraction module uses natural language processing and data mining to extract fault element information that can comprehensively cover each fault from the fault report information, including fault phenomenon, fault location, fault level, etc., to provide key data support for subsequent fault matching.

[0036] A fault matching module is used to match the fault factor information of each fault with the knowledge graph of historical faults and output the matching result; more preferably, the fault matching module is based on a pre-built and continuously updated historical fault knowledge graph library, which contains a wealth of fault cases, fault solutions and fault handling experience. The fault matching module accurately matches the fault factor information of each fault, compares and analyzes it with historical fault cases, and quickly outputs the matching result, including possible causes of the fault, historical solutions and success rates, relevant expert advice and other information, and provides a matching score to assist operation and maintenance personnel in quickly locating problems; The operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module and provides maintenance plan information. More preferably, the operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module, including the severity of the faults, the scope of impact, the processing priority, etc. Based on the evaluation results, the operation and maintenance module automatically generates maintenance plan information, including maintenance tasks, required resources, estimated completion time, etc. At the same time, the operation and maintenance module also has a dynamic adjustment function, which can automatically adjust the maintenance plan according to the real-time feedback during the fault handling process to ensure the flexibility and efficiency of the operation and maintenance work.

[0037] A knowledge graph construction module, which is used to construct the knowledge graph of the historical faults. The knowledge graph construction module extracts relevant entities, attributes and relationships of the historical faults to form nodes and edges of the knowledge graph. Optionally, the knowledge graph construction process includes multiple steps such as data preprocessing, entity recognition, relationship extraction, and graph construction. By continuously optimizing and improving the knowledge graph, the accuracy and timeliness of the knowledge graph can be ensured, providing a reliable data foundation for subsequent fault matching. The knowledge graph includes fault phenomena, fault causes, and fault solutions. Collect data sources for constructing the knowledge graph, including existing knowledge bases; Extract entity attributes and relationships from data sources; Fuse the extracted new knowledge with the existing knowledge in the existing knowledge base; First, define the data structure for the knowledge graph, then add the entities to the knowledge base. The nodes of the constructed data structure include fault information, fault factors, equipment type, equipment fault, possible fault causes, tools, processing steps, and historical fault solutions. The knowledge after knowledge fusion is added to the knowledge base to build a complete knowledge graph. Specifically, it includes: 1) Data collection: Collect data sources used to build knowledge graphs, including structured data (such as records in databases), machine-readable open ontologies or dictionaries, open linked data and open knowledge bases, industry knowledge bases and industry vertical websites, online encyclopedias (such as Wikipedia, Hudong Baike, etc.) and text data, etc. Collection methods such as open linked data collection, encyclopedia collection, and text information collection (using web crawlers and subject crawlers) can be used.

[0038] 2) Knowledge representation and data structure: Knowledge representation level: Logical layer: Use logical storage solutions such as RDF, WIDETABLE, Property Graph, etc., and map them to each other. Storage layer: Use serialized file exchange formats such as JSON-LD, N-TRIPLE, EXCEL / CSV, etc. Computational layer: Involves explicit (entity relationship network) and implicit (distributed representation) knowledge association and reasoning.

[0039] Data structure: Determine the core data structure of the knowledge graph, including data (entities, ontologies, statements) and metadata (version management, information traceability).

[0040] 3) Knowledge extraction and fusion Knowledge extraction: Automatically identify named entities (including names of people, places, institutions, proper nouns, etc.) from text datasets, which is called entity extraction or named entity recognition (NER). Extracting term pairs that represent the same concept, entity, or attribute is called synonymous relationship extraction. Automatically identify the information pair relationship consisting of entities, attributes, and attribute values, which is called entity attribute extraction. Extracting the association relationship between entities from related corpus is called relationship extraction.

[0041] Knowledge fusion: Integrate the extracted new knowledge with the existing knowledge in the knowledge base, process and integrate duplicate, similar, and erroneous knowledge accordingly, and achieve knowledge disambiguation and fusion. The RDF graph model can be used to integrate knowledge from different fields, structures, and formats.

[0042] 4) Knowledge graph construction Construction method: Use the top-down method: first define the data structure for the knowledge graph, and then add the entity to the knowledge base. The constructed data structure includes nodes such as fault information, fault factors, equipment type, equipment fault, possible fault causes, tools, processing steps, and historical fault solutions. Extract knowledge from the collected data to form a network knowledge structure. Perform knowledge fusion to eliminate redundancy and ambiguity between knowledge. Store the integrated knowledge in the knowledge base to build a complete knowledge graph.

[0043] An update module is connected to the operation and maintenance module. The update module is used to extract knowledge from the acquired new fault assessment results and maintenance plan information and integrate them into the knowledge graph. The update module continuously updates the knowledge graph, which can ensure the timeliness and accuracy of the knowledge graph and improve the accuracy and efficiency of subsequent fault matching.

[0044] The skill level management module is used to record maintenance personnel and their corresponding maintenance skill levels. The skill level management module is connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to maintenance personnel based on the results of multiple fault assessments and maintenance skill levels. It is in the processing step node of the knowledge graph. Through reasonable task allocation, this module can ensure the smooth progress of maintenance work and improve maintenance efficiency and quality.

[0045] The intelligent machine management module is used to record intelligent machines and their corresponding intelligent maintenance technology types. The intelligent machine management module is connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to each intelligent machine based on the results of multiple fault assessments and the types of intelligent maintenance technologies. It is located in the tool node of the knowledge graph. By introducing intelligent machines and intelligent maintenance technologies, this module can further improve the intelligence level and efficiency of operation and maintenance work.

[0046] The interactive module is used to receive the demand information input by the user and display the maintenance plan information. Through the friendly user interface and interactive design, this module can facilitate users to query the progress of fault handling, submit demand information and other operations. At the same time, this module can also display the maintenance plan information in real time to help users understand the overall situation and schedule of operation and maintenance work.

[0047] The number of modules and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention are obvious to those skilled in the art.

[0048] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.

Claims

1. An urban rail transit intelligent operation and maintenance system based on knowledge graph, characterized in that: include: Rail transit fault collection module, which is used to collect fault report information of each fault generated during the operation of the urban rail transit system in real time; A fault element extraction module, which is in communication connection with the rail transit fault collection module and is used to receive fault report information and extract elements of the fault report information one by one, so as to obtain fault element information in the fault report information that can fully cover each of the faults; A fault matching module is used to match the fault factor information of each fault with the knowledge graph of historical faults and output the matching result; The operation and maintenance module evaluates multiple faults according to the matching results output by the fault matching module and provides maintenance plan information.

2. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 1, characterized in that: Also includes: A knowledge graph construction module is used to construct the knowledge graph of the historical faults. The knowledge graph construction module extracts relevant entities, attributes and relationships of the historical faults to form nodes and edges of the knowledge graph.

3. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 1, characterized in that: The process of constructing the knowledge graph by the knowledge graph construction module includes: Collect data sources for building knowledge graphs, including existing knowledge bases; Extract entity attributes and relationships from data sources; Fuse the extracted new knowledge with the existing knowledge in the existing knowledge base; First, define the data structure for the knowledge graph, and then add the entities to the knowledge base. The nodes of the constructed data structure include fault information, fault factors, equipment type, equipment failure, possible causes of failure, tools, processing steps, and historical fault solutions. The knowledge after knowledge fusion is added to the knowledge base to construct a complete knowledge graph.

4. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 1, characterized in that: Also includes: An update module is communicatively connected to the operation and maintenance module, and is used to extract knowledge from the acquired new fault assessment results and maintenance plan information, and integrate them into the knowledge graph.

5. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 4, characterized in that: Also includes: A skill level management module is used to record maintenance personnel and their corresponding maintenance skill levels. The skill level management module is communicatively connected to the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to maintenance personnel based on the results of multiple fault assessments and maintenance skill levels. The maintenance personnel are located in the maintenance step node of the knowledge graph.

6. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 4, characterized in that: Also includes: An intelligent machine management module is used to record intelligent machines and their corresponding intelligent maintenance technology types. The intelligent machine management module is communicated with the operation and maintenance module. The operation and maintenance module assigns fault maintenance tasks to each intelligent machine based on the results of multiple fault assessments and the types of intelligent maintenance technologies. The intelligent machine is in the tool node of the knowledge graph.

7. The urban rail transit intelligent operation and maintenance system based on knowledge graph according to claim 1, characterized in that: Also includes: The interactive module is used to receive demand information input by the user and display maintenance plan information.