Coal mine potential safety hazard characterization method and system based on knowledge graph

Abstract

The invention relates to a coal mine potential safety hazard characterization method and system based on a knowledge graph, and belongs to the technical field of coal mine safety. The method comprises the following steps: data collection: collecting coal mine daily safety inspection records including hidden danger types, occurrence places, time and related descriptions; data preprocessing: cleaning, classifying and standardizing the collected data so as to facilitate subsequent knowledge extraction and graph construction; and knowledge graph construction: based on the preprocessed data, identifying key entities, extracting relationships among the entities, and constructing a coal mine potential safety hazard knowledge graph. Through the hidden danger correlation analysis and risk assessment module in the knowledge graph, the system can assess the risk degrees of different hidden dangers in real time and generate corresponding early warning information according to the assessment result, and the dynamic early warning mechanism enables managers to master the safety condition of a coal mine in time and quickly respond to potential safety threats.

Description

Technical Field

[0001] The present invention belongs to the field of coal mine safety technology and relates to a method and system for characterizing coal mine safety hazards based on a knowledge graph. Background Art

[0002] The occurrence of coal mine disasters is affected by factors such as diverse underground geological conditions and complex production environment, and the occurrence of disasters is becoming more and more random and ambiguous. The risk of coal mine accidents is significantly correlated with the number and level of hidden dangers. If risk control measures and hidden danger management measures are missing or ineffective, it is very likely to evolve into an accident. At present, a series of regulations and standards such as "Coal Mine Safety Regulations", "Basic Requirements and Scoring Methods for Coal Mine Safety Standardization (Trial)", and "Criteria for Determining Major Coal Mine Production Safety Accident Hazards" have been issued and revised one after another, aiming to establish and improve the standardized management system of coal mine safety production, promptly eliminate major coal mine accident hazards, and implement the safety production responsibility system and safety management system, which has promoted the continuous improvement of coal mine safety management level.

[0003] There are many types of safety hazards in coal mines, involving mining, electromechanical, transportation, ventilation, geodesy and other disciplines. At present, most coal mines only conduct routine inspections and rectifications of daily safety hazards, and there are no practical methods and tools to reflect the relationship between safety hazards in coal mines. As a result, the inspection and rectification of safety hazards in coal mines are done independently, and the potential relationship between the various elements of safety hazards is not fully recognized. The data link of hazards is not fully opened, and there is a lack of understanding of the concrete expression of safety hazards. Therefore, it is impossible to eliminate the hazards that may cause disasters in time during the incubation period of disasters, and it is impossible to effectively support the prevention and control of coal mine safety production.

[0004] In order to ensure the safe production of coal mines, effective identification and management of safety hazards are particularly important. Traditional coal mine safety management mainly relies on manual inspection and empirical judgment, including regular on-site inspections, sample testing, and manual analysis of monitoring data. Although these methods have played a certain role in safety management in the past, they have obvious limitations. First, manual inspections are inefficient and cannot achieve full-scale and full-time monitoring coverage of coal mines. Second, manual inspections and empirical judgments are easily affected by personal experience and subjectivity.

[0005] Therefore, there is an urgent need for a method that can objectively characterize coal mine safety hazards to overcome the above problems. Summary of the invention

[0006] In view of this, the purpose of the present invention is to provide a method and system for characterizing coal mine safety hazards based on a knowledge graph. Through the hazard association analysis and risk assessment module in the knowledge graph, the system can evaluate the risk levels of different hazards in real time and generate corresponding warning information based on the assessment results. This dynamic warning mechanism enables managers to grasp the safety status of coal mines in a timely manner and respond quickly to potential safety threats.

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

[0008] Scenario 1:

[0009] A method for characterizing coal mine safety hazards based on knowledge graph, specifically comprising the following steps:

[0010] S1: Data collection: Collect daily safety inspection records of coal mines, including the type of hidden dangers, location, time and related descriptions;

[0011] S2: Data preprocessing: Clean, classify and standardize the collected data to facilitate subsequent knowledge extraction and graph construction;

[0012] S3: Knowledge graph construction: Based on the preprocessed data, identify key entities, extract the relationships between entities, and construct a knowledge graph of coal mine safety hazards;

[0013] S4: Hidden danger association analysis: Use the constructed coal mine safety hidden danger knowledge map to analyze the association between hidden dangers and the correlation between hidden dangers and accidents;

[0014] S5: Risk assessment: Based on the results of hidden danger correlation analysis, evaluate the potential risk level of different hidden dangers to coal mine safety production;

[0015] S6: Early warning generation: Based on the results of risk assessment, safety hazard early warning information is generated and pushed to relevant managers.

[0016] Further, step S1 specifically includes:

[0017] (1) Entity recognition: extract key entities from the hazard description, including equipment name, operation location, and operation type;

[0018] (2) Relationship extraction: determine the relationships between entities, including hazard-location relationships, hazard-time relationships, and hazard-hazard relationships;

[0019] (3) Data fusion: Fusion of relevant information in structured data and unstructured data to improve the integrity of knowledge.

[0020] Further, step S4 specifically includes the following steps:

[0021] S41: Association rule mining: Use data mining algorithms to discover association rules between hidden dangers, and use support and confidence to measure the strength of association rules between hidden dangers. The calculation formulas for support and confidence are as follows:

[0022] Support:

[0023] Confidence:

[0024] Among them, P(X∩Y) is the probability of hidden danger X and hidden danger Y occurring at the same time, and P(X) is the probability of hidden danger X occurring;

[0025] S42: Pattern recognition: Identify the patterns and trends of hidden dangers and provide a basis for risk assessment;

[0026] S43: Network analysis: Identify key potential risk nodes and potential risk groups by analyzing the network structure in the knowledge graph.

[0027] Further, step S5 specifically includes the following steps:

[0028] S51: Risk quantification: Assign a risk value to each hazard based on its frequency of occurrence and potential consequences;

[0029] The risk quantification formula is:

[0030]

[0031] Where P(X) is the probability (frequency) of occurrence of hidden danger X; S(X) is the potential consequence (severity) of hidden danger X, estimated based on historical accident data; n is the number of other hidden dangers associated with hidden danger X; w i is the i-th hidden danger Y associated with hidden danger X i The influence weight on X; I(X,Y i ) is hidden danger X and hidden danger Y i The interaction effect function between them;

[0032] S52: Risk Propagation Analysis: Analyze the risk propagation path and impact range of potential risk nodes in the knowledge graph, and use the PageRank algorithm to evaluate the importance of potential risk nodes;

[0033] The basic formula of PageRank algorithm is:

[0034]

[0035] Where PR(A) is the risk propagation value of the potential risk node A; d is the damping coefficient; N is the total number of potential risk nodes; P(B) is the set of all nodes pointing to node A; L(B) is the number of links from node B to other nodes;

[0036] S53: Comprehensive assessment: Comprehensively consider the type, quantity, correlation and time series data of hidden dangers, and output a comprehensive risk assessment report.

[0037] Further, step S6 specifically includes:

[0038] (1) Warning level setting: setting warning thresholds of different levels based on the results of risk assessment;

[0039] (2) Warning information formatting: formatting warning information into standardized messages to facilitate understanding and dissemination;

[0040] (3) Early warning release: Early warning information is pushed to relevant management personnel in real time through the communication system within the coal mine.

[0041] Scenario 2:

[0042] A coal mine safety hazard characterization system based on knowledge graph, including:

[0043] Data collection module, used to collect data related to coal mine safety;

[0044] Knowledge graph construction module, used to construct coal mine safety knowledge graph;

[0045] Hidden danger analysis module, which uses knowledge graph to identify and analyze safety hazards;

[0046] Hidden danger risk assessment and display module, used to output and display safety hazard characterization results;

[0047] The data collection module collects coal mine safety data in real time and transmits it to the knowledge graph construction module through an automated interface. The module updates the knowledge graph to reflect the latest safety status. The hidden danger analysis module uses the knowledge graph to extract the correlation between hidden dangers and inputs the analysis results into the risk assessment module unit in the hidden danger analysis module. The risk assessment module unit quantifies the risk and triggers the generation of early warnings. The early warning information is notified to the management personnel in real time through the communication system within the coal mine. The user interaction interface provides real-time data query and system management functions to ensure the responsiveness and adaptability of the system.

[0048] Preferably, the data collection module includes a historical safety accident data collection unit, a current operating environment data collection unit and an equipment operation status data collection unit;

[0049] The historical safety accident data collection unit is responsible for collecting and storing the safety accident data that occurred in the past, including the accident type, occurrence time, impact scope and loss caused;

[0050] The current working environment data acquisition unit is used to monitor and record the current working environment data in real time, such as temperature, humidity, noise level, etc., and collect data through corresponding sensors;

[0051] The equipment operation status data acquisition unit is used to monitor the operation status of the equipment, including startup time, load conditions and fault records, so as to evaluate the health status and potential risks of the equipment.

[0052] Preferably, the knowledge graph construction module includes an entity relationship determination unit and a structured knowledge representation unit;

[0053] The entity relationship determination unit is responsible for identifying and defining the relationship between different entities (equipment, personnel, and operation processes) as the basis for building a knowledge graph;

[0054] The structured knowledge representation unit is used to convert the collected data and entity relationships into a structured knowledge representation form.

[0055] Preferably, the hidden danger analysis module includes a graph query unit and a risk assessment unit;

[0056] The graph query unit uses the constructed knowledge graph to retrieve relevant safety hazard information through a graph query language;

[0057] The risk assessment unit performs a quantitative assessment of potential risks based on the query results and a preset risk assessment model.

[0058] The beneficial effects of the present invention are:

[0059] 1) The present invention uses a data acquisition module to monitor the operating environment and equipment status in real time, combines historical safety accident data with current operating environment data, and forms a comprehensive knowledge map. This method can not only quickly identify potential safety hazards, but also reveal the potential risks and mutual influence of hidden dangers through correlation analysis between hidden dangers, thereby providing managers with a more scientific and reliable decision-making basis. In this way, coal mining enterprises can achieve more efficient safety management and reduce the probability of accidents.

[0060] 2) Through the hidden danger association analysis and risk assessment module in the knowledge graph, the system of the present invention can evaluate the risk level of different hidden dangers in real time, and generate corresponding early warning information according to the evaluation results. This dynamic early warning mechanism enables managers to grasp the safety status of coal mines in a timely manner and respond quickly to potential safety threats. For example, when the risk value of a certain hidden danger exceeds the set threshold, the system will automatically generate early warning information and push it to relevant managers in real time through the communication system inside the coal mine. The timely early warning mechanism not only improves the safety prevention capability of coal mines, but also effectively reduces the occurrence of accidents.

[0061] 3) Through the continuous collection, analysis and updating of hidden danger data, the system of the present invention can continuously improve and enrich the knowledge graph to form a dynamic safety management platform, which can not only help enterprises identify and manage current safety hazards, but also discover the patterns and trends of hidden dangers through the analysis of historical data, providing valuable reference for future safety management.

[0062] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0064] Figure 1 It is a flow chart of the method for characterizing safety hazards in coal mines based on knowledge graph of the present invention;

[0065] Figure 2 This is a flow chart of the coal mine safety hazard characterization system based on the knowledge graph of the present invention. DETAILED DESCRIPTION

[0066] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0067] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0068] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0069] See also Figure 1-2 , Figure 1 The figure shows a method for characterizing safety hazards in coal mines based on a knowledge graph, which includes the following steps:

[0070] S1: Data collection: Collect daily safety inspection records of coal mines, including the type of hidden dangers, location, time and related descriptions, to ensure the comprehensiveness and timeliness of the information.

[0071] Step S1, i.e. data collection, is the foundation, and the entity recognition, relationship extraction and data fusion contained therein are key pre-steps. Entity recognition extracts key entities from the hidden danger description, such as equipment name, operation location and operation type, which helps to accurately grasp the specific elements related to the hidden danger. Then, relationship extraction determines the relationship between entities, including the relationship between hidden danger and location, hidden danger and time, and hidden danger and hidden danger, which helps to understand the environment and conditions of hidden dangers and the mutual influence between hidden dangers. Finally, data fusion integrates relevant information in structured data and unstructured data to improve the integrity of knowledge and ensure that the knowledge graph covers a wide range and depth. These steps work together to provide a rich, accurate and structured data foundation for the construction of the knowledge graph, which is helpful for the hidden danger association analysis, risk assessment and early warning generation in the subsequent steps, and ultimately significantly improves the efficiency of identifying and managing coal mine safety hazards and ensures the safety of miners.

[0072] S2: Data preprocessing: Clean, classify and standardize the collected data to improve data availability and lay a solid foundation for knowledge extraction and graph construction.

[0073] S3: Knowledge graph construction: Based on the preprocessed data, key entities are identified and the relationships between entities are extracted to form a knowledge structure of coal mine safety hazards, which helps to clearly understand the complex connections between hazards.

[0074] S4: Hazard correlation analysis: Use the constructed coal mine safety hazard knowledge graph to analyze the correlation between hazards and the correlation between hazards and accidents, revealing potential risk points.

[0075] Step S4, i.e., hidden danger association analysis, is a key step, including association rule mining, pattern recognition, and network analysis. Association rule mining discovers association rules between hidden dangers through data mining algorithms, and uses support and confidence to measure the strength of these rules, thereby revealing the potential connections between hidden dangers. Pattern recognition focuses on identifying the patterns and trends of hidden dangers, providing a direct basis for risk assessment. Finally, network analysis analyzes the network structure in the knowledge graph, identifies key hidden danger nodes and hidden danger groups, and helps decision makers understand the impact scope and propagation path of hidden dangers. Through the combined effect of these analysis steps, it provides in-depth insights for the systematic management of coal mine safety hazards, making risk management more scientific and accurate.

[0076] S5: Risk assessment: Based on the results of hidden danger correlation analysis, evaluate the potential risk level of different hidden dangers to coal mine safety production, and realize precise and scientific risk management.

[0077] Step S5, i.e., risk assessment, is the core link, including risk quantification, risk propagation analysis, and comprehensive assessment. Risk quantification assigns a risk value to each hidden danger by considering the probability of occurrence, potential consequences, and the number and impact weight of other hidden dangers associated with it, thereby accurately reflecting the severity of the hidden danger. This process is quantified by a formula, in which the probability of occurrence and potential consequences are estimated based on historical accident data, while the number of other hidden dangers associated with the hidden danger, the impact weight, and the interactive influence function between hidden dangers reflect the complex relationship between hidden dangers. Subsequently, the risk propagation analysis uses the PageRank algorithm to evaluate the importance of hidden danger nodes, analyze the risk propagation path and impact range of hidden danger nodes in the knowledge graph, reveal the mutual influence between hidden dangers, help identify key hidden danger nodes that need to be handled first, and understand how risks propagate throughout the system. Finally, the comprehensive assessment comprehensively considers the type, quantity, correlation, and time series data of hidden dangers, and outputs a comprehensive risk assessment report. This report provides decision makers with comprehensive risk information, including the distribution of hidden dangers, risk levels, and potential impact ranges, so that more scientific and effective risk management strategies can be formulated.

[0078] S6: Early warning generation: Generate safety hazard early warning information based on the results of risk assessment and push it to relevant management personnel in a timely manner to achieve real-time monitoring and early warning, thereby effectively preventing accidents, ensuring the safety of miners, and significantly improving the safety management level of coal mines.

[0079] Step S6, i.e., warning generation, is a key link, including warning level setting, warning information formatting, and warning release. Warning level setting sets warning thresholds of different levels according to the results of risk assessment, ensuring the accuracy and timeliness of warning information, so that managers can take corresponding countermeasures according to the risk level. Warning information formatting formats warning information into standardized messages for easy understanding and dissemination, thereby improving the efficiency and accuracy of information transmission. Finally, warning release pushes warning information to relevant managers in real time through the communication system within the coal mine, achieving timely warning response and providing support for rapid and effective disaster prevention and emergency response.

[0080] Figure 2 The figure shows a coal mine safety hazard characterization system based on a knowledge graph, including a data collection module for collecting coal mine safety-related data; a knowledge graph construction module for constructing a coal mine safety knowledge graph; a hazard analysis module for identifying and analyzing safety hazards using the knowledge graph; and a hazard characterization module for outputting and displaying safety hazard characterization results.

[0081] The data collection module includes a historical safety accident data collection unit, a current operating environment data collection unit, and an equipment operation status data collection unit;

[0082] Historical safety accident data collection unit: responsible for collecting and storing historical safety accident data, including accident type, time of occurrence, scope of impact, losses caused, etc.

[0083] Current working environment data acquisition unit: used to monitor and record the current working environment data in real time, such as temperature, humidity, noise level, etc., and collect data through corresponding sensors.

[0084] Equipment operation status data acquisition unit: monitors the operation status of the equipment, including startup time, load conditions, fault records, etc., to assess the health status and potential risks of the equipment.

[0085] The knowledge graph construction module further includes an entity relationship determination unit and a structured knowledge representation unit;

[0086] The entity relationship determination unit is responsible for identifying and defining the relationships between different entities (equipment, personnel, and work processes) as the basis for building the knowledge graph;

[0087] The structured knowledge representation unit transforms the collected data and entity relationships into a structured knowledge representation.

[0088] The hidden danger analysis module includes a graph query unit and a risk assessment unit;

[0089] The graph query unit uses the constructed knowledge graph to retrieve relevant safety hazard information through the graph query language;

[0090] The risk assessment unit conducts a quantitative assessment of potential risks based on the query results and the preset risk assessment model.

[0091] The data collection module comprehensively collects historical safety accident data, current operating environment data, and equipment operating status data, ensuring the comprehensiveness and real-time nature of the data. On this basis, the knowledge graph construction module identifies and defines the relationship between different entities through the entity relationship determination unit, and then the structured knowledge representation unit converts the data into a structured knowledge representation form to construct an intuitive knowledge structure, which is convenient for understanding the complex relationship between hidden dangers. The graph query unit in the hidden danger analysis module uses the knowledge graph to efficiently retrieve relevant information, and the risk assessment unit combines the preset model to quantitatively assess potential risks, thereby accurately identifying and analyzing safety hazards. Finally, the result output module intuitively displays the results of the safety hazard characterization, providing strong support for safety management. This system not only improves the efficiency and accuracy of risk identification, but also provides a solid foundation for the realization of scientific risk management, significantly improving the safety management level of coal mines.

[0092] The data collection module collects coal mine safety data in real time and transmits it to the knowledge graph construction module through an automated interface. The module updates the knowledge graph to reflect the latest safety status. The hidden danger association analysis module uses the knowledge graph to extract the correlation between hidden dangers and inputs the analysis results into the risk assessment module. The risk assessment module quantifies risks and triggers early warning generation. The early warning information is notified to management personnel in real time through the communication system within the coal mine. The user interaction interface provides real-time data query and system management functions to ensure the responsiveness and adaptability of the system.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A method for characterizing coal mine safety hazards based on knowledge graph, characterized in that: The method specifically comprises the following steps: S1: Data collection: Collect daily safety inspection records of coal mines, including the type of hidden dangers, location, time and related descriptions; S2: Data preprocessing: cleaning, classification and standardization of collected data; S3: Knowledge graph construction: Based on the preprocessed data, identify key entities, extract the relationships between entities, and construct a knowledge graph of coal mine safety hazards; S4: Hidden danger association analysis: Use the constructed coal mine safety hidden danger knowledge map to analyze the association between hidden dangers and the correlation between hidden dangers and accidents; S5: Risk assessment: Based on the results of hidden danger correlation analysis, evaluate the potential risk level of different hidden dangers to coal mine safety production; S6: Early warning generation: Based on the results of risk assessment, safety hazard early warning information is generated and pushed to relevant managers.

2. The method for characterizing safety hazards in coal mines according to claim 1, characterized in that: Step S1 specifically includes: (1) Entity recognition: extract key entities from the hazard description, including equipment name, operation location, and operation type; (2) Relationship extraction: determine the relationships between entities, including hazard-location relationships, hazard-time relationships, and hazard-hazard relationships; (3) Data fusion: Fusion of relevant information in structured data and unstructured data.

3. The method for characterizing safety hazards in coal mines according to claim 1, characterized in that: Step S4 specifically includes the following steps: S41: Association rule mining: Use data mining algorithms to discover association rules between hidden dangers, and use support and confidence to measure the strength of association rules between hidden dangers. The calculation formulas for support and confidence are as follows: Support: Confidence: Among them, P(X∩Y) is the probability of hidden danger X and hidden danger Y occurring at the same time, and P(X) is the probability of hidden danger X occurring; S42: Pattern recognition: Identify the patterns and trends of hidden dangers and provide a basis for risk assessment; S43: Network analysis: Identify key potential risk nodes and potential risk groups by analyzing the network structure in the knowledge graph.

4. The method for characterizing safety hazards in coal mines according to claim 1, characterized in that: Step S5 specifically includes the following steps: S51: Risk quantification: Assign a risk value to each hazard based on its frequency of occurrence and potential consequences; The risk quantification formula is: Where P(X) is the probability of occurrence of hidden danger X; S(X) is the potential consequence of hidden danger X, estimated based on historical accident data; n is the number of other hidden dangers associated with hidden danger X; w i is the ith hidden danger Y associated with hidden danger X i The influence weight on X; I(X,Y i ) is hidden danger X and hidden danger Y i The interaction effect function between them; S52: Risk Propagation Analysis: Analyze the risk propagation path and impact range of potential risk nodes in the knowledge graph, and use the PageRank algorithm to evaluate the importance of potential risk nodes; The basic formula of PageRank algorithm is: Where PR(A) is the risk propagation value of the potential risk node A; d is the damping coefficient; N is the total number of potential risk nodes; P(B) is the set of all nodes pointing to node A; L(B) is the number of links from node B to other nodes; S53: Comprehensive assessment: Comprehensively consider the type, quantity, correlation and time series data of hidden dangers, and output a comprehensive risk assessment report.

5. The method for characterizing safety hazards in coal mines according to claim 1, characterized in that: Step S6 specifically includes: (1) Warning level setting: setting warning thresholds of different levels based on the results of risk assessment; (2) Warning information formatting: formatting warning information into standardized messages to facilitate understanding and dissemination; (3) Early warning release: Early warning information is pushed to relevant management personnel in real time through the communication system within the coal mine.

6. A coal mine safety hazard characterization system based on knowledge graph applicable to the method described in any one of claims 1 to 5, characterized in that: The system includes: Data collection module, used to collect data related to coal mine safety; Knowledge graph construction module, used to construct coal mine safety knowledge graph; Hidden danger analysis module, which uses knowledge graph to identify and analyze safety hazards; Hidden danger risk assessment and display module, used to output and display safety hazard characterization results; The data collection module collects coal mine safety data in real time and transmits it to the knowledge graph construction module through an automated interface. The module updates the knowledge graph to reflect the latest safety status. The hidden danger analysis module uses the knowledge graph to extract the correlation between hidden dangers and inputs the analysis results into the risk assessment module unit in the hidden danger analysis module. The risk assessment module unit quantifies the risk and triggers the generation of early warnings. The early warning information is notified to the management personnel in real time through the communication system within the coal mine. The user interaction interface provides real-time data query and system management functions to ensure the responsiveness and adaptability of the system.

7. The coal mine safety hazard characterization system according to claim 6, characterized in that: The data collection module includes a historical safety accident data collection unit, a current operating environment data collection unit and an equipment operation status data collection unit; The historical safety accident data collection unit is responsible for collecting and storing the safety accident data that occurred in the past, including the accident type, occurrence time, impact scope and loss caused; The current working environment data collection unit is used to monitor and record the current working environment data in real time; The equipment operation status data acquisition unit is used to monitor the operation status of the equipment, including startup time, load conditions and fault records, so as to evaluate the health status and potential risks of the equipment.

8. The coal mine safety hazard characterization system according to claim 6, characterized in that: The knowledge graph construction module includes an entity relationship determination unit and a structured knowledge representation unit; The entity relationship determination unit is responsible for identifying and defining the relationship between different entities as the basis for building a knowledge graph; The structured knowledge representation unit is used to convert the collected data and entity relationships into a structured knowledge representation form.

9. The coal mine safety hazard characterization system according to claim 6, characterized in that: The hidden danger analysis module includes a graph query unit and a risk assessment unit; The graph query unit uses the constructed knowledge graph to retrieve relevant safety hazard information through a graph query language; The risk assessment unit performs a quantitative assessment of potential risks based on the query results and a preset risk assessment model.

Images