Coal mining AI safety personalized learning method and system based on personnel data

Abstract

The present invention discloses a coal mining AI safety personalized learning method and system combined with personnel data, which relates to the field of coal mining technology, including: determining at least one type of work; determining at least one risk operation corresponding to the risk of coal mining hazards; attaching an initial learning focus index to each risk operation; determining the mutual correlation relationship between multiple risk operations; based on the mutual correlation relationship between multiple risk operations and the initial learning focus index of each risk operation, through an AI iterative algorithm, determining the final learning focus index of each risk operation. The advantages of the present invention are: it realizes the personalized scheme design of coal mining safety learning, and the learning content focuses on multiple operations that may have hidden dangers, which facilitates practitioners to quickly master the safety knowledge related to their own work type and meets the comprehensive safety learning needs of multiple types of work in coal mines.

Description

Technical Field

[0001] The present invention relates to the field of coal mining technology, and in particular to a method and system for personalized AI safety learning of coal mining that combines personnel data. Background Art

[0002] Safety in production is a top priority for the coal mining industry. To ensure safety, every measure must be taken to reduce accidents. Numerous accident investigations and analyses have shown that 70%-80% of injuries and deaths are caused by unsafe human behavior. Unsafe behavior by employees is a significant contributor to coal mining accidents, so safety training for employees is a crucial tool for reducing coal mining accidents.

[0003] Existing coal mining learning and training methods lack correlation analysis between various types of work, do not delve deeply into the causes and consequences of coal mining accidents, and lack personalized learning plans for different types of work. The learning content is single and fixed, making it difficult to meet the comprehensive safety learning needs of multiple types of work in coal mines. Summary of the Invention

[0004] In order to solve the above technical problems, a coal mining AI safety personalized learning method and system combined with personnel data is provided. This technical solution solves the above-mentioned existing coal mining learning and training methods, which lack correlation analysis between various types of work, do not deeply explore the causes and consequences of coal mining accidents, and lack personalized learning plans for different types of work. The learning content is single and fixed, and it is difficult to meet the comprehensive safety learning needs of multiple types of work in coal mines.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A coal mining AI safety personalized learning method that combines human data, including:

[0007] Obtaining the job attributes of the personnel, and classifying the personnel based on the job attributes to determine at least one job type;

[0008] Based on historical data of coal mining, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risky operation in the type of work;

[0009] Based on the degree of harm caused by hidden dangers in coal mining, initial learning focus indicators are added to each risk operation;

[0010] Based on the coal mining process, determine the interrelationships between multiple risk operations;

[0011] Based on the interrelationships between multiple risk operations and the initial learning focus indicators of each risk operation, the final learning focus indicators of each risk operation are determined through an AI iterative algorithm;

[0012] According to the final learning focus indicators of each risk operation, corresponding amounts of safety learning content are arranged for all risk operations corresponding to each type of work.

[0013] Preferably, the determining of at least one coal mining hidden danger risk corresponding to each type of work based on historical coal mining data, and determining that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work specifically includes:

[0014] Extracting at least one piece of historical coal mining accident information from historical coal mining data;

[0015] Extracting coal mining accident type keywords and coal mining accident cause keywords from historical coal mining accident information;

[0016] Based on the coal mining accident cause keywords, it is determined whether the historical coal mining accident is related to the current type of work to be determined. If so, the historical coal mining accident information is recorded as relevant historical coal mining accident information; if not, the historical coal mining accident information is recorded as irrelevant historical coal mining accident information;

[0017] Extract the coal mining accident type keywords from all relevant historical coal mining accident information, and summarize the coal mining hidden danger risks corresponding to the work types;

[0018] Determine the operation related to the type of work to be determined that corresponds to each relevant historical coal mining accident information, and record it as the risk operation corresponding to the type of work of coal mining hidden danger risk.

[0019] Preferably, the initial learning focus indicators added to each risk operation based on the degree of harm of the hidden danger risk of coal mining specifically include:

[0020] Based on historical data of coal mining, determine the accident level of each historical coal mining accident caused by each coal mining hidden danger risk;

[0021] Based on the accident level of each historical coal mining accident caused by coal mining hidden danger risk, an initial risk score is given to the coal mining hidden danger risk to obtain an initial disaster score for each coal mining hidden danger risk;

[0022] Based on the causes of each coal mining accident caused by coal mining hidden dangers, a primary and secondary judgment algorithm is used to determine the direct correlation between coal mining hidden dangers and risk operations;

[0023] Based on the initial disaster score of coal mining hidden danger risk and the direct correlation between coal mining hidden danger risk and risk operation, the initial learning focus index of risk operation is calculated through the operation focus formula;

[0024] The operation focuses on the formula:

[0025]

[0026] Where, is the initial learning focus indicator for the j-th risk operation, is the initial disaster score of the i-th coal mine mining hidden danger risk, is the direct correlation between the i-th coal mining hidden danger risk and the j-th risk operation

[0027] Spend.

[0028] Preferably, the initial risk score of the coal mining hidden danger risk is performed based on the accident level of each historical coal mining accident caused by the coal mining hidden danger risk, and the initial disaster score of each coal mining hidden danger risk is obtained specifically including:

[0029] Determine the number of extremely serious accidents, serious accidents, major accidents and ordinary accidents in each historical coal mining accident caused by coal mining hidden risks;

[0030] Calculate the initial disaster score of coal mining hidden danger risk through comprehensive evaluation formula;

[0031] The comprehensive evaluation formula is:

[0032]

[0033] Where, The numbers of particularly serious accidents, serious accidents, major accidents and general accidents in each historical coal mining accident caused by the hidden dangers of coal mining are respectively: The total number of historical coal mining accidents caused by coal mining hidden risks, Provide initial disaster scoring for coal mining hidden danger risks.

[0034] Preferably, the primary and secondary judgment algorithm is specifically as follows:

[0035] Determine the direct operational cause of each coal mining accident caused by coal mining hidden risks, and count the indirect operational causes of each coal mining accident;

[0036] Count the number of risk operations as direct and indirect causes of operations respectively;

[0037] Based on the primary and secondary correlation formula, the direct correlation between the risk of hidden dangers in coal mining and risk operations is calculated;

[0038] The primary and secondary correlation formula is specifically:

[0039]

[0040] Where, is the total number of coal mining accidents caused by the hidden dangers of coal mining in the i-th coal mine, is the number of the jth risk operation as the direct cause of the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operating causes of the j-th risk operation in the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operational causes in the tth coal mining accident caused by the i-th coal mining hidden danger risk.

[0041] Preferably, the determining of the interrelationships between multiple risk operations based on the coal mining process specifically includes:

[0042] Based on the coal mining process, determine the subsequent risk operations that will occur if the risk operation is executed, and build a subordinate risk operation library for the risk operations;

[0043] At the same time, determine the preceding risk operations that may lead to the occurrence of risk operations, and build a superior risk operation library for risk operations.

[0044] Preferably, the AI ​​iterative algorithm is specifically:

[0045] S1. Set an iteration index E and assign E an initial value of 1;

[0046] S2. Use the initial learning focus indicator of each risk operation as the initial iteration indicator of the risk operation, that is, ,in, is the E-th generation iteration indicator of the j-th risk operation;

[0047] The value of S3 and E increases by one;

[0048] S4. Calculate by iterative formula ;

[0049] S5. Determine whether the iteration termination condition is met. If so, output the calculated E-th generation iteration index of the risk operation as the final learning emphasis index of the risk operation. If not, return to step S3.

[0050] The iterative formula is specifically:

[0051]

[0052] Where, is the total number of elements in the lower-level risk operation library of the j-th risk operation, is the first risk operation in the subordinate risk operation library of the jth risk operation The E-1th generation iteration index of elements, is the first risk operation in the subordinate risk operation library of the jth risk operation The total number of elements in the parent risk operation library of the element.

[0053] Preferably, the iteration termination condition is specifically:

[0054]

[0055] Where, is the iteration error threshold, the value range of the iteration error threshold is 0.01-0.1, is the total number of risky operations.

[0056] Preferably, the arrangement of corresponding safety learning content for all risk operations corresponding to each work type according to the final learning emphasis indicator of each risk operation specifically includes:

[0057] Obtain the final learning focus indicators for all risk operations corresponding to the work type;

[0058] The final learning focus indexes of all risk operations corresponding to the work type are summed to obtain the first learning index of the work type;

[0059] Compare the final learning focus indicator of each risk operation corresponding to the job type with the first learning indicator of the job type to obtain the learning content proportion of each risk operation corresponding to the job type;

[0060] Arrange corresponding amounts of safety learning content based on the proportion of learning content for each risk operation corresponding to the type of work.

[0061] Furthermore, a coal mining AI safety personalized learning system combining personnel data is proposed, which is used to implement the above-mentioned coal mining AI safety personalized learning method combining personnel data, including:

[0062] A storage center, the storage center is used to store historical data of coal mining;

[0063] a risk operation analysis module, the risk operation analysis module being electrically connected to the storage center, and configured to extract a plurality of pieces of the latest historical coal mining accident information from historical coal mining data, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work;

[0064] an initial hidden danger analysis module, the initial hidden danger analysis module being electrically connected to the storage center and the risk operation analysis module, and configured to add an initial learning focus indicator to each risk operation based on the degree of harm of the hidden danger risk of coal mining;

[0065] an AI iterative analysis module, the AI ​​iterative analysis module being electrically connected to the initial hidden danger analysis module and the storage center, the AI ​​iterative analysis module being configured to determine, based on the coal mining process, the interrelationships between multiple risk operations, and, based on the interrelationships between the multiple risk operations and the initial learning emphasis indicator for each risk operation, determine, through an AI iterative algorithm, a final learning emphasis indicator for each risk operation;

[0066] A learning allocation module is electrically connected to the AI ​​iterative analysis module and the risk operation analysis module. The learning allocation module is used to arrange a corresponding amount of safety learning content for all risk operations corresponding to each type of work according to the final learning focus indicators of each risk operation.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] The present invention proposes an AI safety personalized learning program for coal mining that combines personnel data. Based on the job attributes of the personnel, the deep correlation between various operational factors that may cause accidents is excavated through AI iterative algorithms. In combination with the different work operations of the job attributes, intelligent production is used to develop a learning program that is adapted to each job. In this way, personalized program design for coal mining safety learning is realized. The learning content focuses on multiple operations that may have operational hazards, which facilitates practitioners to quickly master safety knowledge related to their own jobs and meet the comprehensive safety learning needs of multiple jobs in coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 This is a flow chart of the coal mining AI safety personalized learning method combined with personnel data proposed by the present invention;

[0070] Figure 2 This is a flow chart of the method for determining the correspondence between the risk of hidden dangers in coal mining and at least one risk operation of a work type in the present invention;

[0071] Figure 3 A flow chart of the method for adding an initial learning focus indicator to each risk operation in the present invention;

[0072] Figure 4 This is a flow chart of the method for performing initial risk scoring on coal mining hidden danger risks in the present invention;

[0073] Figure 5This is a flow chart of the primary and secondary judgment algorithm in the present invention;

[0074] Figure 6 A flow chart of a method for determining the interrelationships between multiple risk operations in the present invention;

[0075] Figure 7 This is a flowchart of the AI ​​iterative algorithm in the present invention;

[0076] Figure 8 This is a flow chart of a method for arranging corresponding amounts of safety learning content for all risk operations corresponding to each work type according to the final learning emphasis indicator of each risk operation in the present invention. DETAILED DESCRIPTION

[0077] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0078] Reference Figure 1 As shown in FIG, a coal mining AI safety personalized learning method that combines personnel data includes:

[0079] Obtaining the job attributes of the personnel, and classifying the personnel based on the job attributes to determine at least one job type;

[0080] Based on historical data of coal mining, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risky operation in the type of work;

[0081] Based on the degree of harm caused by hidden dangers in coal mining, initial learning focus indicators are added to each risk operation;

[0082] Based on the coal mining process, determine the interrelationships between multiple risk operations;

[0083] Based on the interrelationships between multiple risk operations and the initial learning focus indicators of each risk operation, the final learning focus indicators of each risk operation are determined through an AI iterative algorithm;

[0084] According to the final learning focus indicators of each risk operation, corresponding amounts of safety learning content are arranged for all risk operations corresponding to each type of work.

[0085] This solution is based on the job attributes of the personnel. Through AI iterative algorithms, it digs out the deep connections between various operational factors that may cause accidents. In combination with the different work operations of the job attributes, intelligent production is adapted to each job type. In this way, personalized program design for coal mining safety learning is achieved.

[0086] Reference Figure 2 As shown, based on historical data of coal mining, determining at least one coal mining hidden danger risk corresponding to each type of work, and determining that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work specifically includes:

[0087] Extracting at least one piece of historical coal mining accident information from historical coal mining data;

[0088] Extracting coal mining accident type keywords and coal mining accident cause keywords from historical coal mining accident information;

[0089] Based on the coal mining accident cause keywords, it is determined whether the historical coal mining accident is related to the current type of work to be determined. If so, the historical coal mining accident information is recorded as relevant historical coal mining accident information; if not, the historical coal mining accident information is recorded as irrelevant historical coal mining accident information;

[0090] Extract the coal mining accident type keywords from all relevant historical coal mining accident information, and summarize the coal mining hidden danger risks corresponding to the work types;

[0091] Determine the operation related to the type of work to be determined that corresponds to each relevant historical coal mining accident information, and record it as the risk operation corresponding to the type of work of coal mining hidden danger risk.

[0092] It is understandable that different types of work have different operations. When arranging safety learning content, it is only necessary to learn the operations that pose safety risks related to the type of work. Therefore, this solution identifies and extracts the risk operations related to each type of work as the basic content for the subsequent arrangement of personalized safety learning content for each type of work.

[0093] Reference Figure 3 As shown in the figure, based on the degree of harm of coal mining hidden dangers, the initial learning focus indicators added to each risk operation include:

[0094] Based on historical data of coal mining, determine the accident level of each historical coal mining accident caused by each coal mining hidden danger risk;

[0095] Based on the accident level of each historical coal mining accident caused by coal mining hidden danger risk, an initial risk score is given to the coal mining hidden danger risk to obtain an initial disaster score for each coal mining hidden danger risk;

[0096] Based on the causes of each coal mining accident caused by coal mining hidden dangers, a primary and secondary judgment algorithm is used to determine the direct correlation between coal mining hidden dangers and risk operations;

[0097] Based on the initial disaster score of coal mining hidden danger risk and the direct correlation between coal mining hidden danger risk and risk operation, the initial learning focus index of risk operation is calculated through the operation focus formula;

[0098] The specific operation focus formula is:

[0099]

[0100] Where, is the initial learning focus indicator for the j-th risk operation, is the initial disaster score of the i-th coal mine mining hidden danger risk, is the direct correlation between the i-th coal mining hidden danger risk and the j-th risk operation.

[0101] In this plan, the initial learning focus index of the risk operation is comprehensively evaluated based on the cause of the safety accident and the degree of disaster caused by the safety accident. The greater the correlation between the risk operation and the safety accident, and the greater the degree of disaster caused by the safety accident caused by the risk operation, the greater the initial learning focus index of the risk operation.

[0102] Reference Figure 4 As shown in the figure, based on the accident level of each historical coal mining accident caused by coal mining hidden danger risk, the coal mining hidden danger risk is initially scored, and the initial disaster score of each coal mining hidden danger risk is obtained, which specifically includes:

[0103] Determine the number of extremely serious accidents, serious accidents, major accidents and ordinary accidents in each historical coal mining accident caused by coal mining hidden risks;

[0104] Calculate the initial disaster score of coal mining hidden danger risk through comprehensive evaluation formula;

[0105] The comprehensive evaluation formula is:

[0106]

[0107] Where, The numbers of particularly serious accidents, serious accidents, major accidents and general accidents in each historical coal mining accident caused by the hidden dangers of coal mining are respectively: The total number of historical coal mining accidents caused by coal mining hidden risks, Provide an initial disaster score for coal mining hidden danger risks.

[0108] It is understandable that the damage caused by historical coal mining accidents of different degrees is different. Based on this, this plan will weightedly sum the types of each historical coal mining accident caused by the risk of coal mining hazards to obtain the initial disaster score of coal mining hazards.

[0109] Reference Figure 5 As shown in the figure, the primary and secondary judgment algorithm is specifically as follows:

[0110] Determine the direct operational cause of each coal mining accident caused by coal mining hidden risks, and count the indirect operational causes of each coal mining accident;

[0111] Count the number of risk operations as direct and indirect causes of operations respectively;

[0112] Based on the primary and secondary correlation formula, the direct correlation between the risk of hidden dangers in coal mining and risk operations is calculated;

[0113] The specific formula for primary and secondary correlation is:

[0114]

[0115] Where, is the total number of coal mining accidents caused by the hidden dangers of coal mining in the i-th coal mine, is the number of the jth risk operation as the direct cause of the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operating causes of the j-th risk operation in the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operational causes in the tth coal mining accident caused by the i-th coal mining hidden danger risk.

[0116] It can be understood that among the causes of accidents, the direct cause that directly leads to the accident is the last insurance for the accident, that is, when the direct operation cause is terminated, the accident can be avoided. Based on this, this plan adopts the primary and secondary analysis method when evaluating the direct correlation between the risk of coal mining hazards and risk operations, and comprehensively analyzes the direct operation causes and indirect operation causes of the accident, and then derives the direct correlation between the risk of coal mining hazards and risk operations. The direct correlation represents the surface correlation factors of each risk operation when the accident occurs.

[0117] Reference Figure 6 As shown in the figure, based on the coal mining process, the interrelationships between multiple risk operations are determined, including:

[0118] Based on the coal mining process, determine the subsequent risk operations that will occur if the risk operation is executed, and build a subordinate risk operation library for the risk operations;

[0119] At the same time, determine the preceding risk operations that may lead to the occurrence of risk operations, and build a superior risk operation library for risk operations.

[0120] Reference Figure 7 As shown in the figure, the AI ​​iterative algorithm is specifically as follows:

[0121] S1. Set an iteration index E and assign E an initial value of 1;

[0122] S2. Use the initial learning focus indicator of each risk operation as the initial iteration indicator of the risk operation, that is, ,in, is the E-th generation iteration indicator of the j-th risk operation;

[0123] The value of S3 and E increases by one;

[0124] S4. Calculate by iterative formula ;

[0125] S5. Determine whether the iteration termination condition is met. If so, output the calculated E-th generation iteration index of the risk operation as the final learning emphasis index of the risk operation. If not, return to step S3.

[0126] The specific iterative formula is:

[0127]

[0128] Where, is the total number of elements in the lower-level risk operation library of the j-th risk operation, is the first risk operation in the subordinate risk operation library of the jth risk operation The E-1th generation iteration index of elements, is the first risk operation in the subordinate risk operation library of the jth risk operation The total number of elements in the parent risk operation library of the element.

[0129] The specific conditions for the iteration termination are:

[0130]

[0131] Where, It is the iteration error threshold, and the value range of the iteration error threshold is 0.01-0.1. is the total number of risky operations.

[0132] The iterative formula in this solution is calculated after several iterations, and the risk of each risk operation is Will tend to be stable, this solution is based on The iteration termination condition is set according to the degree of iteration change. The larger the value of the iteration error threshold, the fewer the number of iterations and the smaller the iteration computing power required, but the less accurate the fault identification. Conversely, the smaller the value of the iteration error threshold, the more the number of iterations, the more iteration computing power required, and the deeper the risk mining.

[0133] It is understandable that there are multiple correlations between the various types of operations in coal mining. One risky operation may trigger a chain reaction, leading to the occurrence of other risky operations. Therefore, this scheme fully utilizes the multiple correlations between the various types of operations in coal mining. Based on the multiple iterative calculations of other risky operations caused by risky operations, the root causes of coal mine accidents can be fully mined. For example, operation A may lead to operation B. Operation B is the direct cause of the accident many times, resulting in a very high initial learning emphasis index for operation B, while operation A has not appeared in many accidents. At this time, since operation A is the hidden operational risk of operation B, through multiple iterations, it can be calculated that the final learning emphasis index of operation A is also very high, thereby realizing the risk mining of operation A.

[0134] Reference Figure 8 As shown in the figure, according to the final learning focus indicators of each risk operation, the corresponding amount of safety learning content is arranged for all risk operations corresponding to each work type, including:

[0135] Obtain the final learning focus indicators for all risk operations corresponding to the work type;

[0136] The final learning focus indexes of all risk operations corresponding to the work type are summed to obtain the first learning index of the work type;

[0137] Compare the final learning focus indicator of each risk operation corresponding to the job type with the first learning indicator of the job type to obtain the learning content proportion of each risk operation corresponding to the job type;

[0138] Arrange corresponding amounts of safety learning content based on the proportion of learning content for each risk operation corresponding to the type of work.

[0139] Furthermore, based on the same inventive concept as the above-mentioned coal mining AI safety personalized learning method combined with personnel data, this solution proposes a coal mining AI safety personalized learning system combined with personnel data, including:

[0140] Storage center, which is used to store historical data of coal mining;

[0141] a risk operation analysis module, the risk operation analysis module being electrically connected to the storage center and configured to extract a number of the latest historical coal mining accident information from historical coal mining data, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work;

[0142] An initial hidden danger analysis module is electrically connected to the storage center and the risk operation analysis module. The initial hidden danger analysis module is used to add initial learning focus indicators to each risk operation based on the degree of harm of the hidden danger risk of coal mining;

[0143] An AI iterative analysis module is electrically connected to the initial hidden danger analysis module and the storage center. The AI ​​iterative analysis module is used to determine the interrelationships between multiple risk operations based on the coal mining process. Based on the interrelationships between the multiple risk operations and the initial learning focus indicators of each risk operation, the AI ​​iterative algorithm is used to determine the final learning focus indicators of each risk operation.

[0144] The learning allocation module is electrically connected to the AI ​​iterative analysis module and the risk operation analysis module. The learning allocation module is used to arrange corresponding amounts of safety learning content for all risk operations corresponding to each type of work according to the final learning focus indicators of each risk operation.

[0145] The process of using the above system is as follows:

[0146] Step 1: The risk operation analysis module retrieves historical coal mining data from the storage center and extracts several pieces of the latest historical coal mining accident information. It then determines at least one coal mining hidden risk corresponding to each type of work, and determines that the coal mining hidden risk corresponds to at least one risk operation of the work type.

[0147] Step 2: The initial hidden danger analysis module adds initial learning focus indicators to each risk operation based on the degree of harm of coal mining hidden danger risks;

[0148] Step 3: The AI ​​iterative analysis module determines the interrelationships between multiple risk operations based on the coal mining process. Based on these interrelationships and the initial learning focus indicators for each risk operation, the AI ​​iterative algorithm determines the final learning focus indicators for each risk operation.

[0149] Step 4: The learning allocation module is used to arrange corresponding amounts of safety learning content for all risk operations corresponding to each type of work according to the final learning focus indicators of each risk operation.

[0150] In summary, the advantages of the present invention are: it realizes the personalized program design of coal mining safety learning, the learning content focuses on multiple operations that may have hidden dangers, and it is convenient for practitioners to quickly master the safety knowledge related to their own jobs, and meet the comprehensive safety learning needs of multiple jobs in coal mines.

[0151] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A coal mining AI safety personalized learning method combined with personnel data, characterized by: include: Obtaining the job attributes of the personnel, and classifying the personnel based on the job attributes to determine at least one job type; Based on historical data of coal mining, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risky operation in the type of work; Based on the degree of harm caused by hidden dangers in coal mining, initial learning focus indicators are added to each risk operation; Based on the coal mining process, determine the subsequent risk operations that will occur if the risk operation is executed, and build a subordinate risk operation library for the risk operations; At the same time, determine the preceding risk operations that may lead to the occurrence of risk operations and build a higher-level risk operation library for risk operations; Based on the interrelationships between multiple risk operations and the initial learning focus indicators of each risk operation, the final learning focus indicators of each risk operation are determined through an AI iterative algorithm; Arrange corresponding safety learning content for all risk operations corresponding to each work type according to the final learning focus indicators of each risk operation; The specific AI iterative algorithm is: S1. Set an iteration index E and assign E an initial value of 1; S2. Use the initial learning focus indicator of each risk operation as the initial iteration indicator of the risk operation, that is, ,in, is the E-th generation iteration indicator of the j-th risk operation, is the initial learning focus indicator for the j-th risk operation; The value of S3 and E increases by one; S4. Calculation by iterative formula ; S5. Determine whether the iteration termination condition is met. If so, output the calculated E-th generation iteration index of the risk operation as the final learning emphasis index of the risk operation. If not, return to step S3. The iterative formula is specifically: Where, is the total number of elements in the lower-level risk operation library of the j-th risk operation, is the first risk operation in the subordinate risk operation library of the jth risk operation The E-1th generation iteration index of elements, is the first risk operation in the subordinate risk operation library of the jth risk operation The total number of elements in the parent risk operation library of the element.

2. The coal mining AI safety personalized learning method based on personnel data according to claim 1 is characterized in that: The determining of at least one coal mining hidden danger risk corresponding to each type of work based on historical coal mining data, and determining that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work specifically includes: Extracting at least one piece of historical coal mining accident information from historical coal mining data; Extracting coal mining accident type keywords and coal mining accident cause keywords from historical coal mining accident information; Based on the coal mining accident cause keywords, it is determined whether the historical coal mining accident is related to the current type of work to be determined. If so, the historical coal mining accident information is recorded as relevant historical coal mining accident information; if not, the historical coal mining accident information is recorded as irrelevant historical coal mining accident information; Extract the coal mining accident type keywords from all relevant historical coal mining accident information, and summarize the coal mining hidden danger risks corresponding to the work types; Determine the operation related to the type of work to be determined that corresponds to each relevant historical coal mining accident information, and record it as the risk operation corresponding to the type of work of coal mining hidden danger risk.

3. The coal mining AI safety personalized learning method based on personnel data according to claim 2 is characterized in that: Based on the degree of hazard of coal mining hidden dangers, the initial learning focus indicators added to each risk operation specifically include: Based on historical data of coal mining, determine the accident level of each historical coal mining accident caused by each coal mining hidden danger risk; Based on the accident level of each historical coal mining accident caused by coal mining hidden danger risk, an initial risk score is given to the coal mining hidden danger risk to obtain an initial disaster score for each coal mining hidden danger risk; Based on the causes of each coal mining accident caused by coal mining hidden dangers, a primary and secondary judgment algorithm is used to determine the direct correlation between coal mining hidden dangers and risk operations; Based on the initial disaster score of coal mining hidden danger risk and the direct correlation between coal mining hidden danger risk and risk operation, the initial learning focus index of risk operation is calculated through the operation focus formula; The operation focuses on the formula: Where, is the initial disaster score of the i-th coal mine mining hidden danger risk, is the direct correlation between the i-th coal mining hidden danger risk and the j-th risk operation.

4. The coal mining AI safety personalized learning method based on personnel data according to claim 3 is characterized in that: The initial risk score of the coal mining hidden danger risk is obtained based on the accident level of each historical coal mining accident caused by the coal mining hidden danger risk, and the initial disaster score of each coal mining hidden danger risk is specifically: Determine the number of extremely serious accidents, serious accidents, major accidents and ordinary accidents in each historical coal mining accident caused by coal mining hidden risks; Calculate the initial disaster score of coal mining hidden danger risk through comprehensive evaluation formula; The comprehensive evaluation formula is: Where, The numbers of particularly serious accidents, serious accidents, major accidents and general accidents in each historical coal mining accident caused by the hidden dangers of coal mining are respectively: The total number of historical coal mining accidents caused by coal mining hidden risks, Provide an initial disaster score for coal mining hidden danger risks.

5. The coal mining AI safety personalized learning method based on personnel data according to claim 4 is characterized in that: The primary and secondary judgment algorithm is specifically as follows: Determine the direct operational cause of each coal mining accident caused by coal mining hidden risks, and count the indirect operational causes of each coal mining accident; Count the number of risk operations as direct and indirect causes of operations respectively; Based on the primary and secondary correlation formula, the direct correlation between the risk of hidden dangers in coal mining and risk operations is calculated; The primary and secondary correlation formula is specifically: Where, is the total number of coal mining accidents caused by the hidden dangers of coal mining in the i-th coal mine, is the number of the jth risk operation as the direct cause of the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operating causes of the j-th risk operation in the coal mining accident caused by the i-th coal mining hidden danger risk, is the number of indirect operational causes in the tth coal mining accident caused by the i-th coal mining hidden danger risk.

6. The coal mining AI safety personalized learning method based on personnel data according to claim 5 is characterized in that: The specific iteration termination condition is: Where, is the iteration error threshold, the value range of the iteration error threshold is 0.01-0.1, is the total number of risky operations.

7. The coal mining AI safety personalized learning method based on personnel data according to claim 6 is characterized in that: The safety learning content for all risk operations corresponding to each type of work, arranged in accordance with the final learning focus indicators of each risk operation, specifically includes: Obtain the final learning focus indicators for all risk operations corresponding to the work type; The final learning focus indexes of all risk operations corresponding to the work type are summed to obtain the first learning index of the work type; Compare the final learning focus indicator of each risk operation corresponding to the job type with the first learning indicator of the job type to obtain the learning content proportion of each risk operation corresponding to the job type; Arrange corresponding amounts of safety learning content based on the proportion of learning content for each risk operation corresponding to the type of work.

8. A coal mining AI safety personalized learning system combined with personnel data, characterized by: A method for implementing the coal mining AI safety personalized learning method combined with personnel data as described in any one of claims 1 to 7, comprising: A storage center, the storage center is used to store historical data of coal mining; a risk operation analysis module, the risk operation analysis module being electrically connected to the storage center, and configured to extract a plurality of pieces of the latest historical coal mining accident information from historical coal mining data, determine at least one coal mining hidden danger risk corresponding to each type of work, and determine that the coal mining hidden danger risk corresponds to at least one risk operation of the type of work; an initial hidden danger analysis module, the initial hidden danger analysis module being electrically connected to the storage center and the risk operation analysis module, and configured to add an initial learning focus indicator to each risk operation based on the degree of harm of the hidden danger risk of coal mining; an AI iterative analysis module, the AI ​​iterative analysis module being electrically connected to the initial hidden danger analysis module and the storage center, the AI ​​iterative analysis module being configured to determine, based on the coal mining process, the interrelationships between multiple risk operations, and, based on the interrelationships between the multiple risk operations and the initial learning emphasis indicator for each risk operation, determine, through an AI iterative algorithm, a final learning emphasis indicator for each risk operation; A learning allocation module is electrically connected to the AI ​​iterative analysis module and the risk operation analysis module. The learning allocation module is used to arrange a corresponding amount of safety learning content for all risk operations corresponding to each type of work according to the final learning focus indicators of each risk operation.

Images