A method and device for mining safety hazard record data of mines
Through the theme mining and clustering processing of mine safety hazard recording data, a hidden danger matrix is built and the correlation relationship is calculated, the problem that mine safety hazard recording data fails to provide high-value content, and the efficiency of safety hazard detection is improved.
Patent Information
- Application Number
- CN202410707260.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-03
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-06-03
AI Technical Summary
The existing technology cannot effectively mine and utilize mine safety hazards to record data, resulting in inefficient inspection of mine safety hazards.
By performing thematic mining, clustering processing and matrix construction on the mining safety hazard record data, the support, confidence and rule improvement are calculated, and the hidden danger matrix is constructed to determine the correlation between hidden danger terms.
It has improved the in-depth mining ability of mining safety hazard recording data, provided higher value content for reference by mining enterprises, and enhanced the reliability and investigation efficiency of safety hazard analysis.
Smart Images

Figure CN118708628B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method and device for mining safety hazard record data of mines. Background Art
[0002] Underground mining has special operating environments and production characteristics. Its working places are usually far away from the surface and are affected by many natural factors such as geological structure, rock stability, groundwater system, toxic gases, etc. In addition, workers work in a closed, narrow and humid environment for a long time, which also increases the risk of safety accidents. These factors work together to make underground metal mines have a highly complex and uncertain safety situation, making it one of the industries with the highest accident incidence and casualty rate.
[0003] In recent years, the country has successively introduced a series of policies and measures to improve the safety situation in mines. Among them, the defense mechanism based on hidden danger investigation and control has become an important way to reduce mine accidents and improve the safety level of mines. The focus of its work is to identify, evaluate and control potential unstable factors that may lead to accidents. It focuses on identifying potential risk factors and weak links before accidents occur, reducing the probability of accidents through proactive preventive measures, and recording the results of hidden danger investigation and control in the form of safety hazard record data.
[0004] At present, after the safety hazard record data is generated, there is no in-depth mining of the safety hazard record data, which makes it impossible for the safety hazard record data to provide higher-value content for reference by mining companies, and thus fails to improve the efficiency of mine safety hazard inspections. Summary of the invention
[0005] In view of this, an embodiment of the present application provides a method and device for mining safety hazard record data of a mine, so that the safety hazard record data can provide content with higher value.
[0006] In a first aspect, an embodiment of the present application provides a method for mining safety hazard record data of a mine, the method comprising:
[0007] After obtaining multiple pieces of safety hazard record data generated during the safety hazard investigation of the target mine, subject mining is performed on the hazard description information in each piece of safety hazard record data to obtain hazard type information for characterizing the hazard type of the hazard description information in the piece of safety hazard record data;
[0008] Clustering the rectification period and penalty information corresponding to the piece of safety hazard record data to obtain hazard level information for characterizing the degree of harm that the safety hazard corresponding to the piece of safety hazard record data can cause;
[0009] The time information representing the time point in the piece of potential safety hazard record data is transformed according to the set time granularity to obtain the time granularity information corresponding to the piece of potential safety hazard record data;
[0010] For the shift information recorded in the piece of potential safety hazard record data, determine the time period information in which the potential safety hazard in the piece of potential safety hazard record data occurs;
[0011] For the responsible unit recorded in the piece of safety hazard record data, determine the hazard subject information used to represent the hazard subject that needs to bear the responsibility for the safety hazard recorded in the piece of safety hazard record data;
[0012] For the hidden danger location recorded in the piece of hidden danger record data, determine the spatial location information used to characterize the location where the hidden danger recorded in the piece of hidden danger record data occurs;
[0013] Construct a hidden danger matrix based on the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data;
[0014] According to the hidden danger matrix, the support of the target item in the hidden danger matrix is calculated using the following formula:
[0015]
[0016] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and N(X) represents the total number of target items;
[0017] According to the hidden danger matrix, the confidence of the first target item and the second target item is calculated using the following formula:
[0018]
[0019] Among them, the confidence of the first target item and the second target item represents the probability that the second target item also appears when the first target item appears, Support(A) is the first support of the first target item, Support(A∪B) is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent of the association rule, the second target item is called the consequent of the association rule, and the first target item and the second target item constitute an association rule;
[0020] According to the hidden danger matrix, the rule improvement of the first target item and the second target item is calculated using the following formula:
[0021]
[0022] Among them, Support (B) is the third support degree of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item occurring under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item occurring under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the occurrence of the first target item and the second target item are independent of each other.
[0023] Optionally, the method further comprises:
[0024] According to the hidden danger matrix, the theoretical maximum improvement of the first target item and the second target item is calculated using the following formula:
[0025]
[0026] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and MAX(N(A), N(B)) represents the larger value of the number of the first target item and the second target item in the hidden danger matrix;
[0027] According to the hidden danger matrix, the standard rule lifting degree of the first target item and the second target item is calculated using the following formula:
[0028]
[0029] Wherein, the standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item, N(A∪B) represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, N(A) represents the total number of the first target item in the hidden danger matrix, and N(B) represents the total number of the second target item in the hidden danger matrix;
[0030] According to the hidden danger matrix and the preset rule knowledge base, the difference between the association rule and the preset rule knowledge base is calculated using the following formula:
[0031]
[0032] Wherein, w(p) represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, and w(q) represents the difference between the second target item and the set of association rule consequents in the preset rule knowledge base; |P| represents the number of items in the set of antecedents of the association rule in the preset rule knowledge base, dif irepresents the difference between the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base. When the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 1; when the first target item and the i-th item in the association rule antecedent set in the preset rule knowledge base belong to different contents in hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, dif i The value is 0; |Q| represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, dif j represents the difference between the second target item and the jth item in the set of association rule terms in the preset rule knowledge base. When the second target item and the jth item in the set of association rule terms in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is l; when the second target item and the jth item in the set of subsequent items of the association rule in the preset rule knowledge base belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is 0.5; when the second target item is the same as the jth item in the set of subsequent items of the association rule in the preset rule knowledge base, dif j The value is 0.
[0033] Optionally, the rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the piece of safety hidden danger record data.
[0034] Optionally, the time granularity is set to quarter.
[0035] In a second aspect, an embodiment of the present application provides a device for mining safety hazard record data of a mine, the device comprising:
[0036] The processing unit is used for, after acquiring a plurality of safety hazard record data generated in the process of safety hazard investigation of the target mine, subject mining the hazard description information in each safety hazard record data to obtain hazard type information for characterizing the hazard type of the hazard description information in the safety hazard record data; and clustering the rectification cycle and penalty information corresponding to the safety hazard record data to obtain hazard level information for characterizing the degree of harm that the safety hazard corresponding to the safety hazard record data can cause; and clustering the time information representing the time point in the safety hazard record data according to the time information. According to the set time granularity, the time information is transformed to obtain the time granularity information corresponding to the piece of safety hazard record data; and, for the shift information recorded in the piece of safety hazard record data, determine the time period information of the safety hazard in the piece of safety hazard record data; and, for the responsible unit recorded in the piece of safety hazard record data, determine the hazard subject information used to characterize the need to bear the responsibility for the safety hazard recorded in the piece of safety hazard record data; and, for the hazard location recorded in the piece of safety hazard record data, determine the spatial location information used to characterize the location where the safety hazard recorded in the piece of safety hazard record data occurs;
[0037] A construction unit, used to construct a hidden danger matrix according to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data;
[0038] The first calculation unit is used to calculate the support of the target item in the hidden danger matrix according to the hidden danger matrix using the following formula:
[0039]
[0040] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and N(X) represents the total number of target items;
[0041] The second calculation unit is used to calculate the confidence of the first target item and the second target item according to the hidden danger matrix using the following formula:
[0042]
[0043] Among them, the confidence of the first target item and the second target item represents the probability that the second target item also appears when the first target item appears, Support(A) is the first support of the first target item, Support(A∪B) is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent of the association rule, the second target item is called the consequent of the association rule, and the first target item and the second target item constitute an association rule;
[0044] The third calculation unit is used to calculate the rule lifting degree of the first target item and the second target item according to the hidden danger matrix by using the following formula:
[0045]
[0046] Among them, Support (B) is the third support degree of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item occurring under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item occurring under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the occurrence of the first target item and the second target item are independent of each other.
[0047] Optionally, the device further comprises:
[0048] The fourth calculation unit is used to calculate the theoretical maximum improvement of the first target item and the second target item according to the hidden danger matrix using the following formula:
[0049]
[0050] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and MAX(N(A), N(B)) represents the larger value of the number of the first target item and the second target item in the hidden danger matrix;
[0051] A fifth calculation unit is configured to calculate the standard rule lifting degree of the first target item and the second target item according to the hidden danger matrix by using the following formula:
[0052]
[0053] Wherein, the standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item, N(A∪B) represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, N(A) represents the total number of the first target item in the hidden danger matrix, and N(B) represents the total number of the second target item in the hidden danger matrix;
[0054] The sixth calculation unit is used to calculate the difference between the association rule and the preset rule knowledge base according to the hidden danger matrix and the preset rule knowledge base using the following formula:
[0055]
[0056] Wherein, w(p) represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, and w(q) represents the difference between the second target item and the set of association rule consequents in the preset rule knowledge base; |P| represents the number of items in the set of antecedents of the association rule in the preset rule knowledge base, dif i represents the difference between the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base. When the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 1; when the first target item and the i-th item in the association rule antecedent set in the preset rule knowledge base belong to different contents in hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, dif i The value is 0; |Q| represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, dif j represents the difference between the second target item and the jth item in the set of association rule terms in the preset rule knowledge base. When the second target item and the jth item in the set of association rule terms in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif jThe value is l; when the second target item and the jth item in the set of subsequent items of the association rule in the preset rule knowledge base belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is 0.5; when the second target item is the same as the jth item in the set of subsequent items of the association rule in the preset rule knowledge base, dif j The value is 0.
[0057] Optionally, the rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the piece of safety hidden danger record data.
[0058] Optionally, the time granularity is set to quarter.
[0059] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for mining safety hazard record data for mines as described in any one of the first aspects.
[0060] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for mining safety hazard record data of a mine as described in any one of the first aspects are executed.
[0061] The technical solution provided by the embodiments of the present application may have the following beneficial effects:
[0062] In the present application, after obtaining the safety hazard record data, the safety hazard record data is converted into specific standardized data, and then the standardized data is used to construct a hazard matrix, and then the hazard matrix is used to determine the relationship between the items included in the hazard matrix, such as: support, confidence and rule improvement. Through this application, the safety hazard record data can be deeply mined to obtain higher value content for reference by mining enterprises. After determining the correlation between the contents included in the safety hazard record data, mining enterprises can conduct more reliable analysis of the safety hazards of mines through the correlation, which is conducive to improving the efficiency of mine safety hazard inspections.
[0063] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0065] Figure 1 A flowchart of a method for mining safety hazard record data for mines provided in an embodiment of the present application;
[0066] Figure 2 A schematic diagram of the structure of a device for mining safety hazard recording data for mines provided in an embodiment of the present application. DETAILED DESCRIPTION
[0067] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0068] Figure 1 A flowchart of a method for mining safety hazard record data for mines provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method comprises the following steps:
[0069] Step 101: After obtaining multiple safety hazard record data generated during the safety hazard inspection process of the target mine, for each safety hazard record data, subject mining is performed on the hazard description information in the safety hazard record data to obtain hazard type information used to characterize the hazard type of the hazard description information in the safety hazard record data.
[0070] Step 102: cluster the rectification period and penalty information corresponding to the piece of potential safety hazard record data to obtain potential safety hazard level information that characterizes the degree of harm that can be caused by the potential safety hazard corresponding to the piece of potential safety hazard record data.
[0071] Step 103: transform the time information representing the time point in the piece of potential safety hazard record data according to the set time granularity to obtain the time granularity information corresponding to the piece of potential safety hazard record data.
[0072] Step 104: For the shift information recorded in the piece of potential safety hazard record data, determine the time period information in which the potential safety hazard occurs in the piece of potential safety hazard record data.
[0073] Step 105: For the responsible unit recorded in the piece of potential safety hazard record data, determine the potential safety hazard subject information used to represent the potential safety hazard subject that needs to bear the responsibility for the potential safety hazard recorded in the piece of potential safety hazard record data.
[0074] Step 106: For the hazard location recorded in the piece of safety hazard record data, determine the spatial location information used to characterize the location where the safety hazard recorded in the piece of safety hazard record data occurs.
[0075] Step 107: construct a hidden danger matrix according to the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data.
[0076] Step 108: According to the hidden danger matrix, the support of the target item in the hidden danger matrix is calculated using the following formula 1:
[0077]
[0078] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and N(X) represents the total number of target items.
[0079] Step 109: According to the hidden danger matrix, the confidence of the first target item and the second target item is calculated using the following formula 2:
[0080]
[0081] Among them, the confidence of the first target item and the second target item represents the probability that the second target item also appears when the first target item appears, Support(A) is the first support of the first target item, Support(A∪B) is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent of the association rule, the second target item is called the consequent of the association rule, and the first target item and the second target item constitute an association rule;
[0082] Step 110: According to the risk matrix, the rule lifting degrees of the first target item and the second target item are calculated using the following formula 3:
[0083]
[0084] Among them, Support (B) is the third support degree of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item occurring under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item occurring under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the occurrence of the first target item and the second target item are independent of each other.
[0085] Specifically, after obtaining the safety hazard record data, each safety hazard record data includes hazard description information, such as "the anchor rods on the upper plate of the mining site are not in place, there is water accumulation, and the ventilation is poor", "the roof of the mining site is broken, there is a large fault, and serious caving occurs", etc. The hazard type information used to characterize the hazard description information in the safety hazard record data can be determined by subject mining of the hazard description information. The hazard type information can use concise and representative type information to represent the specific content of the hazard description. The hazard types include: roof management, lighting problems, blasting management, personnel protection and other types. In the process of subject mining, a custom word library is used to segment the hazard description information, and the word frequency statistics and TF-IDF weighting are performed on the segmentation results to realize the vectorization of the text. Then, the Gibbs sampling algorithm is used to estimate the parameters of the BTM topic model. The optimal number of topics is determined to be 26 at the lowest perplexity and the inflection point. According to the contribution, the high-frequency topic words are brought into the original text for manual recognition. Through result evaluation and semantic merging, 14 effective analysis topics are finally formed, and the analysis topics are used as hazard type information.
[0086] Each safety hazard record data also records the corresponding rectification period and penalty information (for example, the amount of the fine). By clustering these two data in the safety hazard record data (such as using the k-means algorithm to achieve clustering between hazard fines and rectification period), and to ensure the clustering effect, obvious outliers are removed after normalization. Finally, the hazard level information that can be used to characterize the degree of harm that the safety hazard corresponding to the safety hazard record data can be obtained. Because the fine data is considered to be a comprehensive evaluation of the safety inspectors on the harmfulness of the safety hazard and other aspects, it has a greater weight. Therefore, the category with relatively high fine data is selected as a major hazard, followed by the category with a longer rectification period as a larger hazard, and finally as a general hazard, thereby completing the construction of the hazard degree dimension.
[0087] For the time information representing the time point of the safety hazard record data (such as the recording time and review time of the safety hazard record data), the format of the time information can be converted using the set time granularity (including annual, quarterly, monthly, etc.). Specifically, the time calculation function can be used for conversion to determine the time granularity information such as the year, quarter or month to which the time information belongs.
[0088] For the shift information recorded in the safety hazard record data (taking the three-shift system as an example, the shift information included is the 0 o'clock shift, the 8 o'clock shift and the 16 o'clock shift), the time period information when the safety hazard occurs in the safety hazard record data can be determined based on the shift information (taking the 0 o'clock shift as an example, the time period information can be 0 o'clock-8 o'clock).
[0089] For the hazard locations recorded in the safety hazard record data, due to the frequent changes in the production location of underground metal mines and the complex underground production structure, it is impossible to record the hazard locations in a standard and normative manner during the hazard investigation process. Therefore, the data of the same category in the original hazard location data are merged, and the specific mining site numbers are merged into the location type of "mining site". In addition, the spatial location information such as mining connecting roads and ramps is also divided.
[0090] For the responsible units recorded in the safety hazard record data, the responsible units include responsible persons and responsible departments. This application uses departments as the subject information of the hazard, and determines that the responsible subject dimensions are divided into three types: outsourced units, mining production departments, and safety management departments.
[0091] After obtaining the above data, a hidden danger matrix can be constructed according to the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data. The hidden danger matrix obtained is as follows:
[0092]
[0093] Each hidden danger record contains data in six dimensions {I1, I2, I3, I4, I5, I6}, where each column represents a dimension, such as I1 represents the dimension of hidden danger type, and each row represents a safety hidden danger record data. After structuring, each dimension is composed of several fixed items, such as the time period information dimension can be composed of "0 o'clock shift, 8 o'clock shift, 16 o'clock shift", and these items are represented by S ij It means the j-th type tag of dimension i, such as S 11 Represents "Lighting Problem" of the "Hazard Type" dimension.
[0094] After obtaining the above hidden danger matrix, new evaluation indicators can be constructed: the support of the target item in the hidden danger matrix, the confidence of the first target item and the second target item, and the rule improvement of the first target item and the second target item.
[0095] For example, item A and item B represent two different specific type tags, and they belong to different dimensions. 11 (Lighting problem), item B represents S 21 (general hidden danger), or any other type of mark different from the dimension where item A is located. Taking item A as the target item, the support of item A on the hidden danger matrix is defined as the ratio of the number of records containing item A in the hidden danger matrix to the total number of hidden danger matrices. When Support(A) is greater than the minimum support threshold, A is called a frequent item, which means that item A is frequently found.
[0096] When the setting item A (the first target item) appears, there is a certain probability that item B (the second target item) can be derived. Then it is said that there is a correlation between A and B, which is expressed as ,and The probability is called confidence. Among them, item A is called the antecedent of the association rule, and item B is called the consequent of the association rule.
[0097] The rule lift of the first target item and the second target item is the ratio of the confidence to the prior probability of the rule's consequent item. The rule lift can reflect the degree to which the rule's consequent item is affected by the rule's antecedent item, and is a measure of the value of the association rule.
[0098] Through this application, the safety hazard record data can be deeply mined to obtain higher-value content for reference by mining companies. After determining the correlation between the contents included in the safety hazard record data, mining companies can conduct a more reliable analysis of the safety hazards in the mines through the correlation, which is conducive to improving the efficiency of mine safety hazard inspections.
[0099] In a feasible implementation manner, the theoretical maximum improvement of the first target item and the second target item may be calculated according to the hidden danger matrix using the following formula 4:
[0100]
[0101] Among them, N(D) represents the total number of items included in the hidden danger matrix, and MAX(N(A), N(B)) represents the larger value of the number of the first target item and the second target item in the hidden danger matrix.
[0102] After obtaining the theoretical maximum improvement of the first target item and the second target item, the standard rule improvement of the first target item and the second target item can be calculated according to the hidden danger matrix using the following formula 5:
[0103]
[0104] Among them, the standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item, N(A∪B) represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, N(A) represents the total number of the first target items in the hidden danger matrix, and N(B) represents the total number of the second target items in the hidden danger matrix.
[0105] Specifically, when the number of co-occurrences between the preceding and following terms of a rule is the same as the one with less support among the preceding and following terms, that is, when N(A∪B)=min(N(A),N(B)), the lift reaches the theoretical maximum value of this association rule, which is N(D) / max(N(A),N(B)). It can be seen that the lift is related to the support of the preceding and following terms of the rule, which means that the comparison of the value of different rules cannot simply compare the size of the lift. Therefore, a standard lift is constructed. normal This indicator is used for comparative analysis between different association rules. It is the ratio between the lift of the association rule and the maximum theoretical lift. The larger the value, the greater the value of the rule. This indicator can be used to compare the lift value between different rules.
[0106] In a feasible implementation scheme, the difference between the association rule and the preset rule knowledge base can also be calculated according to the hidden danger matrix and the preset rule knowledge base using the following formula 6:
[0107]
[0108] Wherein, w(p) represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, and w(q) represents the difference between the second target item and the set of association rule consequents in the preset rule knowledge base; |P| represents the number of items in the set of antecedents of the association rule in the preset rule knowledge base, dif i represents the difference between the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base. When the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 1; when the first target item and the i-th item in the association rule antecedent set in the preset rule knowledge base belong to different contents in hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, difi The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, dif i The value is 0; |Q| represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, dif j represents the difference between the second target item and the jth item in the set of association rule terms in the preset rule knowledge base. When the second target item and the jth item in the set of association rule terms in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is l; when the second target item and the jth item in the set of subsequent items of the association rule in the preset rule knowledge base belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is 0.5; when the second target item is the same as the jth item in the set of subsequent items of the association rule in the preset rule knowledge base, dif j The value is 0.
[0109] Based on the above content, we can know that the values of the antecedent and the posterior of the association rule difference are between 0 and 1. In order to prevent the denominator from being 0 and ensure the standardization of the difference, and to ensure that the maximum value is 1, the calculation method of formula 6 is adopted. By traversing the rules in the rule base and calculating the minimum difference, the association rule R included in the hidden danger matrix can be obtained. n Relative preset rule knowledge base R b The final difference degree of the internal rules, wherein the association rules included in the hidden danger matrix are obtained through the hidden danger matrix.
[0110] In a feasible implementation scheme, the rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the safety hidden danger record data.
[0111] In a feasible implementation scheme, the set time granularity is quarter.
[0112] Figure 2 A schematic diagram of a mining device for recording data of potential safety hazards in mines provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the device comprises:
[0113] The processing unit 21 is used for, after acquiring a plurality of safety hazard record data generated in the process of safety hazard investigation of the target mine, subject mining the hazard description information in each safety hazard record data to obtain hazard type information for characterizing the hazard type of the hazard description information in the safety hazard record data; and clustering the rectification cycle and penalty information corresponding to the safety hazard record data to obtain hazard level information for characterizing the degree of harm that the safety hazard corresponding to the safety hazard record data can cause; and time information representing a time point in the safety hazard record data, According to the set time granularity, the time information is transformed to obtain the time granularity information corresponding to the piece of safety hazard record data; and, for the shift information recorded in the piece of safety hazard record data, determine the time period information of the safety hazard in the piece of safety hazard record data; and, for the responsible unit recorded in the piece of safety hazard record data, determine the hazard subject information used to characterize the need to bear the responsibility for the safety hazard recorded in the piece of safety hazard record data; and, for the hazard location recorded in the piece of safety hazard record data, determine the spatial location information used to characterize the location where the safety hazard recorded in the piece of safety hazard record data occurs;
[0114] A construction unit 22 is used to construct a hidden danger matrix according to the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each piece of safety hidden danger record data;
[0115] The first calculation unit 23 is used to calculate the support of the target item in the hidden danger matrix using the following formula according to the hidden danger matrix:
[0116]
[0117] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and N(X) represents the total number of target items;
[0118] The second calculation unit 24 is used to calculate the confidence of the first target item and the second target item according to the hidden danger matrix using the following formula:
[0119]
[0120] Among them, the confidence of the first target item and the second target item represents the probability that the second target item also appears when the first target item appears, Support(A) is the first support of the first target item, Support(A∪B) is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent of the association rule, the second target item is called the consequent of the association rule, and the first target item and the second target item constitute an association rule;
[0121] The third calculation unit 25 is used to calculate the rule lifting degree of the first target item and the second target item according to the hidden danger matrix using the following formula:
[0122]
[0123] Among them, Support (B) is the third support degree of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item occurring under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item occurring under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the occurrence of the first target item and the second target item are independent of each other.
[0124] In a feasible embodiment, the device further comprises:
[0125] The fourth calculation unit is used to calculate the theoretical maximum improvement of the first target item and the second target item according to the hidden danger matrix using the following formula:
[0126]
[0127] Wherein, N(D) represents the total number of items included in the hidden danger matrix, and MAX(N(A), N(B)) represents the larger value of the number of the first target item and the second target item in the hidden danger matrix;
[0128] A fifth calculation unit is configured to calculate the standard rule lifting degree of the first target item and the second target item according to the hidden danger matrix by using the following formula:
[0129]
[0130] Wherein, the standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item, N(A∪B) represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, N(A) represents the total number of the first target item in the hidden danger matrix, and N(B) represents the total number of the second target item in the hidden danger matrix;
[0131] The sixth calculation unit is used to calculate the difference between the association rule and the preset rule knowledge base according to the hidden danger matrix and the preset rule knowledge base using the following formula:
[0132]
[0133] Wherein, w(p) represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, and w(q) represents the difference between the second target item and the set of association rule consequents in the preset rule knowledge base; |P| represents the number of items in the set of antecedents of the association rule in the preset rule knowledge base, dif i represents the difference between the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base. When the first target item and the i-th item in the set of association rule antecedents in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 1; when the first target item and the i-th item in the association rule antecedent set in the preset rule knowledge base belong to different contents in hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif i The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, dif i The value is 0; |Q| represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, dif j represents the difference between the second target item and the jth item in the set of association rule terms in the preset rule knowledge base. When the second target item and the jth item in the set of association rule terms in the preset rule knowledge base belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif jThe value is l; when the second target item and the jth item in the set of subsequent items of the association rule in the preset rule knowledge base belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, dif j The value is 0.5; when the second target item is the same as the jth item in the set of subsequent items of the association rule in the preset rule knowledge base, dif j The value is 0.
[0134] In a feasible implementation scheme, the rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the safety hidden danger record data.
[0135] In a feasible implementation scheme, the set time granularity is quarter.
[0136] about Figure 2 For a description of the principles of the relevant content, please refer to Figure 1 The relevant contents are explained in detail and will not be explained in detail here.
[0137] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0140] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0141] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.
[0142] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for mining safety hazard record data in mines, characterized in that: The method comprises: After obtaining multiple pieces of safety hazard record data generated during the safety hazard investigation of the target mine, subject mining is performed on the hazard description information in each piece of safety hazard record data to obtain hazard type information for characterizing the hazard type of the hazard description information in the piece of safety hazard record data; Clustering the rectification period and penalty information corresponding to the piece of safety hazard record data to obtain hazard level information for characterizing the degree of harm that the safety hazard corresponding to the piece of safety hazard record data can cause; The time information representing the time point in the piece of potential safety hazard record data is transformed according to the set time granularity to obtain the time granularity information corresponding to the piece of potential safety hazard record data; For the shift information recorded in the piece of potential safety hazard record data, determine the time period information in which the potential safety hazard in the piece of potential safety hazard record data occurs; For the responsible unit recorded in the piece of safety hazard record data, determine the hazard subject information used to represent the hazard subject that needs to bear the responsibility for the safety hazard recorded in the piece of safety hazard record data; For the hidden danger location recorded in the piece of hidden danger record data, determine the spatial location information used to characterize the location where the hidden danger recorded in the piece of hidden danger record data occurs; Construct a hidden danger matrix based on the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data; According to the hidden danger matrix, the support of the target item in the hidden danger matrix is calculated using the following formula: in, represents the total number of items contained in the hidden danger matrix, Indicates the total number of target items; According to the hidden danger matrix, the confidence of the first target item and the second target item is calculated using the following formula: The confidence of the first target item and the second target item represents the probability that the second target item will also appear when the first target item appears. is the first support of the first target item, is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent item of the association rule, the second target item is called the consequent item of the association rule, and the first target item and the second target item constitute an association rule; According to the hidden danger matrix, the rule improvement of the first target item and the second target item is calculated using the following formula: in, is the third support of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item appearing under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item appearing under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the appearance of the first target item and the second target item are independent of each other. The method further comprises: According to the hidden danger matrix, the theoretical maximum improvement of the first target item and the second target item is calculated using the following formula: in, represents the total number of items contained in the hidden danger matrix, represents the larger value of the number of the first target item and the second target item in the hidden danger matrix; According to the hidden danger matrix, the standard rule lifting degree of the first target item and the second target item is calculated using the following formula: The standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item. represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, represents the total number of the first target items in the hidden danger matrix, represents the total number of the second target items in the hidden danger matrix; According to the hidden danger matrix and the preset rule knowledge base, the difference between the association rule and the preset rule knowledge base is calculated using the following formula: in, represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, Indicates the difference between the second target item and the set of subsequent items of the association rules in the preset rule knowledge base; , represents the number of items in the association rule antecedent set in the preset rule knowledge base, Indicates that the first target item is associated with the first item in the set of association rule antecedents in the preset rule knowledge base. i The difference between the first target item and the first target item in the association rule antecedent set in the preset rule knowledge base is i When the items belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 1; when the first target item is associated with the first item in the association rule antecedent set in the preset rule knowledge base i When the items belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, The value is 0; , represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, Indicates that the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base. j The difference between the second target item and the first item in the association rule subsequent item set in the preset rule knowledge base is j When the items belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 1; when the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base j When the items belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 0.5; when the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base j When the items are the same, The value is 0.
2. The method for mining safety hazard record data of a mine according to claim 1, characterized in that: The rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the safety hidden danger record data.
3. The method for mining safety hazard record data of a mine according to claim 1, characterized in that: The set time granularity is quarterly.
4. A mining device for recording data of potential safety hazards in mines, characterized in that: The device comprises: The processing unit is used for, after acquiring a plurality of safety hazard record data generated in the process of safety hazard investigation of the target mine, subject mining the hazard description information in each safety hazard record data to obtain hazard type information for characterizing the hazard type of the hazard description information in the safety hazard record data; and clustering the rectification cycle and penalty information corresponding to the safety hazard record data to obtain hazard level information for characterizing the degree of harm that the safety hazard corresponding to the safety hazard record data can cause; and clustering the time information representing the time point in the safety hazard record data according to the time information. According to the set time granularity, the time information is transformed to obtain the time granularity information corresponding to the piece of safety hazard record data; and, for the shift information recorded in the piece of safety hazard record data, determine the time period information of the safety hazard in the piece of safety hazard record data; and, for the responsible unit recorded in the piece of safety hazard record data, determine the hazard subject information used to characterize the need to bear the responsibility for the safety hazard recorded in the piece of safety hazard record data; and, for the hazard location recorded in the piece of safety hazard record data, determine the spatial location information used to characterize the location where the safety hazard recorded in the piece of safety hazard record data occurs; A construction unit, used to construct a hidden danger matrix according to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information and spatial location information corresponding to each safety hidden danger record data; The first calculation unit is used to calculate the support of the target item in the hidden danger matrix according to the hidden danger matrix using the following formula: in, represents the total number of items contained in the hidden danger matrix, Indicates the total number of target items; The second calculation unit is used to calculate the confidence of the first target item and the second target item according to the hidden danger matrix using the following formula: The confidences of the first target item and the second target item represent the probability that the second target item will also appear when the first target item appears. is the first support of the first target item, is the second support corresponding to the simultaneous appearance of the first target item and the second target item, the first target item is called the antecedent item of the association rule, the second target item is called the consequent item of the association rule, and the first target item and the second target item constitute an association rule; The third calculation unit is used to calculate the rule lifting degree of the first target item and the second target item according to the hidden danger matrix by using the following formula: in, is the third support of the second target item. When the rule lift is greater than 1, it means that the probability of the second target item appearing under the influence of the first target item is greater than the prior probability. When the rule lift is less than 1, it means that the probability of the second target item appearing under the influence of the first target item is less than the prior probability. When the rule lift is equal to 1, it means that the appearance of the first target item and the second target item are independent of each other. The device also includes: The fourth calculation unit is used to calculate the theoretical maximum improvement of the first target item and the second target item according to the hidden danger matrix using the following formula: in, represents the total number of items contained in the hidden danger matrix, represents the larger value of the number of the first target item and the second target item in the hidden danger matrix; A fifth calculation unit is configured to calculate the standard rule lifting degree of the first target item and the second target item according to the hidden danger matrix by using the following formula: The standard lift of the first target item and the second target item represents the ratio of the lift of the first target item and the second target item to the theoretical maximum lift of the first target item and the second target item. represents the total number of simultaneous occurrences of the first target item and the second target item in the hidden danger matrix, represents the total number of the first target items in the hidden danger matrix, represents the total number of the second target items in the hidden danger matrix; The sixth calculation unit is used to calculate the difference between the association rule and the preset rule knowledge base according to the hidden danger matrix and the preset rule knowledge base using the following formula: in, represents the difference between the first target item and the set of association rule antecedents in the preset rule knowledge base, Indicates the difference between the second target item and the set of subsequent items of the association rules in the preset rule knowledge base; , represents the number of items in the association rule antecedent set in the preset rule knowledge base, Indicates that the first target item is associated with the first item in the set of association rule antecedents in the preset rule knowledge base. i The difference between the first target item and the first target item in the association rule antecedent set in the preset rule knowledge base is i When the items belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 1; when the first target item is associated with the first item in the association rule antecedent set in the preset rule knowledge base i When the items belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 0.5; when the first target item is the same as the i-th item in the association rule antecedent set in the preset rule knowledge base, The value is 0; , represents the number of items in the set of subsequent items of the association rule in the preset rule knowledge base, Indicates that the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base. j The difference between the second target item and the first item in the association rule subsequent item set in the preset rule knowledge base is j When the items belong to hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 1; when the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base j When the items belong to different contents in the hidden danger type information, hidden danger level information, time granularity information, time period information, hidden danger subject information or spatial location information, The value is 0.5; when the second target item is associated with the first item in the set of subsequent items of the association rule in the preset rule knowledge base j When the items are the same, The value is 0.
5. The mining device for recording data of potential safety hazards in mines according to claim 4, characterized in that: The rectification period is determined by the difference between the hidden danger occurrence time and the hidden danger review time in the safety hidden danger record data.
6. The mining device for recording data of potential safety hazards in mines according to claim 4, characterized in that: The set time granularity is quarterly.
7. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for mining safety hazard record data for mines as described in any one of claims 1 to 3.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for mining safety hazard record data of a mine as claimed in any one of claims 1 to 3 are executed.
Citation Information
Patent Citations
Weighted association rule mining method based on data source partition matrix
CN106126577A
Safety production big data analysis and mining method and system
CN110096532A
Improved association rule report data mining method based on mutual exclusion expression
CN111309777A
Mine potential safety hazard identification and early warning system based on big data analysis
CN113688169A
Privacy protection method in association rule mining and storage medium
CN117910044A
