Method and system for determining regulation-violating behaviors of personnel at different positions underground

Abstract

The present application provides a method and system for determining regulation-violating behaviors underground. The method comprises: acquiring historical personnel behavior hidden danger data within a target area underground, and performing text mining and data processing on the historical personnel behavior hidden danger data to obtain spatial-temporal patterns of hidden dangers and prediction and early-warning results; performing association analysis on the basis of personnel regulation-violating data, the spatial-temporal patterns of the hidden dangers and the prediction and early-warning results, and carrying out knowledge modeling to determine an ontology model; using a knowledge extraction method to extract knowledge elements of a knowledge graph from the ontology model; performing knowledge fusion processing on the knowledge elements to determine knowledge fusion data; on the basis of the knowledge fusion data, using a top-down and bottom-up hybrid construction method to construct the knowledge graph; and determining regulation-violating behaviors of personnel underground on the basis of the knowledge graph. The present application can dynamically diagnose safety production risks and regulation-violating behaviors in mines, and can discover and predict related accident signs and provide early warnings to ensure safety production.

Description

Method and system for judging illegal behaviors of personnel in different positions underground Technical Field

[0001] The present application relates to the technical field of underground illegal behavior judgment, and in particular, to a method and system for judging underground illegal behavior. Background Art

[0002] Currently, coal mine production faces challenges such as complex geological conditions, poorly equipped production facilities, unevenly qualified personnel, a relatively backward overall infrastructure, and low safety management. Employee violations are primarily managed manually, resulting in perfunctory safety inspections and hazard detection, and limited traceability of employee behavior. Advanced safety information technology is needed for rapid analysis and decision-making support. Currently, intelligent identification of violations is primarily targeted at the transportation sector, significantly different from underground coal mine production, making it impossible to accurately and dynamically diagnose violations by underground personnel. Summary of the Invention

[0003] In view of this, embodiments of this specification provide a method for determining underground illegal behavior. One or more embodiments of this specification also involve an apparatus for determining underground illegal behavior, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a method for determining an underground illegal behavior is provided, comprising:

[0005] A method for determining an underground illegal behavior, characterized in that the method comprises:

[0006] Obtaining underground employee violation data; wherein, underground employee violation data includes structured data, semi-structured data, and unstructured data in the field of underground employee violation;

[0007] Obtain historical data on personnel behavior hazards in the target area underground, conduct text mining and data processing on the historical personnel behavior hazard data, and obtain the temporal and spatial patterns of hazards and prediction and early warning results;

[0008] Based on employee violation data, spatial and temporal patterns of hidden dangers, and prediction and warning results, correlation analysis is conducted on unsafe behaviors, equipment indicator unsafe factors, environmental indicator unsafe factors, and management indicator unsafe factors in each type of work, and knowledge modeling is performed to determine the ontology model;

[0009] The knowledge extraction method is used to extract the knowledge elements of the knowledge graph from the ontology model; the knowledge elements include entities, relationships and attributes;

[0010] Perform knowledge fusion processing on knowledge elements and determine knowledge fusion data; knowledge fusion processing includes entity alignment, relationship fusion and attribute fusion;

[0011] Based on knowledge fusion data, a top-down and bottom-up hybrid construction method is used to build a knowledge graph;

[0012] Determine the illegal behavior of underground employees based on knowledge graph.

[0013] In one possible implementation, text mining and data processing are performed on historical data on potential hazards of human behavior to obtain temporal and spatial patterns of potential hazards and prediction and warning results, including:

[0014] Configure a Chinese word segmentation system based on historical personnel behavior risk data, add a custom dictionary, add and filter proper nouns and meaningless words, and obtain feature words;

[0015] Determine the perplexity, calculate the number of target clusters based on the perplexity, count the keyword frequencies based on the number of target clusters, and filter out keywords;

[0016] Calculate the LDA model based on Gibbs sampling, feature words and keywords, and identify the hidden danger categories based on the LDA model;

[0017] The hidden danger text is digitized according to the hidden danger category, and the hidden danger text after digitization is analyzed for its temporal and spatial regularity and prediction and warning are made to obtain the prediction and warning results.

[0018] In one possible implementation, the types of unsafe behaviors include irregular operations and failure to perform job duties;

[0019] Unsafe behaviors include preparatory work before operation, finishing work during operation and after operation.

[0020] Equipment indicator unsafe factors include unsafe conditions of equipment;

[0021] Environmental indicator unsafe factors include unsafe conditions of the environment collected by sensors;

[0022] Unsafe factors in management indicators include defects in management systems or technical measures.

[0023] In a possible implementation, performing knowledge fusion processing on knowledge elements includes:

[0024] Establish indicator quantification rules based on the likelihood of unsafe behavior and the severity of consequences, the risk value of unsafe conditions of each device, and the degree of implementation of various environmental indicators and management systems and measures;

[0025] Based on the risk matrix method and indicator quantification rules, determine the risk combination weight value of each unsafe behavior;

[0026] Knowledge fusion processing is performed based on risk combination weight values.

[0027] In one possible implementation, a hybrid top-down and bottom-up approach is used to construct the knowledge graph, including:

[0028] Analyze production information from different positions underground, define the ontology and data model of coal mine employee violations, and select knowledge with high confidence from the acquired entities, attributes, and relationships for conceptual abstraction and construct a model layer;

[0029] Summarize and summarize new knowledge and data, iteratively update the model layer, and conduct a new round of entity filling based on the updated model layer.

[0030] In one possible implementation, the method further includes:

[0031] Use knowledge graph visualization technology to display the interactive relationship between multiple information dimensions.

[0032] According to a second aspect of the embodiments of this specification, a device for determining an underground illegal behavior is provided, comprising:

[0033] A data acquisition module is configured to acquire underground employee violation data; wherein the underground employee violation data includes structured data, semi-structured data, and unstructured data in the field of underground employee violation;

[0034] The text mining module is configured to obtain historical personnel behavior hidden danger data in the target area underground, perform text mining and data processing on the historical personnel behavior hidden danger data, and obtain the temporal and spatial patterns of hidden dangers and prediction and warning results;

[0035] The model building module is configured to conduct correlation analysis on unsafe behaviors, equipment indicator unsafe factors, environmental indicator unsafe factors, and management indicator unsafe factors for each type of work based on employee violation data, temporal and spatial patterns of hidden dangers, and prediction and warning results, and to perform knowledge modeling to determine the ontology model;

[0036] A knowledge extraction module is configured to extract knowledge elements of the knowledge graph from the ontology model using a knowledge extraction method; the knowledge elements include entities, relationships, and attributes;

[0037] The module data fusion block is configured to perform knowledge fusion processing on knowledge elements and determine knowledge fusion data; the knowledge fusion processing includes entity alignment, relationship fusion and attribute fusion;

[0038] The graph construction module is configured to construct a knowledge graph based on knowledge fusion data using a top-down and bottom-up hybrid construction method;

[0039] The behavior judgment module is configured to judge the illegal behavior of underground employees based on the knowledge graph.

[0040] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0041] memory and processor;

[0042] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned method for determining underground illegal behavior are realized.

[0043] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above-mentioned method for determining underground illegal behavior are implemented.

[0044] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for determining underground illegal behavior.

[0045] The present application provides a method and system for judging illegal behavior underground, which includes: obtaining historical personnel behavior hidden danger data in the underground target area, performing text mining and data processing on the historical personnel behavior hidden danger data to obtain the temporal and spatial laws of hidden dangers and prediction and warning results; performing correlation analysis based on employee violation data, temporal and spatial laws of hidden dangers and prediction and warning results, and performing knowledge modeling to determine the ontology model; using a knowledge extraction method to extract knowledge elements of the knowledge graph from the ontology model; performing knowledge fusion processing on the knowledge elements to determine knowledge fusion data; based on the knowledge fusion data, using a top-down and bottom-up hybrid construction method to construct a knowledge graph; judging the illegal behavior of underground employees based on the knowledge graph. The present application can dynamically diagnose mine safety production risks and illegal behaviors, discover, predict and warn related accident signs, and ensure safe production. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0047] FIG1 is a flow chart of a method for determining an underground illegal behavior according to an embodiment of the present application;

[0048] FIG2 is a flow chart of coal mine hidden danger analysis and mining based on text mining in an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of the specific construction process of the knowledge graph in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objectives, features and advantages of the present application more clearly understood, the following detailed description of the specific embodiments of the present application is given in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0051] The embodiment of the present application designs a method for judging illegal behaviors for different positions and types of work in different scenarios underground. It models the knowledge of employee violations through the actual production situation of underground operations such as coal mines. By establishing quantitative rules for indicators and applying the risk matrix method, it determines the risk combination weight values ​​of unsafe behaviors of personnel, equipment, environment and management, constructs a knowledge graph of illegal behaviors, and uses knowledge graph visualization technology to display the interactive relationship between multiple information dimensions. By analyzing the types of work and the categories of violations, the types of work and the nature of violations, the types of work and the locations of violations, and the types of work, types of work, personnel and locations, it diagnoses the illegal behaviors in mines, provides decision support, further improves the efficiency of coal mine safety production management, and provides theoretical support for the intelligent management of coal mines.

[0052] FIG1 is a flow chart of a method for determining an underground illegal behavior provided by an embodiment of the present application. The method includes the following steps:

[0053] S102, obtaining underground employee violation data; wherein the underground employee violation data includes structured data, semi-structured data and unstructured data in the field of underground employee violation.

[0054] In practical applications, violation data is obtained through structured, semi-structured, and unstructured data sources in the field of coal mine employee violations. Violation data mainly includes: violation records of different positions and types of work, violation documents, and other highly professional resource data. Specifically, it includes: (1) structured data, including relational databases stored in laboratory database systems; (2) semi-structured data, including website data within the coal mining industry; (3) unstructured data, including coal mine violation manuals, standards, specifications, as well as the Internet, encyclopedias, and documents.

[0055] S104, obtaining historical personnel behavior hidden danger data in the target area underground, performing text mining and data processing on the historical personnel behavior hidden danger data, and obtaining the temporal and spatial laws of hidden dangers and prediction and warning results.

[0056] In one possible implementation, text mining and digitization are performed on historical personnel behavior hidden danger data to obtain the temporal and spatial patterns of hidden dangers and prediction and warning results, including: configuring a Chinese word segmentation system based on the historical personnel behavior hidden danger data, adding a custom dictionary, adding and filtering proper nouns and meaningless words, and obtaining feature words; determining the perplexity, and calculating the number of target clusters based on the perplexity, counting the keyword frequency based on the number of target clusters, and filtering out keywords; calculating the LDA model based on Gibbs sampling, feature words and keywords, and identifying the hidden danger category based on the LDA model; digitizing the hidden danger text according to the hidden danger category, and analyzing the temporal and spatial patterns of the hidden dangers and making predictions and warnings on the digitized hidden danger text to obtain prediction and warning results.

[0057] For example, FIG2 shows a flow chart of coal mine hidden danger analysis and mining based on text mining, including:

[0058] S21, collecting historical data of hidden dangers, can be performed specifically through text topic mining technology and visualization technology.

[0059] S22, construct a text topic mining model based on historical personnel behavior risk data.

[0060] S23: Configure the Chinese word segmentation system and extract feature words. Feature words are extracted based on the TF-IDF (Term Frequency–Inverse Document Frequency) algorithm.

[0061] S24, calculate the optimal number of clusters based on the perplexity.

[0062] S25, calculates the LDA (Latent Dirichlet Allocation) model based on Gibbs sampling.

[0063] S26, combined with LDA model identification to obtain the hidden danger category.

[0064] S27, digitize the hidden danger text according to the obtained hidden danger category.

[0065] S28, analyze the temporal and spatial patterns of hidden dangers in the digitized data.

[0066] S29, predicting the occurrence of future hidden dangers based on time series neural network.

[0067] S30, visualization results display.

[0068] S106, based on employee violation data, spatial and temporal patterns of hidden dangers and prediction and warning results, conduct correlation analysis on unsafe behaviors of various types of work, unsafe factors of equipment indicators, unsafe factors of environmental indicators and unsafe factors of management indicators, and perform knowledge modeling to determine the ontology model.

[0069] Specifically, taking coal mine production as an example, personnel violations are not only related to job violations but also to unsafe factors related to materials, the environment, and management. This paper analyzes four aspects: underground work positions, equipment and facilities, environmental monitoring sensors, corresponding management systems, and geological disaster prevention and control measures. This paper models the domain knowledge of coal mine employee violations from the perspectives of concepts, relationships, and attributes.

[0070] Furthermore, we analyzed the job responsibilities, job classification, and violation information for underground workers such as shearer drivers, pump station workers, belt conveyor drivers, hydraulic support workers, scraper conveyor drivers, dust control workers, gas inspectors, end maintenance workers, endless rope winch drivers, transfer machine operators, and crusher operators. Unsafe behaviors primarily include: improper operation, failure to perform job duties, and other unsafe factors. For the personnel indicators constructed in this embodiment, unsafe factors for each indicator are extracted from three aspects: pre-operation preparation, operation during operation, and post-operation finishing work.

[0071] Furthermore, the unsafe factors of equipment indicators are mainly reflected in the unsafe state of the equipment, such as the equipment being affected by human, environmental or its own materials, accessories and damage during use, resulting in a decrease in the equipment's integrity rate, incomplete functions, insensitivity, etc., such as incomplete equipment protection; incomplete and intact protective facilities; incomplete, unclear and correct equipment warning signs; and other factors.

[0072] Furthermore, unsafe environmental indicators are primarily manifested in unsafe conditions, such as excessive methane concentrations; excessive concentrations of harmful gases; oxygen concentrations that do not meet coal mine safety regulations; excessive coal dust concentrations; poor ventilation; and inappropriate ambient temperature and humidity. Environmental sensors deployed in the two chutes include wind stations, methane sensors, dust detectors, and carbon monoxide concentration monitors.

[0073] Furthermore, the unsafe factors of management indicators are mainly reflected in the defects of management systems or technical measures, such as whether the management system and relevant technical measures for geological disaster prevention and control are sound and implemented; unreasonable and imperfect organizational structure, unclear responsibilities; incomplete rules and regulations, etc.

[0074] The ontology model is obtained by modeling based on the analysis of unsafe behaviors of various types of work and the correlation between equipment, environment and management.

[0075] S108, using a knowledge extraction method to extract knowledge elements of the knowledge graph from the ontology model; knowledge elements include entities, relationships and attributes.

[0076] Among them, for the constructed ontology model, knowledge extraction technology is used to extract knowledge elements such as entities, relationships and attributes of the knowledge graph from multivariate data. Based on this, a series of high-quality fact expressions are formed, laying the foundation for the construction of the upper model layer.

[0077] After knowledge extraction, the production information of each position can be analyzed. Specifically, the production information of different positions in the coal mine can be analyzed and processed. Knowledge extraction technology can be used to obtain entities, attributes, and relationships. Select knowledge with high confidence for conceptual abstraction, update the initially constructed ontology, and then, based on the updated ontology model, match the newly extracted knowledge and data to fill in the entity.

[0078] S110, performing knowledge fusion processing on the knowledge elements to determine knowledge fusion data; the knowledge fusion processing includes entity alignment, relationship fusion and attribute fusion.

[0079] In one possible implementation, knowledge fusion processing of knowledge elements includes: constructing indicator quantification rules based on the possibility of unsafe behavior and the severity of the consequences, the risk value of the unsafe state of each equipment, and the degree of implementation of various environmental indicators and management systems and measures; determining the risk combination weight value of each unsafe behavior based on the risk matrix method and indicator quantification rules; and performing knowledge fusion processing based on the risk combination weight value.

[0080] The knowledge in the knowledge graph comes from multiple different data sources, so there are problems such as knowledge ambiguity and unclear relationships. Knowledge fusion processing is needed to eliminate the ambiguity between indicators such as entities, relationships, and attributes and factual objects, so that knowledge from different sources can be standardized and integrated. Based on the actual production situation, the possibility of unsafe behaviors and the severity of the consequences, and the risk value of the unsafe state of each piece of equipment, indicator quantification rules are constructed for various environmental indicators, the establishment and implementation of management systems and measures, and the risk matrix method is used to determine the risk combination weight value of each unsafe behavior.

[0081] S112, based on knowledge fusion data, adopts a top-down and bottom-up hybrid construction method to construct a knowledge graph.

[0082] In one possible implementation, a hybrid top-down and bottom-up construction method is used to construct the knowledge graph, including: analyzing production information of different positions underground, defining the ontology and data model of the coal mine employee violation field, and selecting knowledge with higher confidence from the obtained entities, attributes and relationships for conceptual abstraction to construct a model layer; summarizing the new knowledge and data, iteratively updating the model layer, and conducting a new round of entity filling based on the updated model layer.

[0083] A hybrid top-down and bottom-up approach is used to construct the knowledge graph for traffic violations. First, a pattern layer is constructed. New knowledge and data are summarized and summarized, and the pattern layer is iteratively updated. Finally, based on the updated pattern layer, a new round of entity filling is performed. Figure 3 shows an example of the knowledge graph construction process.

[0084] As shown in Figure 3, knowledge modeling and data source acquisition are first performed, where knowledge modeling provides rule constraints for subsequent steps and data source acquisition provides data for subsequent steps; then knowledge acquisition and knowledge fusion are performed, and finally a knowledge graph of personnel violations is output.

[0085] Specifically, natural language processing technologies are used to automatically identify and extract domain knowledge. The domain knowledge of coal mine employee violations is modeled from the perspectives of concepts, relationships, and attributes. Knowledge is acquired from structured, semi-structured, and unstructured data sources in this domain. This acquired knowledge is then integrated and stored in a graph database to form a knowledge graph for coal mine employee violations.

[0086] S114, judging the illegal behavior of underground employees based on the knowledge graph.

[0087] Based on the constructed knowledge graph of violation behaviors, the knowledge graph visualization technology can be used to display the interactive relationship between multiple information dimensions. By analyzing the types of work and violation categories, the types of work and violation natures, the types of work and violation locations, and the types of work, personnel, and locations, violations can be judged and decision support can be provided.

[0088] The method for judging underground illegal behaviors provided in the embodiment of the present application models the domain knowledge of underground employees' violations, can dynamically diagnose mine safety production risks and illegal behaviors, discover, predict and warn related accident signs, and take preventive measures to ensure safe production.

[0089] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for determining underground illegal behavior. FIG4 shows a schematic structural diagram of a device for determining underground illegal behavior provided by one embodiment of this specification. As shown in FIG4 , the device includes:

[0090] The data acquisition module 401 is configured to acquire underground employee violation data; wherein the underground employee violation data includes structured data, semi-structured data, and unstructured data in the field of underground employee violation;

[0091] The text mining module 402 is configured to obtain historical personnel behavior hidden danger data in the target area underground, perform text mining and data processing on the historical personnel behavior hidden danger data, and obtain the temporal and spatial patterns of hidden dangers and prediction and warning results;

[0092] Model building module 403 is configured to perform correlation analysis on unsafe behaviors, equipment indicator unsafe factors, environmental indicator unsafe factors, and management indicator unsafe factors for each type of work based on employee violation data, temporal and spatial patterns of hidden dangers, and prediction and warning results, and to perform knowledge modeling to determine an ontology model;

[0093] The knowledge extraction module 404 is configured to extract knowledge elements of the knowledge graph from the ontology model using a knowledge extraction method; the knowledge elements include entities, relationships, and attributes;

[0094] The module data fusion block 405 is configured to perform knowledge fusion processing on the knowledge elements and determine knowledge fusion data; the knowledge fusion processing includes entity alignment, relationship fusion and attribute fusion;

[0095] A graph construction module 406 is configured to construct a knowledge graph based on the knowledge fusion data using a top-down and bottom-up hybrid construction method;

[0096] The behavior judgment module 407 is configured to judge the illegal behavior of underground employees based on the knowledge graph.

[0097] In a possible implementation, the text mining module 402 is further configured to:

[0098] Configure a Chinese word segmentation system based on historical personnel behavior risk data, add a custom dictionary, add and filter proper nouns and meaningless words, and obtain feature words;

[0099] Determine the perplexity, calculate the number of target clusters based on the perplexity, count the keyword frequencies based on the number of target clusters, and filter out keywords;

[0100] Calculate the LDA model based on Gibbs sampling, feature words and keywords, and identify the hidden danger categories based on the LDA model;

[0101] The hidden danger text is digitized according to the hidden danger category, and the hidden danger text after digitization is analyzed for its temporal and spatial regularity and prediction and warning are made to obtain the prediction and warning results.

[0102] In a possible implementation, the model building module 403 is further configured to:

[0103] Types of unsafe behaviors include non-standard operations and failure to perform job duties;

[0104] Unsafe behaviors include preparatory work before operation, finishing work during operation and after operation.

[0105] Equipment indicator unsafe factors include unsafe conditions of equipment;

[0106] Environmental indicator unsafe factors include unsafe conditions of the environment collected by sensors;

[0107] Unsafe factors in management indicators include defects in management systems or technical measures.

[0108] In a possible implementation, the module data fusion block 405 is further configured to:

[0109] Establish indicator quantification rules based on the likelihood of unsafe behavior and the severity of consequences, the risk value of unsafe conditions of each device, and the degree of implementation of various environmental indicators and management systems and measures;

[0110] Based on the risk matrix method and indicator quantification rules, determine the risk combination weight value of each unsafe behavior;

[0111] Knowledge fusion processing is performed based on risk combination weight values.

[0112] In a possible implementation, the graph construction module 406 is further configured to:

[0113] Analyze production information from different positions underground, define the ontology and data model of coal mine employee violations, and select knowledge with high confidence from the acquired entities, attributes, and relationships for conceptual abstraction and construct a model layer;

[0114] Summarize and summarize new knowledge and data, iteratively update the model layer, and conduct a new round of entity filling based on the updated model layer.

[0115] In a possible implementation, the behavior determination module 407 is further configured to:

[0116] Use knowledge graph visualization technology to display the interactive relationship between multiple information dimensions.

[0117] The above is a schematic diagram of a device for determining underground illegal behavior according to this embodiment. It should be noted that the technical solution of this device for determining underground illegal behavior is based on the same concept as the technical solution of the method for determining underground illegal behavior described above. For details not described in detail in the technical solution of the device for determining underground illegal behavior, please refer to the description of the technical solution of the method for determining underground illegal behavior described above.

[0118] Figure 5 shows a block diagram of a computing device 500 according to one embodiment of this specification. Components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0119] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface controller (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, or a near field communication (NFC) interface.

[0120] In one embodiment of the present specification, the aforementioned components of computing device 500 and other components not shown in FIG5 may also be connected to each other, for example, via a bus. It should be understood that the computing device structure block diagram shown in FIG5 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0121] Computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 500 can also be a mobile or stationary server.

[0122] The processor 520 is used to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for determining underground illegal behavior. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the above-mentioned method for determining underground illegal behavior belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the above-mentioned method for determining underground illegal behavior.

[0123] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the above-mentioned method for determining underground illegal behavior are implemented.

[0124] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solution of the method for determining underground illegal behavior described above. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the method for determining underground illegal behavior described above.

[0125] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for determining underground illegal behavior.

[0126] The above is a schematic diagram of a computer program according to this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the method for determining underground illegal behavior described above are based on the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the method for determining underground illegal behavior described above.

[0127] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium may be appropriately increased or decreased based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0129] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0130] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0131] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for judging underground illegal behaviors, characterized in that, the method includes: Obtain underground employee illegal data; wherein, the underground employee illegal data includes structured data, semi-structured data, and unstructured data in the field of underground employee violations; Obtain historical personnel behavior hazard data within the underground target area, perform text mining and data processing on the historical personnel behavior hazard data to obtain hazard spatio-temporal rules and prediction and early warning results; Based on the employee illegal data, the hazard spatio-temporal rules, and the prediction and early warning results, conduct a correlation analysis on unsafe behaviors, equipment index unsafe factors, environmental index unsafe factors, and management index unsafe factors for each type of work, and conduct knowledge modeling to determine the ontology model; Use a knowledge extraction method to extract knowledge elements of the knowledge graph from the ontology model; the knowledge elements include entities, relationships, and attributes; Perform knowledge fusion processing on the knowledge elements to determine knowledge fusion data; the knowledge fusion processing includes entity alignment, relationship fusion, and attribute fusion; Based on the knowledge fusion data, construct a knowledge graph using a hybrid construction method from top to bottom and from bottom to top; Judge underground employee illegal behaviors based on the knowledge graph.

2. The method according to claim 1, characterized in that, the performing text mining and data processing on the historical personnel behavior hazard data to obtain hazard spatio-temporal rules and prediction and early warning results includes: Configure a Chinese word segmentation system based on the historical personnel behavior hazard data, add a custom dictionary, add and screen proper nouns and meaningless words to obtain feature words; Determine the perplexity, calculate the target clustering number based on the perplexity, count the keyword frequencies based on the target clustering number, and screen to obtain keywords; Calculate the LDA model based on Gibbs sampling, the feature words, and the keywords, and identify the hazard categories based on the LDA model; Digitize the hazard text data according to the hazard categories, and perform hazard spatio-temporal rule analysis and make prediction and early warning on the digitized hazard text to obtain the prediction and early warning results.

3. The method according to claim 1, characterized in that, the types of the unsafe behaviors include non-standard operations and failure to perform the duties of the post; the unsafe behaviors include the preparatory work before operation, the work during operation, and the finishing work after operation; the equipment index unsafe factors include the unsafe states of the equipment; the environmental index unsafe factors include the unsafe conditions of the environment collected by sensors; the management index unsafe factors include defects in management systems or technical measures.

4. The method according to claim 3, characterized in that, the performing knowledge fusion processing on the knowledge elements includes: Construct index quantization rules according to the likelihood of occurrence and severity of consequences of unsafe behaviors, the risk values of each equipment unsafe state, the environmental indicators, and the implementation degree of management systems and measures; Based on the risk matrix method and the index quantization rules, determine the risk combination weight values of each unsafe behavior; Perform knowledge fusion processing based on the risk combination weight values.

5. The method according to claim 3, wherein, the knowledge graph construction is performed by using a hybrid construction method of top-down and bottom-up, including: analyzing the production information of different underground positions, defining the ontology and data schema of the coal mine employees' violation field, and at the same time selecting the knowledge with higher confidence in the obtained entities, attributes and relationships for concept abstraction to construct the schema layer; summarizing the new knowledge and data, iteratively updating the schema layer, and based on the updated schema layer, performing a new round of entity filling.

6. The method according to claim 1, wherein, the method further includes: using knowledge graph visualization technology to display the interaction relationships between multiple information dimensions.

7. A judgment system for underground violation behaviors, wherein, it includes: a data acquisition module configured to acquire underground employees' violation data; wherein, the underground employees' violation data includes structured data, semi-structured data and unstructured data in the field of underground employees' violations; a text mining module configured to acquire the historical personnel behavior hazard data in the underground target area, perform text mining and data processing on the historical personnel behavior hazard data to obtain the hazard spatio-temporal rules and prediction and early warning results; a model construction module configured to perform correlation analysis on the unsafe behaviors of each work type, the unsafe factors of equipment indicators, the unsafe factors of environmental indicators and the unsafe factors of management indicators based on the employees' violation data, the hazard spatio-temporal rules and the prediction and early warning results, and perform knowledge modeling to determine the ontology model; a knowledge extraction module configured to extract the knowledge elements of the knowledge graph from the ontology model by using a knowledge extraction method; the knowledge elements include entities, relationships and attributes; a data fusion module configured to perform knowledge fusion processing on the knowledge elements to determine the knowledge fusion data; the knowledge fusion processing includes entity alignment, relationship fusion and attribute fusion; a graph construction module configured to construct a knowledge graph based on the knowledge fusion data by using a hybrid construction method of top-down and bottom-up; a behavior judgment module configured to judge the underground employees' violation behaviors based on the knowledge graph.

8. A computing device, wherein, it includes: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the judgment method for underground violation behaviors according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the judgment method for underground violation behaviors according to any one of claims 1 to 6 are implemented.

Images