Coal mine safety monitoring data mining method and system based on AI artificial intelligence

Abstract

The invention discloses a coal mine safety monitoring data mining method and system based on AI artificial intelligence, and the method comprises the steps: collecting and preprocessing multiple safety monitoring data of a target coal mine, and extracting demand data in the preprocessed safety monitoring data; determining a related service type of each type of data in the demand data, and establishing a related network model according to the related service type; obtaining a security problem of the user, calling a target network model through AI artificial intelligence according to the security problem, obtaining a data rule and a development trend corresponding to the security problem through the target network model, and determining a security situation according to the data rule and the development trend; and performing risk prediction on the coal mine based on the safety situation, determining risk factors and hidden danger types, generating a risk report, uploading the risk report and sending out an early warning signal. Risk prediction and security situation assessment can be quickly performed according to the acquired data based on artificial intelligence, so that the labor cost is reduced while the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of coal mine monitoring technology, and in particular to a coal mine safety monitoring data mining method and system based on AI artificial intelligence. Background Art

[0002] In recent years, coal mine accidents have occurred repeatedly, and coal mine safety issues have become increasingly prominent. Therefore, it is very important to monitor the safety status of coal mines to respond to emergencies. Coal mine enterprise safety risk management is the basic guarantee for safe production, and risk identification and management are important measures to prevent safety accidents in coal mine enterprises.

[0003] At present, the risk control of coal mine enterprises is mainly carried out through the relevant department personnel to conduct daily inspections at each affiliated coal mine, monitor data transcription, report summary, manual calculation and analysis, and telephone text message notification to check and predict the hidden dangers and risks of coal mines. The hidden dangers and risks of daily inspections are reported step by step in the form of report documents, and the risk disposal measures and management methods formed by the superior management unit are issued step by step in the form of documents. The risk monitoring, disposal and control work are complicated, resulting in low work efficiency, untimely risk investigation and disposal, and inability to achieve real-time control; daily inspections and multi-level reporting may have blind spots such as missed reports and late reports, and risks that are not checked in time still pose a threat to mine safety. Secondly, the risk alarm information push notification is not timely. After the risk is found by manual calculation and analysis, the manual editing of text messages is slow, resulting in low efficiency in the transmission of risk disposal information. Summary of the invention

[0004] In response to the above-mentioned problems, the present invention provides a coal mine safety monitoring data mining method and system based on AI artificial intelligence to solve the problems mentioned in the background technology, such as the complicated manual investigation process, low work efficiency and inability to achieve real-time management and control. At the same time, after the risk is discovered, the manual editing of text messages is slow, resulting in low efficiency in transmitting risk management information.

[0005] A coal mine safety monitoring data mining method based on AI artificial intelligence includes the following steps:

[0006] Collect multiple safety monitoring data of the target coal mine and pre-process them, and extract the required data from the pre-processed safety monitoring data;

[0007] Determine the relevant business types of each type of data in the demand data, and establish relevant network models according to the relevant business types;

[0008] Obtain the user's security issues, use AI to retrieve the target network model based on the security issues, obtain the data patterns and development trends corresponding to the security issues through the target network model, and determine the security situation based on the data patterns and development trends;

[0009] Based on the safety situation, risk prediction is carried out for coal mines, risk factors and hidden danger types are determined, risk reports are generated and uploaded, and early warning signals are issued.

[0010] Preferably, the collecting of a plurality of safety monitoring data of the target coal mine and preprocessing the data, and extracting the required data from the preprocessed safety monitoring data, comprises:

[0011] Determine multiple safety monitoring areas of the target coal mine, determine the data collection method for each safety monitoring area, and collect safety monitoring data for each safety monitoring area through the data collection method;

[0012] Perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data;

[0013] Determine the associated risk attribute item of each piece of data in the preprocessed safety monitoring data, and filter out the first safety monitoring data according to the associated risk attribute item;

[0014] The data demand of the user is obtained, and the second safety monitoring data is extracted from the first safety monitoring data according to the data renewal as the user's demand data.

[0015] Preferably, the determining of the relevant service type of each type of data in the demand data and establishing the relevant network model according to the relevant service type includes:

[0016] Determine the data collection scenarios and data contents of each type of data in the demand data, determine the function parameters according to the data collection scenarios, and obtain multiple related businesses of the function parameters;

[0017] Determine state description information and data features according to data content of each type of data, and determine relevant business types of each type of data among multiple relevant businesses according to the state description information and data features;

[0018] Determine business needs according to relevant business types, and build a regression network model for each type of data based on the business needs through the data values ​​of each type of data.

[0019] Preferably, the obtaining of the user's security issues, calling the target network model through AI artificial intelligence according to the security issues, obtaining the data rules and development trends corresponding to the security issues through the target network model, and determining the security situation according to the data rules and development trends include:

[0020] Obtain the user's security report, obtain security log information based on the security report, and obtain the user's security issues based on the security log information;

[0021] Determine the associated services based on the user's security issues, and use AI to retrieve the target network model corresponding to the associated services.

[0022] Determine data patterns through target network model combined with real-time security monitoring data, conduct data mining based on data patterns, and determine data development trends based on mining results;

[0023] Determine data anomalies based on data development trends, and determine security trends based on data anomalies.

[0024] Preferably, the risk prediction of the coal mine based on the safety situation, determining the risk factors and hidden danger types, generating a risk report for uploading and issuing a warning signal includes:

[0025] Determine the abnormal data characteristics based on the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators;

[0026] According to the correlation coefficient between the characteristic index and each associated risk factor, the risk of the coal mine is predicted, and the environmental risk factor, state risk factor and operation risk factor of the coal mine are determined;

[0027] Determine the potential hidden danger types of coal mines based on coal mine environmental risk factors, state risk factors and operation risk factors;

[0028] A risk report is generated based on the potential hidden dangers of the coal mine and uploaded to the server, while a sound warning signal is issued as a prompt.

[0029] A coal mine safety monitoring data mining system based on AI artificial intelligence, the system includes:

[0030] An extraction module is used to collect multiple safety monitoring data of the target coal mine and pre-process them, and extract the required data from the pre-processed safety monitoring data;

[0031] A construction module is used to determine the relevant business types of each type of data in the demand data, and to establish relevant network models according to the relevant business types;

[0032] The determination module is used to obtain the user's security issues, call the target network model through AI artificial intelligence based on the security issues, obtain the data patterns and development trends corresponding to the security issues through the target network model, and determine the security situation based on the data patterns and development trends;

[0033] The prediction module is used to predict the risks of coal mines based on the safety situation, determine the risk factors and hidden danger types, generate risk reports for uploading and issue early warning signals.

[0034] Preferably, the extraction module comprises:

[0035] The collection submodule is used to determine multiple safety monitoring areas of the target coal mine, determine the data collection method for each safety monitoring area, and collect safety monitoring data for each safety monitoring area through the data collection method;

[0036] The preprocessing submodule is used to perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data;

[0037] A selection submodule is used to determine the associated risk attribute items of each piece of data in the preprocessed safety monitoring data, and filter out the first safety monitoring data according to the associated risk attribute items;

[0038] The extraction submodule is used to obtain the user's data demand and extract the second safety monitoring data from the first safety monitoring data as the user's demand data according to the data renewal.

[0039] Preferably, the building blocks include:

[0040] The first determination submodule is used to determine the data collection scenario and data content of each type of data in the demand data, determine the function parameters according to the data collection scenario, and obtain multiple related services of the function parameters;

[0041] A second determination submodule is used to determine the state description information and data characteristics according to the data content of each type of data, and determine the relevant business type of each type of data among multiple relevant businesses according to the state description information and data characteristics;

[0042] The construction submodule is used to determine the business requirements according to the relevant business types, and to construct a regression network model of the data type through the data values ​​of each type of data based on the business requirements.

[0043] Preferably, the determining module includes:

[0044] The acquisition submodule is used to obtain the user's security report, obtain security log information according to the security report, and obtain the user's security issues based on the security log information;

[0045] The retrieval submodule is used to determine the associated services based on the user's security issues, and retrieve the target network model corresponding to the associated services through AI artificial intelligence based on the associated services;

[0046] The data mining submodule is used to determine the data rules by combining the target network model with the real-time security monitoring data, conduct data mining based on the data rules, and determine the data development trend based on the mining results;

[0047] The third determination submodule is used to determine data anomalies according to data development trends, and determine security situations according to the data anomalies.

[0048] Preferably, the prediction module comprises:

[0049] The fourth determination submodule is used to determine the abnormal data characteristics according to the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators;

[0050] The prediction submodule is used to predict the risk of coal mines according to the correlation coefficient between the characteristic index and each associated risk factor, and determine the environmental risk factor, state risk factor and operation risk factor of the coal mine;

[0051] The fifth determination submodule is used to determine the potential hidden danger type of the coal mine according to the coal mine environmental risk factor, state risk factor and operation risk factor;

[0052] The early warning module is used to generate risk reports based on the potential hidden dangers of coal mines and upload them to the server while issuing sound early warning signals for prompts.

[0053] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0056] Figure 1 A workflow diagram of a coal mine safety monitoring data mining method based on AI artificial intelligence provided by the present invention;

[0057] Figure 2 Another workflow diagram of a coal mine safety monitoring data mining method based on AI artificial intelligence provided by the present invention;

[0058] Figure 3 This is a structural schematic diagram of a coal mine safety monitoring data mining system based on AI artificial intelligence provided by the present invention;

[0059] Figure 4 This is a structural schematic diagram of an extraction module in a coal mine safety monitoring data mining system based on AI artificial intelligence provided by the present invention. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0061] In recent years, coal mine accidents have occurred repeatedly, and coal mine safety issues have become increasingly prominent. Therefore, it is very important to monitor the safety status of coal mines to respond to emergencies. Coal mine enterprise safety risk management is the basic guarantee for safe production, and risk identification and management are important measures to prevent safety accidents in coal mine enterprises.

[0062] At present, the risk control of coal mine enterprises is mainly carried out by relevant department personnel to conduct daily inspections, monitor data transcription, report summary, manual calculation and analysis, and telephone text message notifications to investigate and predict the hidden dangers and risks of coal mines. The hidden dangers and risks of daily inspections are reported step by step in the form of report documents, and the risk disposal measures and management methods formed by the superior management unit are issued step by step in the form of documents. The risk monitoring, disposal and control work are complicated, resulting in low work efficiency, untimely risk investigation and disposal, and inability to achieve real-time control; daily inspections and multi-level reporting may have blind spots such as missed reports and late reports, and risks that are not timely investigated still pose a threat to mine safety. Secondly, the risk alarm information push notification is not timely. After the risk is found by manual calculation and analysis, the manual editing of text messages is slow, resulting in low efficiency in the transmission of risk disposal information. In order to solve the above problems, this embodiment discloses a coal mine safety monitoring data mining method based on AI artificial intelligence.

[0063] A coal mine safety monitoring data mining method based on AI artificial intelligence, such as Figure 1 As shown, the following steps are included:

[0064] Step S101, collecting multiple safety monitoring data of the target coal mine and preprocessing them, and extracting demand data from the preprocessed safety monitoring data;

[0065] Step S102: Determine the relevant service type of each type of data in the demand data, and establish a relevant network model according to the relevant service type;

[0066] Step S103: Obtain the user's security issues, call the target network model through AI artificial intelligence according to the security issues, obtain the data rules and development trends corresponding to the security issues through the target network model, and determine the security situation according to the data rules and development trends;

[0067] Step S104: predict the risk of the coal mine based on the safety situation, determine the risk factors and hidden danger types, generate a risk report for uploading and issue a warning signal.

[0068] In this embodiment, a plurality of security monitoring data are acquired by way of sensors or server calls;

[0069] In this embodiment, the safety monitoring data includes: mine pressure, gas concentration, water level, ventilation volume, etc.

[0070] The working principle of the above technical solution is: collect multiple safety monitoring data of the target coal mine and pre-process them, extract the demand data from the pre-processed safety monitoring data; determine the relevant business types of each type of data in the demand data, and establish relevant network models according to the relevant business types; obtain the user's safety issues, call the target network model through AI artificial intelligence according to the safety issues, obtain the data laws and development trends corresponding to the safety issues through the target network model, and determine the safety situation according to the data laws and development trends; predict the risks of coal mines based on the safety situation, determine the risk factors and hidden danger types, generate risk reports for upload and issue early warning signals.

[0071] The beneficial effects of the above technical solution are as follows: by constructing a network model based on various businesses and business-related data in the coal mine, and then using the network model to perform data mining and development trend prediction based on the periodic changes of business-related data to determine the safety situation of the coal mine, and then performing intelligent risk prediction, risk prediction and safety situation assessment can be quickly performed based on the collected data based on artificial intelligence, without the need for manual investigation, which improves work efficiency while reducing labor costs, and realizes early detection and prediction of safety hazards in coal mines, which can effectively avoid the occurrence of safety accidents and improve safety. Furthermore, by quickly generating risk reports for uploading and issuing early warning signals, reports can be quickly transmitted online through the network, so that staff can quickly know the hidden dangers and risks of coal mines, improving the efficiency of information transmission and the staff's experience, and solving the problems mentioned in the prior art of complicated manual investigation procedures, low work efficiency and inability to achieve real-time control. At the same time, after the risk is discovered, the manual editing of text messages is slow to send, resulting in low efficiency in risk handling information transmission.

[0072] In one embodiment, Figure 2 As shown, the multiple safety monitoring data of the target coal mine are collected and preprocessed, and the required data in the preprocessed safety monitoring data are extracted, including:

[0073] Step S201, determining multiple safety monitoring areas of the target coal mine, determining a data collection method for each safety monitoring area, and collecting safety monitoring data for each safety monitoring area through the data collection method;

[0074] Step S202: Perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data;

[0075] Step S203, determining the associated risk attribute items of each piece of data in the preprocessed safety monitoring data, and filtering out the first safety monitoring data according to the associated risk attribute items;

[0076] Step S204: obtaining the user's data demand, and extracting the second safety monitoring data from the first safety monitoring data as the user's demand data according to the data renewal.

[0077] In this embodiment, the safety monitoring field refers to the monitoring work field for coal mine safety, such as: coal transportation field, coal washing field, coal production field, etc.

[0078] The beneficial effects of the above technical solution are: by collecting security monitoring data of each security monitoring field and performing preprocessing, the quality of the data can be improved, the associated risk attribute items of each data in the preprocessed security monitoring data can be determined and the first security monitoring data can be screened out, and the second security monitoring data can be extracted from the first security monitoring data as demand data according to user needs, the second security monitoring data required by the user can be accurately and quickly screened out, and the security monitoring data with low risks can be excluded, thereby narrowing the range of data screening samples and improving screening efficiency.

[0079] In one embodiment, determining the relevant service type of each type of data in the demand data and establishing the relevant network model according to the relevant service type includes:

[0080] Determine the data collection scenarios and data contents of each type of data in the demand data, determine the function parameters according to the data collection scenarios, and obtain multiple related businesses of the function parameters;

[0081] Determine state description information and data features according to data content of each type of data, and determine relevant business types of each type of data among multiple relevant businesses according to the state description information and data features;

[0082] Determine business needs according to relevant business types, and build a regression network model for each type of data based on the business needs through the data values ​​of each type of data.

[0083] The beneficial effects of the above technical solution are: determining the functional parameters according to the data collection scenario, obtaining multiple related businesses of the functional parameters, quickly determining multiple different businesses corresponding to the parameters, and improving the efficiency of data processing. Furthermore, determining the related business type of each type of data according to the data content of each type of data, and constructing a regression network model for this type of data can improve the prediction accuracy and generalization ability of the model, which helps to more accurately predict the results and improve the adaptability of the model in various situations.

[0084] In one embodiment, the obtaining of the user's security issues, calling the target network model through AI artificial intelligence according to the security issues, obtaining the data rules and development trends corresponding to the security issues through the target network model, and determining the security situation according to the data rules and development trends include:

[0085] Obtain the user's security report, obtain security log information based on the security report, and obtain the user's security issues based on the security log information;

[0086] Determine the associated services based on the user's security issues, and use AI to retrieve the target network model corresponding to the associated services.

[0087] Determine data patterns through target network model combined with real-time security monitoring data, conduct data mining based on data patterns, and determine data development trends based on mining results;

[0088] Determine data anomalies based on data development trends, and determine security trends based on data anomalies.

[0089] The beneficial effects of the above technical solution are: obtaining the user's security issues based on the user's security report, determining the related business and calling the corresponding target network model through AI artificial intelligence, and selecting the adapted network model for data mining and prediction, thereby improving work efficiency. Furthermore, the data development trend is determined, the security situation is determined, and by monitoring the data trend, any abnormal situation can be discovered in time, the development trend of coal mine safety can be determined at all times, and the monitoring efficiency and stability can be improved.

[0090] In one embodiment, the risk prediction of the coal mine based on the safety situation, determining the risk factors and hidden danger types, generating a risk report for uploading and issuing an early warning signal includes:

[0091] Determine the abnormal data characteristics based on the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators;

[0092] According to the correlation coefficient between the characteristic index and each associated risk factor, the risk of the coal mine is predicted, and the environmental risk factor, state risk factor and operation risk factor of the coal mine are determined;

[0093] Determine the potential hidden danger types of coal mines based on coal mine environmental risk factors, state risk factors and operation risk factors;

[0094] A risk report is generated based on the potential hidden dangers of the coal mine and uploaded to the server, while a sound warning signal is issued as a prompt.

[0095] The beneficial effects of the above technical solution are: risk prediction of coal mines is carried out according to the correlation coefficient between the characteristic indicators corresponding to the abnormal data characteristics and each associated risk factor, and the potential hidden danger types of coal mines are determined. The safety status of coal mines can be assessed more accurately, and corresponding measures can be taken in time to reduce risks, generate risk reports and issue early warning signals, so as to timely discover problems and issue early warnings, greatly reducing the dangers brought by risks.

[0096] In one embodiment, this embodiment also discloses a coal mine safety monitoring data mining system based on AI artificial intelligence, such as Figure 3 As shown, the system includes:

[0097] An extraction module 301 is used to collect multiple safety monitoring data of a target coal mine and pre-process the data, and extract the required data from the pre-processed safety monitoring data;

[0098] A construction module 302 is used to determine the relevant business type of each type of data in the demand data, and establish a relevant network model according to the relevant business type;

[0099] The determination module 303 is used to obtain the user's security question and retrieve the target network model through AI artificial intelligence according to the security question.

[0100] Obtain the data patterns and development trends corresponding to security issues through the target network model, and determine the security situation based on the data patterns and development trends;

[0101] The prediction module 304 is used to predict the risk of the coal mine based on the safety situation, determine the risk factors and hidden danger types, generate a risk report for uploading and issue a warning signal.

[0102] The working principle and beneficial effects of the above technical solution have been explained in the method embodiment and will not be repeated here.

[0103] In one embodiment, Figure 4 As shown, the extraction module 301 includes:

[0104] The collection submodule 3011 is used to determine multiple safety monitoring areas of the target coal mine, determine the data collection method for each safety monitoring area, and collect safety monitoring data for each safety monitoring area through the data collection method;

[0105] The preprocessing submodule 3012 is used to perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data;

[0106] A selection submodule 3013 is used to determine the associated risk attribute item of each piece of data in the pre-processed safety monitoring data, and filter out the first safety monitoring data according to the associated risk attribute item;

[0107] The extraction submodule 3014 is used to obtain the data demand of the user and extract the second safety monitoring data from the first safety monitoring data as the user's demand data according to the data renewal.

[0108] In one embodiment, the building block comprises:

[0109] The first determination submodule is used to determine the data collection scenario and data content of each type of data in the demand data, determine the function parameters according to the data collection scenario, and obtain multiple related services of the function parameters;

[0110] A second determination submodule is used to determine the state description information and data characteristics according to the data content of each type of data, and determine the relevant business type of each type of data among multiple relevant businesses according to the state description information and data characteristics;

[0111] The construction submodule is used to determine the business requirements according to the relevant business types, and to construct a regression network model of the data type through the data values ​​of each type of data based on the business requirements.

[0112] In one embodiment, the determining module includes:

[0113] The acquisition submodule is used to obtain the user's security report, obtain security log information according to the security report, and obtain the user's security issues based on the security log information;

[0114] The retrieval submodule is used to determine the associated services based on the user's security issues, and retrieve the target network model corresponding to the associated services through AI artificial intelligence based on the associated services;

[0115] The data mining submodule is used to determine the data rules by combining the target network model with the real-time security monitoring data, conduct data mining based on the data rules, and determine the data development trend based on the mining results;

[0116] The third determination submodule is used to determine data anomalies according to data development trends, and determine security situations according to the data anomalies.

[0117] In one embodiment, the prediction module includes:

[0118] The fourth determination submodule is used to determine the abnormal data characteristics according to the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators;

[0119] The prediction submodule is used to predict the risk of coal mines according to the correlation coefficient between the characteristic index and each associated risk factor, and determine the environmental risk factor, state risk factor and operation risk factor of the coal mine;

[0120] The fifth determination submodule is used to determine the potential hidden danger type of the coal mine according to the coal mine environmental risk factor, state risk factor and operation risk factor;

[0121] The early warning module is used to generate risk reports based on the potential hidden dangers of coal mines and upload them to the server while issuing sound early warning signals for prompts.

[0122] Those skilled in the art should understand that the first and second in the present invention merely refer to different application stages.

[0123] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0124] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A coal mine safety monitoring data mining method based on AI artificial intelligence, characterized in that: The following steps are involved: Collect multiple safety monitoring data of the target coal mine and pre-process them, and extract the required data from the pre-processed safety monitoring data; Determine the relevant business types of each type of data in the demand data, and establish relevant network models according to the relevant business types; Obtain the user's security issues, use AI to retrieve the target network model based on the security issues, obtain the data patterns and development trends corresponding to the security issues through the target network model, and determine the security situation based on the data patterns and development trends; Based on the safety situation, risk prediction is carried out for coal mines, risk factors and hidden danger types are determined, risk reports are generated and uploaded, and early warning signals are issued.

2. The coal mine safety monitoring data mining method based on AI artificial intelligence according to claim 1 is characterized in that: The collecting of multiple safety monitoring data of the target coal mine and preprocessing thereof, and extracting the required data from the preprocessed safety monitoring data, include: Determine multiple safety monitoring areas of the target coal mine, determine the data collection method for each safety monitoring area, and collect safety monitoring data for each safety monitoring area through the data collection method; Perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data; Determine the associated risk attribute item of each piece of data in the preprocessed safety monitoring data, and filter out the first safety monitoring data according to the associated risk attribute item; The data demand of the user is obtained, and the second safety monitoring data is extracted from the first safety monitoring data according to the data renewal as the user's demand data.

3. The coal mine safety monitoring data mining method based on AI artificial intelligence according to claim 1 is characterized in that: The determining of the relevant service types of each type of data in the demand data and establishing the relevant network model according to the relevant service types includes: Determine the data collection scenarios and data contents of each type of data in the demand data, determine the function parameters according to the data collection scenarios, and obtain multiple related businesses of the function parameters; Determine state description information and data features according to data content of each type of data, and determine relevant business types of each type of data among multiple relevant businesses according to the state description information and data features; Determine business needs according to relevant business types, and build a regression network model for each type of data based on the business needs through the data values ​​of each type of data.

4. The coal mine safety monitoring data mining method based on AI artificial intelligence according to claim 1 is characterized in that: The obtaining of the user's security issues, calling the target network model through AI artificial intelligence according to the security issues, obtaining the data patterns and development trends corresponding to the security issues through the target network model, and determining the security situation according to the data patterns and development trends, include: Obtain the user's security report, obtain security log information based on the security report, and obtain the user's security issues based on the security log information; Determine the associated services based on the user's security issues, and use AI to retrieve the target network model corresponding to the associated services. Determine data patterns through target network model combined with real-time security monitoring data, conduct data mining based on data patterns, and determine data development trends based on mining results; Determine data anomalies based on data development trends, and determine security trends based on data anomalies.

5. The coal mine safety monitoring data mining method based on AI artificial intelligence according to claim 1 is characterized in that: The risk prediction of the coal mine based on the safety situation, determination of risk factors and hidden danger types, generation of risk reports for uploading and issuance of early warning signals include: Determine the abnormal data characteristics based on the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators; According to the correlation coefficient between the characteristic index and each associated risk factor, the risk of coal mines is predicted, and the environmental risk factor, state risk factor and operation risk factor of coal mines are determined; Determine the potential hidden danger types of coal mines based on coal mine environmental risk factors, state risk factors and operation risk factors; A risk report is generated based on the potential hidden dangers of the coal mine and uploaded to the server, while a sound warning signal is issued as a prompt.

6. A coal mine safety monitoring data mining system based on AI artificial intelligence, characterized in that: The system includes: An extraction module is used to collect multiple safety monitoring data of the target coal mine and pre-process them, and extract the required data from the pre-processed safety monitoring data; A construction module is used to determine the relevant business types of each type of data in the demand data, and to establish relevant network models according to the relevant business types; The determination module is used to obtain the user's security issues and use AI artificial intelligence to retrieve the target network model based on the security issues. Obtain the data patterns and development trends corresponding to security issues through the target network model, and determine the security situation based on the data patterns and development trends; The prediction module is used to predict the risks of coal mines based on the safety situation, determine the risk factors and hidden danger types, generate risk reports for uploading and issue early warning signals.

7. The coal mine safety monitoring data mining system based on AI artificial intelligence according to claim 6 is characterized in that: The extraction module comprises: The collection submodule is used to determine multiple safety monitoring areas of the target coal mine, determine the data collection method for each safety monitoring area, and collect safety monitoring data for each safety monitoring area through the data collection method; The preprocessing submodule is used to perform data cleaning and deduplication preprocessing on the safety monitoring data of each safety monitoring field to obtain the preprocessed safety monitoring data; A selection submodule is used to determine the associated risk attribute items of each piece of data in the preprocessed safety monitoring data, and filter out the first safety monitoring data according to the associated risk attribute items; The extraction submodule is used to obtain the user's data demand and extract the second safety monitoring data from the first safety monitoring data as the user's demand data according to the data renewal.

8. The coal mine safety monitoring data mining system based on AI artificial intelligence according to claim 6 is characterized in that: The building blocks include: The first determination submodule is used to determine the data collection scenario and data content of each type of data in the demand data, determine the function parameters according to the data collection scenario, and obtain multiple related services of the function parameters; A second determination submodule is used to determine the state description information and data characteristics according to the data content of each type of data, and determine the relevant business type of each type of data among multiple relevant businesses according to the state description information and data characteristics; The construction submodule is used to determine the business requirements according to the relevant business types, and to construct a regression network model of the data type through the data values ​​of each type of data based on the business requirements.

9. The coal mine safety monitoring data mining system based on AI artificial intelligence according to claim 6 is characterized in that: The determining module comprises: The acquisition submodule is used to obtain the user's security report, obtain security log information according to the security report, and obtain the user's security issues based on the security log information; The retrieval submodule is used to determine the associated services based on the user's security issues, and retrieve the target network model corresponding to the associated services through AI artificial intelligence based on the associated services; The data mining submodule is used to determine the data rules by combining the target network model with the real-time security monitoring data, conduct data mining based on the data rules, and determine the data development trend based on the mining results; The third determination submodule is used to determine data anomalies according to data development trends, and determine security situations according to the data anomalies.

10. The coal mine safety monitoring data mining system based on AI artificial intelligence according to claim 6 is characterized in that: The prediction module comprises: The fourth determination submodule is used to determine the abnormal data characteristics according to the security situation, obtain the characteristic indicators corresponding to the abnormal data characteristics, and determine the associated risk factors of the characteristic indicators; The prediction submodule is used to predict the risk of coal mines according to the correlation coefficient between the characteristic index and each associated risk factor, and determine the environmental risk factor, state risk factor and operation risk factor of the coal mine; The fifth determination submodule is used to determine the potential hidden danger type of the coal mine according to the coal mine environmental risk factor, state risk factor and operation risk factor; The early warning module is used to generate risk reports based on the potential hidden dangers of coal mines and upload them to the server while issuing sound early warning signals for prompts.

Images