Mining area risk determination method and device

Abstract

The invention relates to the technical field of mining area management, in particular to a mining area risk determination method and device. The method comprises the following steps: acquiring multi-dimensional mining area data corresponding to a mining area scene; the multi-dimensional mining area data comprises personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; under the condition of determining that the mining area data of any dimension has the security risk, taking the mining area data of the dimension as the mining area data of the target dimension, and analyzing a time sequence association relationship and a space association relationship between the mining area data of the target dimension and the mining area data of other dimensions; and determining the risk evolution level of the mining area scene according to the time sequence association relationship and the space association relationship. According to the method and the device, by acquiring the multi-dimensional mining area data and analyzing the time sequence association relationship and the space association relationship between the target-dimensional mining area data and the other-dimensional mining area data, the problem of limitation of identifying and evaluating potential risks of a mining area at present is solved, and the technical effect of comprehensively analyzing the mining area risks is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of mining area management, and in particular to a method and device for determining mining area risks. Background Art

[0002] Mine safety management is aimed at various safety risks and hidden dangers in the mine production process. Through the comprehensive use of diversified management methods, advanced technical measures and strict system norms, the mine area is managed and controlled in a comprehensive, systematic and efficient manner. Its core purpose is to ensure the safe and smooth progress of mine production activities, effectively protect the life safety and health of miners, effectively prevent the occurrence of mine accidents, and minimize property losses and damage to the environment.

[0003] At present, mine safety management is gradually adopting digital management methods based on the Internet of Things. Through in-depth data analysis of the mining area, all-round safety supervision of the coal mine production site has been achieved.

[0004] However, the existing digital management methods are still relatively simple in terms of analytical methods, which leads to certain limitations in comprehensively identifying and assessing potential risks in mining areas. In order to further improve the effectiveness of mine safety management, it is necessary to continuously explore and innovate more diverse and accurate analytical methods and technical means. Summary of the invention

[0005] Based on this, it is necessary to provide a mining area risk determination method and device that can conduct a comprehensive analysis of mining area risks in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for determining risk in a mining area, the method comprising: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; among them, the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of that dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; Based on the temporal and spatial correlation relationships, the risk evolution level of the mining area scenario is determined.

[0007] In one embodiment, the mining area environmental data includes mining area geological data, mining area construction structure data, construction environment data and mining area climate data; the personnel construction data includes personnel behavior data, personnel fatigue data and personnel historical operation data; the equipment operation data includes equipment status data, equipment performance data and equipment maintenance records; Among them, the mining area geological data at least includes rock stability data and fault distribution data; the mining area construction structure data at least includes building structure data and support structure data.

[0008] In one embodiment, determining whether environmental dimension mining area data has security risks includes: Determine the degree of correlation between the mine area climate data and the mine area construction structure data and the mine area geological data; If any of the mining area geological data, mining area construction structure data and mining area climate data has a security risk, and the degree of correlation is greater than the preset correlation, then it is determined that the mining area data in the environmental dimension has a security risk.

[0009] In one embodiment, if the target dimension mining area data is personnel dimension mining area data, then analyzing the temporal correlation relationship and spatial correlation relationship between the target dimension mining area data and other dimension mining area data includes: Use time series analysis technology to determine the temporal correlation between the changes in mining area data in the personnel dimension and mining area data in the environment dimension; Use time series analysis technology to determine the temporal correlation between changes in personnel-dimension mining data and equipment-dimension mining data; Based on the personnel location data and the mining area location data, determine the spatial correlation between the personnel construction data and the mining area environment data; Based on the personnel location data and equipment location data, the spatial correlation relationship between the personnel construction data and the equipment operation data is determined.

[0010] In one embodiment, a time series analysis technique is used to determine the temporal correlation between changes in personnel dimension mining area data and environmental dimension mining area data, including: Using time series analysis technology, determine the environmental behavior time series relationship between mining area geological data, mining area construction structure data, construction environment data, mining area climate data and personnel behavior data; Use time series analysis technology to determine the environmental fatigue time series relationship between mining area geological data, mining area construction structure data, construction environment data, mining area climate data and personnel fatigue data; According to the behavior temporal relationship, fatigue temporal relationship and the environmental dimension mining area data at the historical moments corresponding to the erroneous operations in the historical operation data of the personnel, the temporal correlation relationship between the changes in the personnel dimension mining area data and the environmental dimension mining area data is determined.

[0011] In one embodiment, a time series analysis technique is used to determine the temporal correlation between changes in personnel dimension mining area data and equipment dimension mining area data, including: Use time series analysis technology to determine the equipment behavior time series relationship between equipment status data and personnel behavior data; Use time series analysis techniques to determine the equipment fatigue time series relationship between equipment performance data and personnel fatigue data; Use time series analysis techniques to determine the equipment historical temporal relationship between equipment maintenance records and personnel historical operation data; Use time series analysis technology to determine the equipment location time series relationship between equipment location data and personnel location data; According to the timing relationship of equipment behavior, equipment fatigue, equipment history and equipment location, the timing correlation relationship between the changes in personnel dimension mining data and equipment dimension mining data is determined.

[0012] In one embodiment, based on the personnel location data and the mine location data, determining the spatial association relationship between the personnel construction data and the mine environment data includes: Based on the personnel location data and the mine location data, under the condition of satisfying the spatial association analysis, the environmental behavior spatial relationship between the personnel behavior data and the mine construction structure data, the environmental fatigue spatial relationship between the personnel fatigue data and the construction environment data, and the climate history spatial relationship between the personnel historical operation data and the mine climate data are determined; According to the spatial relationship of environmental behavior, environmental fatigue and climate history, the spatial correlation between personnel construction data and mining area environmental data is determined.

[0013] In one embodiment, based on the personnel location data and the equipment location data, determining the spatial association relationship between the personnel construction data and the equipment operation data includes: Based on the personnel location data and equipment location data, under the conditions that satisfy the spatial association analysis, determine the equipment behavior spatial relationship between the personnel behavior data and the equipment status data, determine the equipment fatigue spatial relationship between the personnel fatigue data and the equipment performance data, and determine the equipment maintenance spatial relationship between the personnel historical operation data and the equipment maintenance records; According to the spatial relationship of equipment fatigue, historical operation data of personnel and spatial relationship of equipment maintenance, the spatial correlation relationship between personnel construction data and equipment operation data is determined.

[0014] In one embodiment, a time series analysis technique is used to determine a device behavior time series relationship between device status data and personnel behavior data, including: Determine the equipment status time series and the personnel behavior time series within the target period according to the equipment status data and personnel behavior data within the target period; Using the cross-correlation function, the time delay between the equipment status time series and the personnel behavior time series is determined; Based on the time delay, the device behavior temporal relationship between the device status data and the personnel behavior data is determined.

[0015] In a second aspect, the present application also provides a mining area risk determination device, comprising: An acquisition module is used to acquire multi-dimensional mining area data corresponding to a mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; An analysis module, for, when determining that any dimension of mining area data has a security risk, using the dimension of mining area data as target dimension of mining area data, and analyzing the temporal correlation relationship and spatial correlation relationship between the target dimension of mining area data and other dimension of mining area data; A risk determination module is used to determine the risk evolution level of the mining scene according to the temporal correlation relationship and the spatial correlation relationship. In a third aspect, the present application also provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of the dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; The risk evolution level of the mining area scenario is determined based on the temporal correlation relationship and the spatial correlation relationship.

[0016] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of the dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; The risk evolution level of the mining area scenario is determined based on the temporal correlation relationship and the spatial correlation relationship.

[0017] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of the dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; The risk evolution level of the mining area scenario is determined based on the temporal correlation relationship and the spatial correlation relationship.

[0018] The above-mentioned mining area risk determination method and device, this application realizes comprehensive data integration by acquiring mining area data in personnel dimension, environmental dimension and equipment dimension. This multi-dimensional data fusion helps to more comprehensively identify and evaluate the safety risks in mining areas, and overcomes the limitations of single-dimensional data analysis. This application reveals the laws and trends of data changes over time by analyzing the temporal correlation between mining area data of different dimensions. This helps managers to more accurately grasp the development trend of safety risks and formulate more accurate safety management strategies. Through the analysis of spatial correlation relationships, the system can identify the mutual influence and dependency of data of different dimensions in space. This helps managers to more intuitively understand the spatial distribution characteristics of safety risks and take targeted spatial management measures. Based on the analysis of temporal correlation relationships and spatial correlation relationships, this application can determine the risk evolution level of mining area scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of a process for determining a mining area risk in one embodiment; Figure 2 A schematic diagram of a process for determining the presence of security risks in mining area data in an environmental dimension in one embodiment; Figure 3 A schematic flow chart of the steps of analyzing the temporal correlation relationship and spatial correlation relationship between the target dimension mining area data and the other dimension mining area data in one embodiment; Figure 4 A flowchart of a step of determining a temporal correlation relationship between changes in personnel dimension mining area data and environment dimension mining area data in one embodiment; Figure 5 A flowchart of a step of determining a temporal correlation relationship between changes in personnel dimension mining area data and equipment dimension mining area data in one embodiment; Figure 6 It is a flowchart of the steps of determining the spatial association relationship between personnel construction data and mining area environment data in one embodiment; Figure 7 A schematic flow chart of the steps of determining the spatial association relationship between personnel construction data and equipment operation data in one embodiment; Figure 8 It is a structural block diagram of a mining area risk determination device in one embodiment. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] In an exemplary embodiment, a method for determining risk in a mining area is provided, such as Figure 1 As shown, the method includes: S101, obtaining multi-dimensional mining area data corresponding to the mining area scene.

[0023] Among them, multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data.

[0024] Specifically, when collecting multi-dimensional mining area data, it is necessary to clearly define which data in terms of personnel, environment, and equipment dimensions need to be collected, as well as the specific content and format of these data. Based on data requirements, corresponding sensors, monitoring equipment, positioning systems, etc. are deployed in the mining area to ensure that the required data can be obtained in real time or regularly.

[0025] Among them, the personnel dimension mining area data includes the personnel construction data and personnel location data of the construction personnel in the mining area scene.

[0026] Specifically, personnel construction data can be collected through monitoring cameras, smart wearable devices, etc. The personnel location data can use positioning systems (such as GPS, RFID, UWB, etc.) to track the location information of construction personnel in real time.

[0027] Among them, the mining area data of the environmental dimension includes the mining area environment data and mining area location data within the mining area scene.

[0028] Specifically, the mining area environmental data can be collected through environmental sensors to collect environmental parameters such as temperature, humidity, air pressure, gas concentration (such as gas, carbon monoxide, etc.), noise, etc. The mining area location data can use the geographic information system (GIS) to obtain spatial information such as the topography, geological structure, and mineral layer distribution of the mining area.

[0029] Among them, the equipment dimension mining area data includes the equipment operation data and equipment location data of the mining area equipment in the mining area scene.

[0030] Specifically, the equipment operation data can be collected through the equipment's own sensors or monitoring system to collect the equipment's operating status, working parameters, fault alarms and other data. The equipment location data also uses the positioning system to obtain the specific location information of the equipment in the mining area.

[0031] S102, when it is determined that there is a security risk in the mining area data of any dimension, the mining area data of the dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed.

[0032] Optionally, when it is determined that there is a security risk in the mining area data of any dimension, the preset security threshold, anomaly detection algorithm or machine learning model is used to conduct a preliminary screening of the mining area data of each dimension to identify the dimensions that may have security risks. The risk data initially screened out is reviewed, and expert experience and historical data are combined to confirm which dimensions do have security risks, and these dimensions are marked as target dimensions.

[0033] Specifically, when analyzing the temporal correlation and spatial correlation between the target dimension mining area data and other dimension mining area data, it includes: (1) Time series construction: construct time series data for the target dimension and other related dimensions, and record the changes of each dimension data over time. Time series correlation analysis: use time series analysis techniques (such as autocorrelation analysis, cross-correlation analysis, Granger causality test, etc.) to explore the temporal correlation between the target dimension data and other dimension data, and identify which factors may lead to security risks in the target dimension.

[0034] (2) Spatial data preparation: For data with spatial attributes (such as personnel location, equipment location, mining area environmental data, etc.), spatial coordinate conversion and geocoding are performed to facilitate spatial analysis. Spatial data mining techniques (such as spatial association rule mining, spatial clustering analysis, etc.) are used to explore the spatial distribution patterns and associations between target dimension data and other dimension data, and identify which areas or locations may be related to the safety risks of the target dimension.

[0035] S103, determining the risk evolution level of the mining area scenario according to the temporal correlation relationship and the spatial correlation relationship.

[0036] Specifically, based on the analysis results of temporal correlation and spatial correlation, key factors that have a significant impact on the safety risk of mining areas are identified. A weight is assigned to each risk factor based on its importance, historical data, expert experience, etc. The weight reflects the degree of influence of the factor on the risk evolution level.

[0037] According to the characteristics and needs of mine safety management, select appropriate risk assessment methods, such as fuzzy comprehensive evaluation, analytic hierarchy process (AHP), grey system theory, etc. Use the selected evaluation method, combined with risk factors and weights, to construct a risk assessment model. The model should be able to comprehensively consider the temporal and spatial correlation relationships and conduct a quantitative assessment of the safety risks of the mine area. Substitute the actual value or state of the risk factor into the risk assessment model to calculate the risk quantification value of the mine area. This value can be a continuous value, indicating the degree of risk. According to the risk quantification value, the safety risks of the mine area are divided into different levels, such as low risk, medium risk, high risk and extremely high risk. The level division should be based on actual management needs and industry standards.

[0038] In an exemplary embodiment, the mining area environmental data includes mining area geological data, mining area construction structure data, construction environment data and mining area climate data. Personnel construction data includes personnel behavior data, personnel fatigue data and personnel historical operation data. Equipment operation data includes equipment status data, equipment performance data and equipment maintenance records. Among them, mining area geological data at least includes rock formation stability data and fault distribution data. Mining area construction structure data at least includes building structure data and support structure data.

[0039] Alternatively, mining area geological data can be obtained through geological exploration, drilling, seismic monitoring, remote sensing technology (such as satellite image analysis) and on-site inspections by geological experts. Among them, rock formation stability data refers to whether the rock formation is stable and whether there are risks such as landslides and collapses, usually including the physical and mechanical properties of the rock formation, structural surface characteristics, etc. Fault distribution data refers to the location, direction, scale and activity nature of underground faults, which is crucial for assessing earthquake risks and formation stability.

[0040] Optionally, the construction structure data of the mining area can be obtained through design drawings, construction records, on-site surveys, and drone aerial photography. Among them, building structure data: including the size, material, and load-bearing capacity of building facilities such as mines, tunnels, derricks, and work platforms. Support structure data: describes the type, layout, and status of the support system (such as anchors, steel frames, grouting, etc.) used to support and stabilize the ore body, tunnels, and other structures.

[0041] Optionally, construction environment data can use environmental monitoring sensors (such as temperature and humidity sensors, gas concentration detectors), video surveillance, etc. Specifically, it includes the temperature, humidity, lighting conditions, air quality (such as gas and carbon monoxide concentrations), noise level, etc. of the construction area, which directly reflects the comfort and safety of the construction environment.

[0042] Optionally, the mining area climate data can be obtained through weather stations, weather satellites, network weather services, etc. It covers the meteorological conditions such as rainfall, wind speed, wind direction, temperature, humidity, etc. in the mining area, which is of great significance for predicting natural disasters (such as mudslides and floods) and arranging work plans.

[0043] Optionally, personnel behavior data can be collected through video surveillance, smart wearable devices (such as built-in sensors in helmets), behavior recognition algorithms, etc. to record construction workers' work behaviors, operating habits, compliance with safety regulations, etc., to assess the impact of personnel behavior on safety.

[0044] For example, in order to comprehensively evaluate the impact of personnel behavior on construction safety, a variety of technical means can be used to collect and analyze personnel behavior data. These means include but are not limited to video surveillance, smart wearable devices (such as helmets with built-in sensors), and advanced behavior recognition algorithms.

[0045] Taking the human trajectory recognition algorithm as an example, its working principle is as follows: First, extract key information from the continuous video frames captured by the camera. Then, using an efficient target detection algorithm, the location information of the target to be tracked (such as construction workers) can be accurately obtained. Subsequently, through an intelligent tracking algorithm, the system can determine whether the target is a known target and check whether its existing trajectory is still active. For known and active targets, the system will update its motion trajectory in real time; for newly appearing targets, a new tracking trajectory will be established for them; and for target trajectories that have not moved for a long time, the system will remove them to maintain data accuracy and real-time performance.

[0046] The core of the object detection algorithm consists of three key layers: the skeleton layer, the bottleneck layer, and the output layer. In the skeleton layer, the algorithm aggregates features at different image granularities to build a convolutional neural network that can capture features at all levels of the image. These features provide a solid foundation for subsequent image analysis. Next, in the bottleneck layer, the algorithm compresses the image information, retains the most representative feature channels, and passes these features to the prediction layer (such as FPN or PANET). Finally, in the output layer, the algorithm deeply analyzes and predicts the image features, generates accurate bounding boxes, and predicts the category of the target. In order to optimize the prediction effect, the cross entropy loss function (BCEclsloss) is used to calculate the category probability, and GIOU Loss is used as the metric for the bounding box loss. Throughout the image recognition process, the algorithm performs a series of complex processing operations on the input image, including convolution, pooling, and activation, to extract the most effective features. These features are then input into the fully connected layer, and the category information of the image is finally output through the calculation of the fully connected layer. Optionally, personnel fatigue data can be collected through physiological monitoring equipment (such as heart rate monitors, electroencephalographs), questionnaires, work time records, etc. to reflect the physical and mental fatigue of construction workers and help identify potential fatigue operation risks.

[0047] Optionally, personnel historical operation data can be extracted from files such as employee training records, operation records, and accident records. Specifically, it includes the construction personnel's past operation experience, skill level, accident records, etc., which are used to evaluate their operation capabilities and safety awareness.

[0048] Optionally, the equipment status data can reflect the working status of the equipment in real time, such as operating status (running / stopping), operating parameters (such as pressure, temperature, speed), fault indication, etc., through built-in sensors, monitoring systems, regular inspections, etc.

[0049] Optionally, equipment performance data can be performance tests, regular maintenance checks, technical specifications provided by the manufacturer, etc. Specifically describe the performance indicators of the equipment, such as efficiency, accuracy, durability, energy consumption, etc., to evaluate whether the equipment meets the operating requirements.

[0050] Optionally, equipment maintenance records can be obtained through maintenance logs, repair records, maintenance plans and other documents. Recording the maintenance history of equipment, including maintenance time, maintenance content, replaced parts, maintenance personnel and other information, helps predict equipment failures and arrange maintenance plans.

[0051] In an exemplary embodiment, Figure 2 As shown in the figure, it is determined that there are security risks in mining area data in environmental dimensions, including: S201, determining the degree of correlation between the mining area climate data and the mining area construction structure data and the mining area geological data.

[0052] Specifically, statistical methods (such as correlation coefficient analysis and regression analysis) are used to quantify the correlation between climate data (such as rainfall, temperature, wind speed, etc.) and construction structure data (such as building structure stability, support structure status, etc.) and geological data (such as rock formation stability, fault activity, etc.). Machine learning models (such as neural networks, decision trees, etc.) are trained to identify the complex relationship between climate data and the other two types of data. The model can learn these relationships based on historical data and output a correlation index.

[0053] S202: If any one of the mining area geological data, mining area construction structure data and mining area climate data has a security risk and the degree of correlation is greater than the preset correlation, it is determined that the mining area data of the environmental dimension has a security risk.

[0054] Optionally, it is necessary to evaluate whether there are security risks in the mining area geological data, mining area construction structure data and mining area climate data respectively. This can be achieved by setting a security threshold, using anomaly detection algorithms or combining expert experience. Next, check whether the self-association degree calculated in step S201 is greater than a preset association threshold. This threshold is set according to actual conditions and safety management requirements, and is used to determine whether the association between climate data and other data is strong enough so that when one of the data has a security risk, it will affect or aggravate the security risk of other data.

[0055] If one of the following conditions is met, it is determined that the mining area data in the environmental dimension has a security risk: the mining area geological data has a security risk, and the correlation between the climate data and the geological data is greater than the preset correlation. The mining area construction structure data has a security risk, and the correlation between the climate data and the construction structure data is greater than the preset correlation. The mining area climate data itself has a security risk (such as extreme weather events), and the degree of correlation between this climate condition and other data indicates that it may pose a threat to the safety of the mining area.

[0056] In an exemplary embodiment, Figure 3 As shown, if the target dimension mining area data is the personnel dimension mining area data, the temporal correlation relationship and spatial correlation relationship between the target dimension mining area data and the mining area data of other dimensions are analyzed, including: S301, using time series analysis technology to determine the temporal correlation between changes in mining area data of personnel dimension and mining area data of environment dimension.

[0057] Understandably, the goal of this step is to identify and analyze how changes in personnel behavior, status, or performance over time are associated with changes in environmental conditions (such as climate, geological conditions). Time series analysis techniques such as autoregressive models (AR), moving average models (MA), autoregressive moving average models (ARMA), or more complex autoregressive integrated moving average models (ARIMA) can be used for this purpose. Through analysis, it can be revealed, for example, how personnel fatigue changes with changes in temperature or humidity, or how personnel operational error rates are associated with specific weather patterns.

[0058] S302, using time series analysis technology to determine the temporal correlation between changes in personnel dimension mining area data and equipment dimension mining area data.

[0059] Understandably, this step aims to explore the temporal dependencies between human behavior or status and equipment performance, status, or maintenance history. Using the same time series analysis techniques, it is possible to analyze, for example, how equipment failure rates affect human productivity or safety behavior, or how human operating patterns lead to premature wear of equipment.

[0060] S303: Determine the spatial correlation between the personnel construction data and the mining area environment data based on the personnel location data and the mining area location data.

[0061] Understandably, this step involves combining the location information of personnel with the geographic or spatial characteristics of the mining area to analyze how personnel activities are affected by environmental conditions. For example, through geographic information systems (GIS) or spatial analysis tools, it is possible to identify the frequency of personnel activities in high-risk geological areas, or to assess the distribution and efficiency of personnel in different mining areas under different climate conditions.

[0062] S304: Determine the spatial correlation between the personnel construction data and the equipment operation data based on the personnel location data and the equipment location data.

[0063] Understandably, this step focuses on the spatial interaction between people and equipment. By analyzing the location data of people and equipment, we can understand how people interact with equipment, for example, identifying areas where people frequently approach or operate specific equipment, or analyzing the location and reaction of people when equipment fails. This helps to evaluate the synergy between people and equipment, as well as optimize equipment layout and personnel scheduling to improve safety and efficiency.

[0064] In one possible implementation, Figure 4 As shown, S301 uses time series analysis technology to determine the temporal correlation between changes in personnel dimension mining area data and environmental dimension mining area data, including: S401, using time series analysis technology to determine the environmental behavior time series relationship between mining area geological data, mining area construction structure data, construction environment data, mining area climate data and personnel behavior data.

[0065] Understandably, the goal of this step is to analyze how environmental dimension mining data (including geology, construction structure, construction environment, and climate data) influence or trigger changes in personnel behavior. Through time series analysis techniques, the temporal sequence and correlation between specific environmental conditions (such as geological instability, rising temperatures, increased humidity, etc.) and personnel behavior (such as decreased operating efficiency, increased illegal operations, etc.) can be identified. This analysis helps to understand how environmental factors shape personnel behavior patterns and provides a basis for predicting and preventing unsafe behaviors caused by environmental factors.

[0066] S402, using time series analysis technology to determine the environmental fatigue time series relationship between the mining area geological data, mining area construction structure data, construction environment data and mining area climate data and personnel fatigue data.

[0067] Understandably, this step focuses on analyzing how environmental dimension mining data affects the fatigue status of personnel. Fatigue is a common safety issue in mining operations, which may be caused by a variety of environmental factors, such as working in high temperature or high humidity environments for a long time, and performing high-intensity operations in geologically unstable areas. Through time series analysis, the temporal correlation between environmental factors and personnel fatigue can be revealed, thereby helping to identify high-risk environmental conditions and time periods that cause fatigue, and providing a basis for the reasonable arrangement of working time and rest systems.

[0068] S403, determining the temporal correlation between changes in the personnel dimension mining area data and the environmental dimension mining area data according to the behavior temporal relationship, fatigue temporal relationship and the environmental dimension mining area data at the historical moments corresponding to the erroneous operations in the personnel historical operation data.

[0069] It is understandable that this step is to comprehensively determine the temporal correlation between the personnel dimension mining area data and the environmental dimension mining area data by combining the analysis results of the previous two steps and the error operation records in the personnel historical operation data. By comparing the personnel behavior, fatigue status and error operation under different environmental conditions, we can have a deeper understanding of how environmental factors affect the performance and safety of personnel. This comprehensive analysis helps to identify key environmental factors and safety risk points, and provide a scientific basis for the formulation of targeted safety management measures and emergency plans.

[0070] In one possible implementation, Figure 5 As shown, S302 uses time series analysis technology to determine the temporal correlation between changes in personnel dimension mining area data and equipment dimension mining area data, including: S501, using time series analysis technology to determine the device behavior time series relationship between device status data and personnel behavior data.

[0071] Optionally, a time series analysis technique is used to determine the device behavior time series relationship between the device state data and the personnel behavior data, including: determining the device state time series and the personnel behavior time series within the target time period based on the device state data and the personnel behavior data within the target time period. Using a cross-correlation function, a time delay between the device state time series and the personnel behavior time series is determined. Based on the time delay, the device behavior time series relationship between the device state data and the personnel behavior data is determined.

[0072] Exemplarily, the device status data within the target time period is collected, which is recorded as D(t), where t represents time, and the personnel behavior data within the corresponding time period is collected, which is recorded as B(t).

[0073] Preprocess the equipment status data D(t) and personnel behavior data B(t), such as removing outliers, filling missing values, etc. Construct equipment status time series {D1, D2, …, Dn} and personnel behavior time series {B1, B2, …, Bn}, where n is the number of time points.

[0074] The cross-correlation function (CCF) is used to measure the similarity and time delay between two time series. For the equipment status time series {Dt} and the personnel behavior time series {Bt}, their cross-correlation function ρDB(l) is calculated, where l represents the time delay (which can be positive or negative).

[0075] The calculation formula of the cross-correlation function is: ρDB(l)=∑t=1n(Dt−Dˉ)2∑t=1n(Bt−Bˉ)2 ∑t=1n−l(Dt−Dˉ)(Bt+l−Bˉ) Find the maximum or minimum value of the cross-correlation function ρDB(l). The l value corresponding to the maximum or minimum value is the time delay between the device state and the human behavior. Based on the time delay l, the timing relationship between the device state data and the human behavior data can be determined. If l>0, it means that the change in device state precedes the change in human behavior; if l<0, it means that the change in human behavior precedes the change in device state; if l=0, it means that both change at the same time. Based on the size of the time delay and the value of the cross-correlation function, we can further analyze how the device state affects human behavior, or how human behavior responds to changes in device state.

[0076] S502, using time series analysis technology to determine the equipment fatigue time series relationship between equipment performance data and personnel fatigue data.

[0077] Understandably, this step focuses on analyzing how equipment performance affects personnel fatigue. Similar to S501, it is also necessary to collect equipment performance data and personnel fatigue data, construct time series, and perform cross-correlation analysis to determine the temporal relationship between them.

[0078] S503, using time series analysis technology to determine the equipment historical time series relationship between the equipment maintenance record and the personnel historical operation data.

[0079] It can be understood that this step aims to analyze how the equipment maintenance history is related to the personnel operation behavior. By comparing the equipment maintenance records and the personnel historical operation data, the change pattern of the personnel operation behavior after the equipment maintenance can be identified.

[0080] S504, using time series analysis technology to determine the device location time series relationship between the device location data and the personnel location data.

[0081] Understandably, this step focuses on how the relative positions of equipment and personnel in space change over time, and analyzes the impact of such changes on personnel behavior and equipment operation. By collecting equipment location data and personnel location data and performing time series analysis, the spatial temporal relationship between them can be revealed.

[0082] S505, determining the temporal correlation relationship between changes in personnel dimension mining area data and equipment dimension mining area data according to the equipment behavior temporal relationship, equipment fatigue temporal relationship, equipment history temporal relationship and equipment position temporal relationship.

[0083] Optionally, use data fusion technology to integrate information from different data sources to obtain a more comprehensive perspective. Through comprehensive analysis, determine the temporal correlation between personnel dimension mining area data and equipment dimension mining area data. These correlations may include how equipment behavior affects personnel operation, how equipment fatigue affects personnel work efficiency, and how equipment historical performance affects personnel decision-making.

[0084] In one possible implementation, Figure 6 As shown, S303 determines the spatial association relationship between the personnel construction data and the mining area environment data based on the personnel location data and the mining area location data, including: S601, based on the personnel location data and the mine location data, determine the environmental behavior spatial relationship between the personnel behavior data and the mine construction structure data, determine the environmental fatigue spatial relationship between the personnel fatigue data and the construction environment data, and determine the climate history spatial relationship between the personnel historical operation data and the mine climate data under the conditions that meet the spatial correlation analysis.

[0085] It can be understood that the spatial relationship of environmental behavior refers to the comparison of personnel behavior data (such as operating efficiency, illegal operation, etc.) with mining construction structure data (such as tunnel layout, working face location, etc.), which can reveal how the construction structure affects personnel behavior. For example, some complex tunnel structures may cause personnel to get lost or reduce operating efficiency.

[0086] Environmental fatigue spatial relationship refers to combining personnel fatigue data with construction environment data (such as temperature, humidity, noise, etc.) to analyze how environmental factors cause personnel fatigue. For example, a high temperature and high humidity environment may accelerate the physical consumption of personnel and increase fatigue.

[0087] Climate history spatial relationship means that by comparing personnel historical operation data with mining area climate data (such as temperature, rainfall, etc.), it is possible to identify how climate conditions affect personnel historical operation performance. For example, extreme weather conditions may lead to an increase in personnel operation error rate.

[0088] S602, determining the spatial correlation relationship between personnel construction data and mining area environmental data according to the environmental behavior spatial relationship, environmental fatigue spatial relationship and climate history spatial relationship.

[0089] Optionally, assign weights to each spatial relationship based on their importance or impact. These weights can be determined through expert evaluation, historical data analysis, or machine learning algorithms. Use a geographic information system (GIS) or similar spatial analysis tool to overlay the weighted spatial relationship data. This may include operations such as spatial interpolation, raster overlay, buffer analysis, etc. to reveal the interactions and overlay effects between different spatial relationships. Apply association rule mining algorithms (such as Apriori algorithm, FP-Growth algorithm, etc.) to discover association rules between personnel construction data and mining environment data. These rules can be expressed in the form of "if...then...", such as "if the temperature in a certain area exceeds 30 degrees Celsius, then the fatigue of personnel in that area will increase."

[0090] Use spatial clustering algorithms (such as K-means clustering, DBSCAN clustering, etc.) to identify spatially similar or related areas or patterns. These clusters can reveal the spatial distribution characteristics and association patterns between personnel construction data and mining environment data. Based on the results of association rule mining and spatial clustering analysis, construct a comprehensive spatial association relationship between personnel construction data and mining environment data. This may include identifying key influencing factors, determining the direction and strength of association, and drawing spatial association relationship diagrams.

[0091] In one possible implementation, Figure 7 As shown, S304 determines the spatial association relationship between the personnel construction data and the equipment operation data based on the personnel location data and the equipment location data, including: S701, based on the personnel location data and the equipment location data, determine the equipment behavior spatial relationship between the personnel behavior data and the equipment status data, determine the equipment fatigue spatial relationship between the personnel fatigue data and the equipment performance data, and determine the equipment maintenance spatial relationship between the personnel historical operation data and the equipment maintenance records under the conditions that satisfy the spatial association analysis.

[0092] It is understandable that determining whether the conditions for spatial association analysis are met based on the personnel location data and the device location data means judging whether the personnel location data and the device location data meet the conditions for spatial association analysis based on the personnel location data and the device location data. This usually involves checking the integrity and accuracy of the data and whether the spatial distances between them are close enough to be considered to be spatially associated.

[0093] It can be understood that the spatial relationship of equipment behavior refers to combining personnel behavior data and equipment status data to analyze the spatial relationship between personnel behavior (such as operation mode, movement path, etc.) and equipment status (such as operating status, fault conditions, etc.). This may involve the use of spatial analysis techniques, such as spatial overlay analysis and buffer analysis in geographic information systems (GIS), to identify the spatial interaction between personnel behavior and equipment status.

[0094] It can be understood that the spatial relationship of equipment fatigue refers to the use of personnel fatigue data and equipment performance data to analyze the spatial relationship between personnel fatigue and equipment performance degradation. This may include comparing the fatigue level of personnel and the performance of equipment at different spatial locations, as well as their mutual influence.

[0095] It can be understood that the spatial relationship of equipment maintenance refers to combining historical operation data of personnel and equipment maintenance records to analyze the spatial relationship between personnel operation habits, skill levels and equipment maintenance needs and maintenance history. This may involve the use of data mining technology to discover hidden patterns or associations between personnel operations and equipment maintenance.

[0096] S702, determining the spatial correlation relationship between personnel construction data and equipment operation data according to the equipment fatigue spatial relationship, personnel historical operation data and equipment maintenance spatial relationship.

[0097] Optionally, the equipment behavior spatial relationship, equipment fatigue spatial relationship and equipment maintenance spatial relationship determined in S701 are comprehensively analyzed, which may involve using multivariate analysis, cluster analysis or association rule mining techniques to reveal the interactions and dependencies between these spatial relationships.

[0098] Based on the results of comprehensive spatial relationship analysis, a spatial correlation model between personnel construction data and equipment operation data is constructed. This model should be able to reflect the spatial correlation and mutual influence between personnel behavior, fatigue, historical operation and equipment status, performance, and maintenance records.

[0099] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0100] Based on the same inventive concept, the embodiment of the present application also provides a mining area risk determination device for implementing the mining area risk determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more mining area risk determination device embodiments provided below can refer to the limitations of the mining area risk determination method above, and will not be repeated here.

[0101] In an exemplary embodiment, Figure 8 As shown, a mining area risk determination device is provided, the device comprising: The acquisition module 11 is used to acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; The analysis module 12 is used to use the mining area data of any dimension as the target mining area data when it is determined that there is a security risk in the mining area data of any dimension, and analyze the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions; The risk determination module 13 is used to determine the risk evolution level of the mining area scenario based on the temporal correlation relationship and the spatial correlation relationship. Each module in the above-mentioned mining area risk determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0102] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; among them, the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of that dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; Based on the temporal and spatial correlation relationships, the risk evolution level of the mining area scenario is determined.

[0103] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; among them, the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of that dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; Based on the temporal and spatial correlation relationships, the risk evolution level of the mining area scenario is determined.

[0104] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; among them, the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of that dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; Based on the temporal and spatial correlation relationships, the risk evolution level of the mining area scenario is determined.

[0105] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0106] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0107] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining mining area risk, characterized in that: The method comprises: Acquire multi-dimensional mining area data corresponding to the mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; When it is determined that there is a security risk in the mining area data of any dimension, the mining area data of the dimension is used as the mining area data of the target dimension, and the temporal correlation relationship and spatial correlation relationship between the mining area data of the target dimension and the mining area data of other dimensions are analyzed; The risk evolution level of the mining area scenario is determined based on the temporal correlation relationship and the spatial correlation relationship.

2. The method according to claim 1, characterized in that: The mining area environmental data includes mining area geological data, mining area construction structure data, construction environment data and mining area climate data; the personnel construction data includes personnel behavior data, personnel fatigue data and personnel historical operation data; the equipment operation data includes equipment status data, equipment performance data and equipment maintenance records; The mining area geological data at least includes rock layer stability data and fault distribution data; the mining area construction structure data at least includes building structure data and support structure data.

3. The method according to claim 2, characterized in that Identify security risks in mining data in environmental dimensions, including: Determining the degree of self-correlation between the mining area climate data and the mining area construction structure data and the mining area geological data; If any one of the mining area geological data, mining area construction structure data and mining area climate data has a security risk, and the degree of self-correlation is greater than the preset correlation, it is determined that the mining area data in the environmental dimension has a security risk.

4. The method according to claim 2, characterized in that: If the target dimension mining area data is the personnel dimension mining area data, then analyzing the temporal correlation relationship and spatial correlation relationship between the target dimension mining area data and other dimension mining area data includes: Using time series analysis technology, determine the temporal correlation between the changes in the personnel dimension mining area data and the environmental dimension mining area data; Using time series analysis technology, determine the temporal correlation between changes in the personnel dimension mining area data and the equipment dimension mining area data; Based on the personnel location data and the mining area location data, determining a spatial correlation relationship between the personnel construction data and the mining area environment data; Based on the personnel location data and the equipment location data, a spatial association relationship between the personnel construction data and the equipment operation data is determined.

5. The method according to claim 4, characterized in that The time series analysis technology is used to determine the time series correlation relationship between the changes in the personnel dimension mining area data and the environment dimension mining area data, including: Using time series analysis technology, determine the environmental behavior time series relationship between the mining area geological data, mining area construction structure data, construction environment data and mining area climate data and the personnel behavior data; Using time series analysis technology, determine the environmental fatigue time series relationship between the mining area geological data, mining area construction structure data, construction environment data and mining area climate data and the personnel fatigue data; According to the behavior time series relationship, the fatigue time series relationship and the environmental dimension mining area data of the historical moments corresponding to the erroneous operations in the personnel historical operation data, the time series correlation relationship between the changes in the personnel dimension mining area data and the environmental dimension mining area data is determined.

6. The method according to claim 4, characterized in that The time series analysis technology is used to determine the time series correlation relationship between the changes in the personnel dimension mining area data and the equipment dimension mining area data, including: Using time series analysis technology to determine the device behavior time series relationship between the device status data and the personnel behavior data; Using time series analysis technology to determine the equipment fatigue time series relationship between the equipment performance data and the personnel fatigue data; Using time series analysis technology to determine the equipment historical time series relationship between the equipment maintenance record and the personnel historical operation data; Using time series analysis technology to determine the device location time series relationship between the device location data and the personnel location data; According to the equipment behavior timing relationship, equipment fatigue timing relationship, equipment history timing relationship and equipment position timing relationship, the timing correlation relationship between the changes in the personnel dimension mining area data and the equipment dimension mining area data is determined.

7. The method according to claim 4, characterized in that The determining, based on the personnel location data and the mining area location data, the spatial association relationship between the personnel construction data and the mining area environment data comprises: Based on the personnel location data and the mining area location data, under the condition that the spatial association analysis is satisfied, the environmental behavior spatial relationship between the personnel behavior data and the mining area construction structure data, the environmental fatigue spatial relationship between the personnel fatigue data and the construction environment data, and the climate history spatial relationship between the personnel historical operation data and the mining area climate data are determined; The spatial correlation relationship between the personnel construction data and the mining area environmental data is determined based on the environmental behavior spatial relationship, the environmental fatigue spatial relationship and the climate history spatial relationship.

8. The method according to claim 4, characterized in that The determining, based on the personnel location data and the equipment location data, a spatial association relationship between the personnel construction data and the equipment operation data includes: Based on the personnel location data and the equipment location data, under the condition that the spatial association analysis is satisfied, determine the equipment behavior spatial relationship between the personnel behavior data and the equipment status data, determine the equipment fatigue spatial relationship between the personnel fatigue data and the equipment performance data, and determine the equipment maintenance spatial relationship between the personnel historical operation data and the equipment maintenance record; The spatial association relationship between the personnel construction data and the equipment operation data is determined based on the equipment fatigue spatial relationship, the personnel historical operation data and the equipment maintenance spatial relationship.

9. The method according to any one of claims 6 to 8, characterized in that: The adopting of time series analysis technology to determine the device behavior time series relationship between the device status data and the personnel behavior data includes: Determine the device status time series and the personnel behavior time series within the target time period according to the device status data and the personnel behavior data within the target time period; Using a cross-correlation function, determining the time delay between the device state time series and the personnel behavior time series; Based on the time delay, a device behavior temporal relationship between the device status data and the personnel behavior data is determined.

10. A mining area risk determination device, characterized in that: The device comprises: An acquisition module is used to acquire multi-dimensional mining area data corresponding to a mining area scene; the multi-dimensional mining area data includes personnel dimension mining area data, environment dimension mining area data and equipment dimension mining area data; wherein the personnel dimension mining area data includes personnel construction data and personnel location data of construction personnel in the mining area scene, the environment dimension mining area data includes mining area environment data and mining area location data in the mining area scene, and the equipment dimension mining area data includes equipment operation data and equipment location data of mining area equipment in the mining area scene; An analysis module, for, when determining that any dimension of mining area data has a security risk, using the dimension of mining area data as target dimension of mining area data, and analyzing the temporal correlation relationship and spatial correlation relationship between the target dimension of mining area data and other dimension of mining area data; The risk determination module is used to determine the risk evolution level of the mining area scenario based on the temporal correlation relationship and the spatial correlation relationship.

Images