Data risk analysis method and system based on internet of things

Abstract

The application discloses a data risk analysis method based on Internet of Things, and relates to the field of risk analysis, which comprises the following steps: acquiring laser radar point cloud data of a target mining area; collecting sensor information of the target mining area by using multiple types of sensors; constructing a mining area three-dimensional model of the target mining area by using the laser radar point cloud data, and acquiring slope crack information of the target mining area; generating a crack monitoring point distribution strategy of the target mining area in combination with the mining area three-dimensional model and the slope crack information; deploying a displacement sensor according to the crack monitoring point distribution strategy, and monitoring local displacement information of the slope crack by using the displacement sensor; constructing a slope risk prediction model, and acquiring slope risk information of the target mining area by using the slope risk prediction model; and visually displaying the slope risk information through a mining area digital twin model. The application can effectively realize all-around accurate monitoring of a slope area of the target mining area.

Description

Technical Field

[0001] This application relates to the field of data analysis, and in particular to a data risk analysis method and system based on the Internet of Things. Background Technology

[0002] With the accelerating pace of industrialization in modern society, the demand for minerals, as a crucial guarantee for modernization, is increasing daily. However, various safety hazards often accompany mineral extraction, such as gas explosions and mine collapses. Mine collapses are among the most frequent accidents in mines, and one of the most vulnerable areas is the mine slope. Factors leading to collapses include, but are not limited to, slope cracks, unstable rock structures, and improper mining techniques. Once a collapse occurs, it can lead to serious safety incidents, threatening the personal safety of mine workers. Therefore, it is necessary to conduct risk analysis on mine slopes and identify potential safety hazards.

[0003] Traditional risk monitoring methods are relatively simple, mainly relying on manual inspections and various types of sensors installed in the mining area. However, manual inspections are easily affected by subjective factors and cannot provide 24-hour uninterrupted risk monitoring. In addition, for large mining areas, the slope areas are also large, and manual inspections and various types of sensors cannot provide comprehensive monitoring of the slope areas. Therefore, it is impossible to conduct a comprehensive risk assessment of the slope areas. As a result, the failure to detect potential collapse hazards in time can lead to slope collapse accidents, threatening the lives of miners. Therefore, how to achieve comprehensive and high-precision risk monitoring of mining slope areas is a major challenge facing the mining industry. Summary of the Invention

[0004] This application provides a data risk analysis method based on the Internet of Things, which is used to solve the problem that existing technologies cannot achieve high-precision risk monitoring of all-round slope areas in mining areas.

[0005] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0006] Firstly, a data risk analysis method based on the Internet of Things is provided, which includes:

[0007] Acquire lidar point cloud data collected by drones in the target mining area;

[0008] Sensor information of the target mining area is collected based on multiple types of sensors preset in the target mining area, including stress sensors and groundwater level sensors;

[0009] A three-dimensional model of the target mining area is constructed using the lidar point cloud data. Based on the three-dimensional model of the mining area, the slope crack information of the target mining area is calculated using the point cloud computing method.

[0010] A distribution strategy for crack monitoring points in the slope area of ​​the target mining area is generated by combining the three-dimensional model of the mining area and the slope crack information.

[0011] According to the monitoring point distribution strategy, multiple displacement sensors are deployed in the target mining area. The displacement sensors are used to monitor the local displacement of all the slope cracks in the slope area to obtain local displacement information.

[0012] Based on the sensor information, the slope crack information, and the local displacement information, a slope risk prediction model is constructed, and the slope risk prediction model is used to perform slope risk analysis on the slope area to obtain the slope risk information of the target mining area.

[0013] A digital twin model of the target mining area is constructed by combining the three-dimensional model of the mining area and the slope risk prediction model, and the slope risk information is visualized through the digital twin model of the mining area.

[0014] Optionally, the step of constructing a three-dimensional model of the target mining area using the lidar point cloud data, and calculating the slope crack information of the target mining area based on the three-dimensional model and using the point cloud computing method, includes the following steps:

[0015] The lidar point cloud data of each target area in the target mining area are preprocessed, and the target area includes slope areas;

[0016] The preprocessed lidar point cloud data is fitted with a surface to obtain multiple fitted surfaces, and the three-dimensional model of the target mining area is constructed by combining the multiple fitted surfaces. The fitted surfaces include the slope fitted surfaces corresponding to the slope area.

[0017] Calculate the residual values ​​between all slope point clouds belonging to the slope region in the lidar point cloud data and the slope fitting surface, and integrate all slope point clouds whose residual values ​​are greater than a preset first residual threshold into multiple suspected crack point cloud regions.

[0018] For each suspected crack point cloud region, calculate the angle between the normal vectors of each slope point cloud and the neighboring point cloud in the suspected crack point cloud region, where the neighboring point cloud is all point clouds within a preset neighborhood around the slope point cloud.

[0019] If the included angle of the normal vector is greater than a preset included angle threshold and the residual value is less than a preset second residual threshold, then the corresponding slope point cloud is taken as the region edge point cloud of the suspected crack point cloud region, and the second residual threshold is less than the first residual threshold.

[0020] The average curvature of the point cloud at the edge of all the aforementioned regions is calculated using the curvature calculation formula.

[0021] If the average curvature is positive curvature, then the suspected crack point cloud region is taken as the initial crack point cloud region.

[0022] The non-crack point cloud regions in the initial crack point cloud region are screened out using a region growing algorithm to obtain the target crack point cloud region.

[0023] Based on the three-dimensional model of the mining area, the crack point cloud in the target crack point cloud area is mapped in multiple directions in two dimensions to obtain the two-dimensional point cloud coordinates of the crack point cloud in different directions. Based on the two-dimensional point cloud coordinates, the slope crack information of the target mining area is calculated.

[0024] Optionally, the step of using a region growing algorithm to filter out non-crack point clouds in the initial crack point cloud region to obtain the target crack point cloud region includes the following steps:

[0025] The curvature of the initial crack point cloud is estimated by calculating the angle between the normal vectors of all initial crack point clouds in the initial crack point cloud region, and the principal curvature of all the initial crack point clouds is obtained.

[0026] Construct an empty seed point sequence and a non-crack region point set, and add the initial crack point cloud with the smallest principal curvature as the seed point for the curvature region growth algorithm to the seed point sequence;

[0027] Based on a preset neighborhood order and using the K-neighborhood algorithm, multiple seed neighbors of the seed point are identified, and the normal angle between the seed point and each of the seed neighbors is calculated respectively.

[0028] If all the included angles of the normals are greater than the included angle threshold, then the region growth is considered complete.

[0029] If any one or more of the normal angles are less than a preset normal angle threshold, then the corresponding seed neighborhood point is added to the non-crack region point set.

[0030] Calculate the curvature value of each of the seed neighborhood points in the non-crack region point set;

[0031] If any one or more of the curvature values ​​are less than a preset curvature value threshold, the corresponding seed neighborhood point is added to the seed point sequence as a new seed point for region growth, and the original seed points in the seed point sequence are removed.

[0032] If all the curvature values ​​are greater than the curvature value threshold or the seed point sequence is an empty set, then the region growth is determined to be complete.

[0033] If the region growth is completed, the non-crack region point set is removed from the initial crack point cloud region to obtain the target crack point cloud region.

[0034] Optionally, the step of performing multi-directional two-dimensional mapping of the crack point cloud within the target crack point cloud area based on the three-dimensional model of the mining area to obtain the two-dimensional point cloud coordinates of the crack point cloud in different directions, and calculating the slope crack information of the target mining area based on the two-dimensional point cloud coordinates, includes the following steps:

[0035] For each target fracture point cloud region, obtain the point cloud three-dimensional coordinate set of all fracture point clouds in the target fracture point cloud region according to the three-dimensional model of the mining area;

[0036] Based on the three-dimensional coordinate set of the point cloud, all the crack point clouds in the target crack point cloud region are mapped in two dimensions in three mapping directions: x-axis-y-axis plane, y-axis-z-axis plane, and x-axis-z-axis plane, to obtain two-dimensional point clouds in the three mapping directions;

[0037] Based on the coordinates of the two-dimensional point clouds in the three mapping directions, the crack width, crack length, and crack depth of the local cracks in the slope corresponding to the target crack point cloud region are calculated.

[0038] The location of the local crack in the slope corresponding to the target crack point cloud region is calculated using the three-dimensional coordinate set of the point cloud.

[0039] The crack width, crack length, crack depth, and crack location of all the target crack point cloud regions corresponding to the local cracks on the slope are integrated into the slope crack information of the target mining area.

[0040] Optionally, the step of constructing a slope risk prediction model based on the sensor information, the slope crack information, and the local displacement information, and using the slope risk prediction model to perform slope risk analysis on the slope area to obtain the slope risk information of the target mining area includes the following steps:

[0041] Obtain the blasting information of the target mining area according to the preset mining plan;

[0042] Based on the blasting information and local displacement information of the mining area, the slope crack information is analyzed for change trends to obtain crack prediction information of the target mining area in the future time period;

[0043] Based on the crack location information and the three-dimensional model of the mining area, and using the threshold method to analyze the stress distribution of the rock mass stress information collected by the stress sensor, the stress distribution information of the target mining area is obtained.

[0044] The groundwater prediction information for the target mining area is estimated based on the precipitation information for the future time period obtained in advance and the groundwater information collected by the groundwater level sensor.

[0045] Based on the crack prediction information and the groundwater prediction information, and using the threshold method to analyze the seepage rate level of the target mining area, the slope seepage information of the target mining area is obtained.

[0046] Based on the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information, a slope risk prediction model for the target mining area is constructed, and the slope risk information of the target mining area is predicted based on the slope risk prediction model.

[0047] Optionally, the step of analyzing the trend of slope crack information based on the blasting information and local displacement information in the mining area to obtain crack prediction information for the target mining area in the future time period includes the following steps:

[0048] The blasting influence radius of the target mining area is calculated based on the blasting information of the mining area. The degree of blasting influence on the slope crack is assessed based on the blasting influence radius. The assessment result of the degree of blasting influence is used as the first influence factor.

[0049] The displacement impact degree of all slope cracks is assessed based on the local displacement information and the pre-constructed displacement crack digital model, and the displacement impact degree assessment result is used as the second impact factor.

[0050] The grey relational analysis model is used to analyze the degree of influence of the first influence factor and the second influence factor on the slope cracks, and weights are assigned to the first influence factor and the second influence factor according to the degree of influence.

[0051] The least squares method is used to perform linear regression analysis on all the first and second influencing factors after weight allocation and the fracture information of the mining area, and a fracture prediction model is constructed based on the results of the linear regression analysis.

[0052] Based on the crack prediction model, crack changes are predicted for the slope cracks to obtain crack prediction information for all slope cracks in the target mining area in the future time period.

[0053] Optionally, the step of constructing a slope risk prediction model for the target mining area based on the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information, and predicting the slope risk information of the target mining area based on the slope risk prediction model, includes the following steps:

[0054] Based on the pre-acquired slope risk assessment index, the degree of direct influence is assigned to the local displacement information, the stress distribution information, the slope seepage information and the crack prediction information using the scaling method.

[0055] The local displacement information, stress distribution information, slope seepage information, and crack prediction information are used as the core influencing factors of the slope in the target mining area. Based on the assignment of the degree of direct influence, a slope direct influence matrix of the core influencing factors is constructed. The slope direct influence matrix is ​​S = [s...]. ij ] 4×4 , where s ij This indicates the degree of influence of the core slope influencing factor i on the core slope influencing factor j;

[0056] The slope direct influence matrix is ​​normalized to obtain a standardized matrix;

[0057] Based on the standardized matrix, a series of decreasing matrix sequences are generated as the slope indirect influence matrix;

[0058] A comprehensive slope influence matrix is ​​established by combining the direct slope influence matrix and all the indirect slope influence matrices.

[0059] The influence degree and the degree of being influenced by the core influencing factors of the slope are calculated based on the comprehensive influence matrix of the slope, and the centrality and causality of the core influencing factors of the slope are calculated based on the influence degree and the degree of being influenced.

[0060] A slope risk prediction model is established by combining the centrality and causality and based on the coupling coordination function. The slope risk information of the target mining area is obtained according to the slope risk prediction model.

[0061] Optionally, the step of combining the centrality and the causality and establishing a slope risk prediction model based on the coupling coordination function, and obtaining the slope risk information of the target mining area according to the slope risk prediction model, includes the following steps:

[0062] The weights of the core influencing factors of the slope are obtained by assigning weights to the centrality corresponding to the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information.

[0063] A four-quadrant diagram is constructed based on the centrality and causality of the core influencing factors of the slope, and the core influencing factors of the slope are divided into causal factors and outcome factors based on the four-quadrant diagram.

[0064] A slope risk prediction model is established based on the weights and coupling coordination function corresponding to the core influencing factors of the slope. The slope risk prediction model is as follows:

[0065]

[0066] Where γ is the risk coupling degree, The weight of the i-th core influencing factor of the slope is... This is the nth core influencing factor of the slope.

[0067] By combining the causal factors and outcome factors of the slope and using the slope risk prediction model, the slope risk information of the target mining area is obtained.

[0068] Optionally, the method of combining the causal factors and the outcome factors of the slope and using the slope risk prediction model to obtain the slope risk information of the target mining area includes the following steps:

[0069] Based on the three-dimensional model of the mining area, the slope region is divided into multiple slope sub-regions;

[0070] Based on the three-dimensional model of the mining area, the sub-regions of slopes containing the aforementioned slope causative factors are screened out to obtain the slope risk areas;

[0071] The slope risk area is analyzed based on the slope result factors, and the presence of stress concentration and seepage phenomena in the slope risk area is determined based on the analysis results.

[0072] If the slope risk area does not have the stress concentration phenomenon and / or the seepage phenomenon, then the slope risk area is determined to be a low-risk area;

[0073] If the slope risk area simultaneously exhibits the stress concentration phenomenon and the seepage phenomenon, then the weights corresponding to the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information are input into the slope risk prediction model to obtain the risk coupling degree of the slope risk area.

[0074] If the risk coupling degree is greater than the preset risk coupling degree threshold, the slope risk area is marked as a high-risk area;

[0075] If the risk coupling degree is less than or equal to the risk coupling degree threshold, then the slope risk area is marked as the low-risk area;

[0076] Based on the three-dimensional model of the mining area, the location information of all the high-risk areas and the low-risk areas is obtained, and the locations of the high-risk areas and the low-risk areas are obtained.

[0077] The slope risk information of the target mining area is obtained by integrating all the locations of the high-risk areas and the low-risk areas.

[0078] Secondly, this application provides a data risk analysis system based on the Internet of Things, characterized in that it includes:

[0079] The memory is configured to store instructions; and

[0080] A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for data risk analysis based on the Internet of Things as described in any of the first aspects.

[0081] The above technical solution utilizes lidar point cloud data collected by drones to construct a 3D model of the target mine area. This allows for a comprehensive and intuitive understanding of the overall condition of the target mine, facilitating subsequent risk monitoring of the slope areas. By calculating point cloud residuals and curvature, point clouds containing slope cracks are precisely identified. Furthermore, based on these crack point clouds and using 2D mapping, the length, width, and depth of the cracks are accurately calculated, aiding in the subsequent assessment of the target mine's risk level. A slope risk prediction model is established using the decision laboratory method, enabling a comprehensive assessment of slope area risk. Considering the large area of ​​the target mine's slopes, the area is divided into multiple sub-regions, achieving precise risk level assessment. In summary, this method provides a more comprehensive and accurate mine risk monitoring approach, enabling efficient and precise all-around monitoring of the target mine's slope areas and ensuring the safety of mine workers.

[0082] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0083] Figure 1 A flowchart illustrating a data risk analysis method based on the Internet of Things provided in this application embodiment;

[0084] Figure 2 A flowchart of a curvature-based region growing algorithm provided in this application embodiment;

[0085] Figure 3A schematic diagram illustrating the relationship between the normal vectors of a point cloud and its neighboring points, provided in an embodiment of this application.

[0086] Figure 4 This is a schematic diagram of the process for providing slope crack information based on crack point cloud computing in an embodiment of this application. Detailed Implementation

[0087] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0088] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0089] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0090] Figure 1 The illustration shows a flowchart of a data risk analysis method based on the Internet of Things according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a data risk analysis method based on the Internet of Things, which may include the following steps:

[0091] S101. Acquire lidar point cloud data collected by the drone in the target mining area.

[0092] In this embodiment, the UAV uses its onboard LiDAR equipment to emit laser pulses across the entire target mining area. Based on the received laser emission signals, it generates a 3D point cloud of the target mine. This 3D point cloud, containing 3D coordinates, laser reflection intensity, and color information, is the LiDAR point cloud data. Because the UAV's laser point cloud scanning accuracy is extremely high, reaching the millimeter level, it can accurately reflect the true situation of the target mining area. Furthermore, the dense laser point cloud data, containing a large number of points, makes the subsequently constructed 3D model of the mining area more refined and accurate.

[0093] S102. Collect sensor information of the target mining area based on multiple types of sensors preset in the target mining area. The multiple types of sensors include stress sensors and groundwater level sensors.

[0094] In this embodiment, before predicting mining area risks, mining personnel installed various types of sensors in the target mining area, especially on its slopes. These sensors collected sensor information from the target mining area. Stress sensors were primarily used to monitor stress changes within the rock mass of the mining area. Stress changes affect the stability of the target mining area and, in severe cases, may lead to collapses. Groundwater sensors were mainly used to monitor groundwater level changes in the target mining area. This is because groundwater also affects the stability of the target mining area. When the groundwater level rises, the wetting range of the soil and rock increases, and the degree of wetting intensifies. The soil and rock become saturated and softened by water, leading to a decrease in shear strength and making the area prone to deformation, slippage, collapse, and other adverse geological phenomena. This effect is particularly pronounced in river terraces, mining slopes, and riverbank areas.

[0095] S103. Construct a three-dimensional model of the target mining area using lidar point cloud data, and calculate the slope crack information of the target mining area based on the three-dimensional model and the point cloud computing method.

[0096] In this embodiment, after denoising and removing outliers from the collected lidar point cloud data, surface fitting is performed on the point cloud data. Methods for surface fitting include polynomial regression and spline interpolation. The point cloud is constructed into a mathematical surface, and this surface is made as close as possible to all point clouds to obtain multiple fitted surfaces, including a slope fitted surface. By fusing multiple fitted surfaces, a three-dimensional model of the target mining area can be obtained. After obtaining the slope fitted surface, the residual values ​​between all point clouds and the surface are calculated. Point clouds with residual values ​​greater than a preset first residual threshold are filtered out to obtain multiple suspected crack point cloud areas. This is because the residual values ​​of areas with slope cracks are large, while the residual values ​​of areas on the slope without cracks or obstacles are almost zero. This method can initially screen out suspected crack point cloud areas, but the screened suspected crack areas are not accurate. Some areas may have protruding obstacles, such as rocks, and these areas may not have slope cracks. Therefore, further screening is required.

[0097] The neighborhood of the point cloud within the suspected crack point cloud region is divided into neighborhoods based on a preset neighborhood range threshold. Then, the angle between the normal vectors of each point cloud in the suspected crack point cloud region and its corresponding neighboring point clouds is calculated. Point clouds with a normal vector angle greater than a preset angle threshold and a residual value less than a preset second residual threshold are filtered out to obtain the region edge point cloud of the suspected crack point cloud region. This is because the normal vector angle suddenly increases at the boundary between the slope crack region and the slope surface protrusion region and the flat land on the slope. Furthermore, the residual value of the point cloud at the boundary is smaller than the residual value at the bottom of the crack or the top of the protrusion. Therefore, a second residual threshold less than the first residual threshold is set to filter out the point cloud at the boundary to obtain the region edge point cloud of the suspected crack point cloud region.

[0098] Then, the edge point cloud of the region is fitted into a surface, and the average curvature of the edge point cloud of the region is calculated using the curvature calculation formula. If the calculated average curvature is positive, it means that the suspected crack point cloud region is the initial crack point cloud region. This is because the surface fitted to the edge point cloud of the slope crack region is convex, so the calculated average curvature is positive. On the other hand, the surface fitted to the edge point cloud of the protruding area of ​​the slope surface is concave, so the calculated average curvature should be negative. By using positive and negative curvature, the point cloud of the protruding area in the suspected crack point cloud region can be screened out and removed to obtain the initial crack point cloud region.

[0099] To ensure the accuracy and reliability of subsequent calculations of crack width, length, and depth, a region growing algorithm is used again to filter out non-crack point clouds in the initial crack point cloud region, resulting in the target crack point cloud region. The region growing algorithm selects the point with the minimum curvature as the seed point and uses the normal angle and curvature value as thresholds to stop growth, thereby extracting the crack region and obtaining the target crack point cloud region. This method effectively, accurately, and completely extracts the point cloud of the crack region, yielding the target crack point cloud region. After segmenting the precise target crack point cloud region, mapping is performed along three directions: the x-y axis plane, the y-z axis plane, and the x-z axis plane, resulting in three two-dimensional point clouds in different directions. Based on the two-dimensional coordinates of these point clouds, the crack width, length, and depth of the corresponding local cracks in the slope within the target crack point cloud region can be calculated. Two-dimensional point clouds mapped in the xy direction can be used to calculate the width of local slope cracks, those mapped in the yz direction can be used to calculate the length, and those mapped in the xz direction can be used to calculate the depth. Furthermore, because the segmented target crack point cloud regions are highly precise, the calculated crack width, length, and depth are also accurate. Finally, based on the three-dimensional coordinates of the target crack point cloud regions and the three-dimensional model of the mining area, the specific locations of all local slope cracks within the target mining area can be determined, thus obtaining the crack locations. Integrating the crack width, length, depth, and location of the corresponding local slope cracks across all target crack point cloud regions yields the slope crack information for the target mining area.

[0100] S104. Combine the three-dimensional model of the mining area and the slope crack information to generate a crack monitoring point distribution strategy for the slope area of ​​the target mining area.

[0101] In this embodiment, the crack monitoring point distribution strategy is generated based on the distribution of slope cracks on the three-dimensional model of the mining area, as well as the length, width, and depth of the slope cracks. Specifically, one or more displacement sensors are deployed at each slope crack. The number of displacement sensors is determined based on the crack width, crack length, and crack depth. That is, for slope cracks whose crack length, crack length, and crack depth exceed the corresponding preset thresholds, multiple displacement sensors will be set to facilitate more accurate acquisition of rock mass movement information at the slope cracks and timely control of the degree of slope rock mass deformation.

[0102] S105. Based on the monitoring point distribution strategy, deploy multiple displacement sensors in the target mining area and use the displacement sensors to monitor the local displacement of all slope cracks in the slope area to obtain local displacement information.

[0103] In this embodiment, one or more displacement sensors are deployed at the slope cracks in the target mining area according to the generated monitoring point distribution strategy. These sensors are used to monitor the local displacement of all slope cracks in the slope area, obtaining local displacement information. Commonly used displacement sensors are GPS / GNSS (Satellite Navigation System) receivers, capable of monitoring millimeter-level displacement. Local displacement information includes the degree and direction of displacement. The degree of displacement refers to the distance the rock mass around the slope crack has moved, and the direction of displacement refers to the direction of rock mass movement; for example, when rock mass subsides, the direction of rock mass movement is vertically downwards.

[0104] S106. Based on sensor information, slope crack information and local displacement information, a slope risk prediction model is constructed, and the slope risk prediction model is used to conduct slope risk analysis on the slope area to obtain slope risk information of the target mining area.

[0105] In this embodiment, the changing trend of slope cracks in future event periods is first analyzed based on mining blasting information and local displacement information, i.e., crack prediction information. Specifically, the impact of mining blasting information on all slope cracks is assessed based on the amount of explosives used and the distance between the blasting location and the slope cracks in the mining blasting information, resulting in a blasting impact level. Similarly, the impact of local displacement information on all slope cracks is assessed based on the local displacement information, resulting in a displacement impact level. Linear regression analysis is then performed between the slope crack information and the blasting and displacement impact levels of all slope cracks to fit a linear regression equation. A crack prediction model is constructed based on the fitted linear regression equation, and crack prediction information for future time periods is predicted based on the blasting and displacement impact levels of the current event node. The resulting crack prediction information includes the predicted crack width, predicted crack length, and predicted crack depth for all slope cracks in the future time period.

[0106] Based on the 3D model of the mining area, the toe and shoulder locations of the slopes were determined. Since stress distribution is more concentrated at the toe, shoulder, and crack locations, the locations of these areas, along with the stress magnitude at the stress sensor locations, were analyzed to identify areas with a high probability of stress concentration. All location information was integrated and marked on the 3D model of the mining area to obtain the stress distribution information. Based on crack prediction information and future precipitation data, seepage level analysis was performed on the target mining area to obtain the seepage level of the area surrounding each slope crack. The seepage levels of all areas surrounding slope cracks were then integrated to obtain the slope seepage information for the target mining area.

[0107] Finally, based on the obtained local displacement information, stress distribution information, slope seepage information, and crack prediction information, and using the decision laboratory method, a slope risk prediction model for the target mining area is constructed. The risk coupling degree of each slope risk area in the target mining area is calculated based on the slope risk prediction model. The risk level of the slope risk area is divided according to the risk coupling degree. The location information and risk level of all slope risk areas are integrated to obtain slope risk information.

[0108] S107. Construct a digital twin model of the target mining area by combining the three-dimensional model of the mining area and the slope risk prediction model, and visualize the slope risk information through the digital twin model of the mining area.

[0109] In this embodiment, a digital twin model of the target mining area is constructed based on the three-dimensional model of the mining area and the slope risk prediction model. The digital twin model refers to a virtual model of a physical entity, process, or system created on an information platform through digital modeling technology. The location information and risk level of the slope risk area are visualized in the digital twin model of the mining area, which makes it easier for mining staff to eliminate risks in the mining area based on the digital twin model of the mining area, eliminate safety hazards in a timely manner, and prioritize the investigation of high-risk areas.

[0110] In one embodiment, constructing a three-dimensional model of the target mining area using lidar point cloud data, and calculating slope crack information of the target mining area based on the three-dimensional model and using point cloud computing methods includes the following steps:

[0111] Preprocess the lidar point cloud data of each target area in the target mining area, including the slope area;

[0112] The preprocessed lidar point cloud data is fitted with surfaces to obtain multiple fitted surfaces. The three-dimensional model of the target mining area is constructed by combining the multiple fitted surfaces. The fitted surfaces include the slope fitted surfaces corresponding to the slope areas.

[0113] Calculate the residual values ​​between all slope point clouds belonging to the slope area in the lidar point cloud data and the slope fitting surface, and integrate all slope point clouds with residual values ​​greater than the preset first residual threshold into multiple suspected crack point cloud areas.

[0114] For each suspected crack point cloud region, calculate the angle between the normal vectors of each slope point cloud and the neighboring point cloud in the suspected crack point cloud region. The neighboring point cloud is all point clouds within a preset neighborhood range around the slope point cloud.

[0115] If the angle between the normal vectors is greater than the preset angle threshold and the residual value is less than the preset second residual threshold, then the corresponding slope point cloud is taken as the edge point cloud of the suspected crack point cloud area, and the second residual threshold is less than the first residual threshold.

[0116] The average curvature of the point cloud at the edge of all regions is calculated using the curvature calculation formula.

[0117] If the average curvature is positive, then the suspected crack point cloud region is taken as the initial crack point cloud region.

[0118] The non-crack point cloud regions in the initial crack point cloud region are filtered out using a region growing algorithm to obtain the target crack point cloud region.

[0119] Based on the 3D model of the mining area, the crack point cloud in the target crack point cloud area is mapped in multiple directions in two dimensions to obtain the two-dimensional point cloud coordinates of the crack point cloud in different directions. Based on the two-dimensional point cloud coordinates, the slope crack information of the target mining area is calculated.

[0120] In this embodiment, the acquired lidar point cloud data is first processed to remove noise and outliers. Commonly used methods for noise removal and outlier removal include radius filtering and Gaussian filtering, which can effectively remove noise points and outliers from the lidar point cloud data. After preprocessing, the point cloud data of the slope area in the preprocessed lidar point cloud data is used for surface fitting. Methods that can be used for surface fitting include polynomial regression, spline interpolation, and triangulation algorithms. The point cloud is constructed into a mathematical surface, and this surface is made as close as possible to all the point cloud data. This surface is the slope fitting surface. Taking triangulation as an example, the point clouds in the LiDAR point cloud data are first connected into triangles to construct a triangular mesh. Adjacent triangular meshes are then stitched together to form a continuous surface. The size, shape, and distribution of the triangles are adjusted to ensure the surface is smooth and free of obvious defects. Finally, by stitching and optimizing the triangular meshes, fitted surfaces for different areas in multiple target mining areas are obtained, including slope fitted surfaces. These multiple fitted surfaces can be fused using modeling software to obtain a 3D model of the target mining area. Commonly used modeling software includes CloudCompare (3D point cloud processing software) and Meshlab (open-source mesh model processing software). After obtaining the slope fitted surface, the residual value between all point clouds and the surface is calculated. The residual value refers to the vertical distance between the point cloud and the fitted surface. Point clouds with residual values ​​greater than a preset first difference threshold are filtered out to obtain suspected crack point cloud areas. This is because areas with slope cracks on the slope appear concave, resulting in larger distances between the point cloud data in these concave areas and the fitted surface of the slope, leading to larger residual values. Conversely, the distances between the point cloud data and the fitted surface in areas with gentle slopes are extremely small, with some point cloud residuals even approaching zero. Therefore, a threshold method can be used to initially screen out suspected crack point cloud areas. However, since there may be protruding obstacles on the slope, such as rocks, the residual values ​​in these areas may also exceed the first residual threshold, necessitating further screening.

[0121] Based on a preset neighborhood range threshold, the point cloud within the suspected crack point cloud region is divided into neighborhoods. Then, the angle between the normal vectors of each point cloud within the suspected crack point cloud region and its corresponding neighboring point clouds is calculated. Figure 3 As shown, a close circle is first constructed by connecting the point cloud and its corresponding neighboring points. Then, the tangents at the point cloud and the neighboring points are obtained. The normal vectors of the point cloud and the neighboring points are obtained based on the perpendicular lines of the tangents. The angle between the normal vectors is then calculated. Similarly, the angle between the normal vectors of each point cloud and its neighboring points is calculated. Based on the angle between the normal vectors, the suspected crack point cloud regions are further filtered. Point clouds with a normal vector angle greater than a preset threshold and a residual value less than a preset second residual value threshold are filtered out, thus obtaining the region edge point cloud of the suspected crack point cloud region. This is because the normal vector angle suddenly increases at the boundary between the crack region or the raised region and the flat ground on the slope. Furthermore, the residual value of the point cloud at the boundary is smaller than the residual value at the bottom of the crack or the top of the raised region. Therefore, by setting a second residual threshold less than the first residual threshold, the point cloud at the boundary can be filtered out, thus obtaining the region edge point cloud of the suspected crack point cloud region.

[0122] Then, the edge point cloud is fitted to an edge surface, and the average curvature of the edge point cloud is calculated using the curvature calculation formula. The method for fitting the edge surface is the same as the method for fitting the slope surface; both can use triangulation algorithms, polynomial regression, etc. The formula for calculating the average curvature is as follows:

[0123]

[0124] Among them, E, F, and G are the first fundamental invariants of the surface, and L, M, and N are the second fundamental invariants of the surface.

[0125] If the calculated average curvature is positive, it indicates that the suspected crack point cloud region is the initial crack point cloud region. This is because the surface fitted to the edge point cloud of the slope crack region is convex, hence the calculated average curvature is positive. Conversely, the surface fitted to the edge point cloud of the protruding area on the slope surface is concave, hence the calculated average curvature should be negative. Using positive and negative curvature, the point clouds of the protruding areas in the suspected crack point cloud region can be filtered out and removed, resulting in the initial crack point cloud region. To ensure that the subsequently calculated crack width, crack length, and crack depth information are more accurate and reliable, it is necessary to use a region growing algorithm again to filter out the non-crack point clouds in the initial crack point cloud region, obtaining the target crack point cloud region. After segmenting the precise target crack point cloud region, mapping is performed along three directions: the x-y axis, the y-z axis, and the x-z axis. This yields three different 2D point clouds. Based on the 2D coordinates of these point clouds, the crack width, length, and depth of the corresponding local cracks on the slope within the target crack point cloud region can be calculated. Finally, using the 3D coordinates of the target crack point cloud region and the 3D model of the mining area, the specific locations of all local slope cracks within the target mining area can be determined, thus obtaining the crack locations. Integrating the crack width, length, depth, and location of all local slope cracks corresponding to the target crack point cloud regions yields the slope crack information for the target mining area.

[0126] In one embodiment, such as Figure 2 As shown, the process of using a region growing algorithm to remove non-crack point clouds from the initial crack point cloud region to obtain the target crack point cloud region includes the following steps:

[0127] The curvature of the initial crack point cloud is estimated by calculating the angle between the normal vectors of all initial crack point clouds in the initial crack point cloud region, and the principal curvature of all initial crack point clouds is obtained.

[0128] Construct an empty seed point sequence and a non-crack region point set, and add the initial crack point cloud with the smallest principal curvature as the seed point for the curvature region growth algorithm to the seed point sequence.

[0129] Based on the preset neighborhood order and using the K-neighborhood algorithm, multiple seed neighbors of the seed point are identified, and the normal angle between the seed point and each seed neighbor is calculated.

[0130] If all included angles of normals are greater than the included angle threshold, then the region growth is considered complete.

[0131] If any one or more normal angles are less than the preset normal angle threshold, the corresponding seed neighborhood point is added to the non-crack region point set.

[0132] Calculate the curvature values ​​of each seed neighbor point in the non-crack region point set;

[0133] If any one or more curvature values ​​are less than the preset curvature value threshold, the corresponding seed neighborhood point is added to the seed point sequence as a new seed point for region growth, and the original seed point in the seed point sequence is removed.

[0134] If all curvature values ​​are greater than the curvature value threshold or the seed point sequence is an empty set, then the region growth is considered complete.

[0135] If the region growth is complete, the non-crack region point set is removed from the initial crack point cloud region to obtain the target crack point cloud region.

[0136] In this embodiment, the normal curvature of all initial point clouds is calculated based on the angle between the normal vectors of all initial crack point clouds in the initial crack point cloud region. The formula for calculating the normal curvature is as follows:

[0137]

[0138] Where α is the angle between the line connecting the initial crack point cloud and its corresponding initial neighboring point cloud and the normal vector of the initial crack point cloud, β is the angle between the initial normal vectors, and pq i It is the straight-line distance between the initial crack point cloud p and the i-th initial neighboring point cloud q.

[0139] The principal curvatures of all initial crack point clouds are calculated based on the normal curvature. The relationship between the principal curvatures and the normal curvature is as follows:

[0140]

[0141] Where θ is the angle between the two principal direction vectors of the initial crack point cloud p, θ i For pq i With PQ i The angle between the planar projections, k1 and k2 are the two principal curvatures of the initial crack point cloud.

[0142] Construct an empty seed point sequence and a non-crack region point set. Add the initial crack point cloud with the smallest principal curvature as the seed point for the curvature region growing algorithm to the seed point sequence. First, determine the neighborhood order (which can be first order). Calculate the distance between the point cloud and all other point clouds. Select the K nearest points as the neighboring point clouds of this point cloud. This is the K-neighborhood algorithm. Using this method, multiple seed points can be determined. Then, calculate the normal angle between the seed point and each of its seed neighbors. A normal is a line on a plane that is perpendicular to the tangent to the curve at a point. The normal angle between the seed point and each of its seed neighbors can be calculated using geometry. If all calculated normal angles are greater than the normal angle threshold, the region growing is complete. If any one or more calculated normal angles are less than the preset normal angle threshold, the seed point is added to the non-crack region point set. Then, the curvature value of all seed neighbor points in the non-crack region point set is calculated using the normal curvature calculation formula. Seed neighbor points with curvature values ​​less than the preset curvature value threshold are added to the seed point sequence as new seed points for region growing. The seed points are then removed from the seed point sequence. The above steps are repeated until all seed points in the seed sequence are removed, indicating that the region growing is complete. The non-crack region point set is then removed from the initial crack point cloud region to obtain the target crack point cloud region.

[0143] In one embodiment, such as Figure 3 As shown, based on the 3D model of the mining area, multi-directional 2D mapping of the crack point cloud within the target crack point cloud region is performed to obtain the 2D point cloud coordinates of the crack point cloud in different directions. The slope crack information of the target mining area is calculated based on the 2D point cloud coordinates, including the following steps:

[0144] S201. For each target crack point cloud region, obtain the three-dimensional coordinate set of all crack point clouds in the target crack point cloud region based on the three-dimensional model of the mining area.

[0145] S202. Based on the three-dimensional coordinate set of the point cloud, perform two-dimensional mapping on all the crack point clouds in the target crack point cloud region in the three mapping directions of the x-axis-y-axis plane, the y-axis-z-axis plane, and the x-axis-z-axis plane to obtain two-dimensional point clouds in the three mapping directions.

[0146] S203. Based on the coordinates of the two-dimensional point cloud in the three mapping directions, calculate the crack width, crack length and crack depth of the local crack in the slope corresponding to the target crack point cloud area.

[0147] S204. The location of the local crack in the slope corresponding to the target crack point cloud area is calculated by using the three-dimensional coordinate set of the point cloud.

[0148] S205. Integrate the crack width, crack length, crack depth, and crack location of the corresponding local cracks on the slope of all target crack point cloud areas into slope crack information of the target mining area.

[0149] In this embodiment, a three-dimensional coordinate set of all crack point clouds in each target crack point cloud region is obtained based on the three-dimensional model of the mining area. These point cloud three-dimensional coordinates contain information on the width, length, and depth of the local cracks in the slope. This information can be stably and clearly represented from the side view, top view, and front view of all crack point clouds. Therefore, mapping these three views yields mapping maps in the xy, yz, and xz directions. Based on the point cloud three-dimensional coordinate set, mapping is performed in the x-axis-y-axis plane, y-axis-z-axis plane, and x-axis-z-axis plane of the target crack point cloud region to obtain three two-dimensional point clouds in different directions. Based on the two-dimensional coordinates of these two-dimensional point clouds, the crack width, crack length, and crack depth of the corresponding local cracks in the slope in the target crack point cloud region can be calculated. The two-dimensional point cloud mapped in the xy direction can be used to calculate the local crack width, the two-dimensional point cloud mapped in the yz direction can be used to calculate the local crack length, and the two-dimensional point cloud mapped in the xz direction can be used to calculate the local crack depth. For example, in the mapping along the x-axis and y-axis plane, the two-dimensional coordinates of the nth two-dimensional point cloud are (Xn, Yn). Therefore, the crack length can be obtained by calculating the difference between the maximum and minimum values ​​of the X-axis coordinates. Similarly, the crack width can be obtained by calculating the difference between the maximum and minimum values ​​of the Y-axis coordinates. Furthermore, since the segmented target crack point cloud region is highly precise, the calculated crack width, crack length, and crack depth are also accurate. Finally, the center point coordinates of the target crack point cloud region are determined based on the three-dimensional model of the mining area, and these center point coordinates are used as the crack location of the slope crack in the target mining area. The crack width, crack length, crack depth, and crack location of all target crack point cloud regions corresponding to local slope cracks are integrated to obtain the slope crack information of the target mining area.

[0150] In one embodiment, a slope risk prediction model is constructed based on sensor information, slope crack information, and local displacement information. The slope risk prediction model is then used to perform slope risk analysis on the slope area to obtain slope risk information for the target mining area. This process includes the following steps:

[0151] Obtain blasting information for the target mining area based on the pre-set mining plan;

[0152] Based on the blasting information and local displacement information in the mining area, the trend analysis of slope crack information is carried out to obtain the crack prediction information of the target mining area in the future time period.

[0153] Based on the crack location information and the three-dimensional model of the mining area, and using the threshold method to analyze the stress distribution of the rock mass stress information collected by the stress sensor, the stress distribution information of the target mining area is obtained.

[0154] The groundwater prediction information for the target mining area is estimated based on the precipitation information obtained in advance for the future time period and the groundwater information collected by the groundwater level sensor.

[0155] Based on crack prediction information and groundwater prediction information, and using the threshold method to analyze the seepage velocity level of the target mining area, the slope seepage information of the target mining area is obtained.

[0156] Based on local displacement information, stress distribution information, slope seepage information, and crack prediction information, a slope risk prediction model for the target mining area is constructed, and the slope risk information of the target mining area is predicted based on the slope risk prediction model.

[0157] In this embodiment, the changing trend of slope cracks in future event periods is first analyzed based on blasting information and local displacement information in the mining area, i.e., crack prediction information. Specifically, the blasting influence radius of the blasting operation is calculated based on the explosive mass and type in the blasting information and the influence radius calculation formula. The blasting influence range is determined based on the blasting influence radius and blasting location. The degree of blasting influence on slope cracks is measured based on the blasting influence range. The degree of displacement influence of local displacement information on the displacement of all slope cracks is evaluated based on a pre-constructed displacement crack digital model. Linear regression analysis is performed between the slope crack information of all slope cracks and the degree of blasting influence and displacement influence of all slope cracks to fit a linear regression equation. A crack prediction model is constructed based on the fitted linear regression equation. The crack prediction information for future time periods is predicted based on the degree of blasting influence and displacement influence of the current event node. The obtained crack prediction information includes the predicted crack width, predicted crack length, and predicted crack depth of all slope cracks in the future time period.

[0158] The toe and shoulder locations of the slopes are determined based on the 3D model of the mining area. Since the stress distribution is more concentrated at the toe, shoulder, and crack locations, the location information of areas with a high probability of stress concentration in the target mining area is analyzed based on the stress magnitude at the toe, shoulder, and crack locations, as well as the location of the stress sensor. Specifically, the distances between the crack location and the toe, the crack location and the shoulder, and the crack location and the location where the stress exceeds the preset stress threshold are calculated. The three distances are added together to obtain the comprehensive distance. The probability level of stress concentration is divided according to the magnitude of the comprehensive distance. The stress distribution information is obtained by integrating the probability level of stress concentration of all slope cracks with the slope locations corresponding to all slope cracks. For example, coordinates (20, 10, 20) indicate that the probability level of stress concentration is level one stress.

[0159] Future precipitation information refers to the total precipitation within the future time period. Groundwater information collected by groundwater level sensors refers to the groundwater level in the target mining area, collected using groundwater level gauges and other groundwater sensors. Based on the total precipitation in the future time period and the groundwater level at the current time point, the predicted groundwater level for the future time period can be estimated, i.e., groundwater prediction information. Then, based on crack prediction information and groundwater prediction information, slope seepage information of the target mining area is predicted. Slope seepage information refers to the seepage velocity level of the area surrounding all cracks in the slope area. Since crack width affects the seepage path and velocity of groundwater, the seepage velocity of groundwater is measured based on the crack prediction width and the predicted groundwater level in the crack prediction information. For example, the area surrounding slope cracks where the crack prediction width is greater than a preset crack prediction width threshold and the predicted groundwater level is greater than a preset predicted groundwater level threshold is classified as a level one seepage velocity. By integrating the crack locations of all slope cracks and the corresponding seepage velocity levels of the areas surrounding the cracks, the slope seepage information of the target mining area is obtained.

[0160] Since local displacement information, stress distribution information, slope seepage information, and crack prediction information all affect whether the target mining area will experience collapses, landslides, or other accidents, a slope risk prediction model for the target mining area can be constructed using the obtained local displacement information, stress distribution information, slope seepage information, and crack prediction information, and the decision laboratory method. Based on the slope risk prediction model, the risk coupling degree of each slope risk area in the target mining area can be calculated. The risk level of the slope risk area can be divided according to the risk coupling degree. The location information and risk level of all slope risk areas can be integrated to obtain slope risk information.

[0161] In one embodiment, the process of analyzing the changing trends of slope crack information based on blasting information and local displacement information in the mining area to obtain crack prediction information for the target mining area in the future includes the following steps:

[0162] The blasting influence radius of the target mining area is calculated based on the blasting information in the mining area. The degree of blasting influence on slope cracks is assessed based on the blasting influence radius, and the assessment result of the degree of blasting influence is used as the first influence factor.

[0163] The displacement impact of all slope cracks is assessed based on local displacement information and a pre-constructed displacement crack digital model, and the displacement impact assessment result is used as the second influencing factor.

[0164] The grey relational analysis model was used to analyze the degree of influence of the first and second influencing factors on slope cracks, and weights were assigned to the first and second influencing factors according to the degree of influence.

[0165] The least squares method was used to perform linear regression analysis on all the first and second influencing factors after weight allocation and the information on fractures in the mining area. A fracture prediction model was constructed based on the results of the linear regression analysis.

[0166] Based on the crack prediction model, crack changes in slopes are predicted, and crack prediction information for all slope cracks in the target mining area in the future time period is obtained.

[0167] In this embodiment, the explosive equivalent is calculated using the equivalent calculation formula based on the explosive mass and type in the mine blasting information. The explosion pressure is then calculated using the pressure calculation formula based on the calculated explosive equivalent. Finally, the blasting influence radius is calculated using the blasting influence radius calculation formula based on the calculated explosion equivalent and explosion pressure. The blasting range is calculated based on the blasting location and blasting influence radius in the mine blasting information. The degree of overlap between the blasting range and the crack locations in the slope crack information is used as the degree of blasting influence on the slope cracks in the target mine area. The overlap refers to the number of slope cracks within the blasting range. This degree of blasting influence is used as the first influencing factor. The equivalent calculation formula is as follows:

[0168]

[0169] Where W is the mass of the explosive, Q is the energy released by the explosive, and Q TNT This refers to the energy release of TNT.

[0170] The pressure calculation formula is as follows:

[0171]

[0172] Where P is the pressure at a distance R, K is a constant that depends on the type of explosive and environmental conditions, R is the distance from the explosion center, and n is the decay exponent, which is usually between 1.5 and 2.0.

[0173] The formula for calculating the radius of influence of a blast is as follows:

[0174]

[0175] By combining local displacement information and slope crack information, a pre-constructed displacement-crack digital model is used to obtain the critical displacement values ​​for slope cracks of different widths, depths, and lengths. The difference between the local displacement corresponding to each slope crack and the critical displacement value is used as the degree of influence of local displacement on each slope crack. The critical displacement value is simulated experimentally; exceeding this value will lead to crack propagation. The displacement-crack digital model is also constructed through pre-conducted simulation experiments. The obtained degree of displacement influence is used as a second influencing factor.

[0176] The predicted crack information of all slope cracks is used as the reference sequence for the grey relational analysis model, and the first and second influencing factors are used as the comparison sequences. The reference and comparison sequences are dimensionless, and the grey relational coefficients between them are calculated using the formulas of grey system relational analysis. The average value of these grey relational coefficients is used as the correlation degree value between the reference and comparison sequences, representing the influence of the first and second influencing factors on slope cracks. Weights are assigned to the first and second influencing factors based on this correlation degree value. After weight allocation, a linear relationship is assumed between the first and second influencing factors and the crack information in the mining area. Then, the slope and intercept of the linear relationship are calculated using the least squares method, yielding the regression equation between the first and second influencing factors and the crack information in the mining area. A crack prediction model is constructed based on this regression equation. In the future time period of the target mining area, there is no need to recalculate the crack information. The predicted crack information of all slope cracks in the target mining area in the future time period can be directly predicted based on the blasting information and local displacement information collected by displacement sensors, using the crack prediction model.

[0177] In one embodiment, a slope risk prediction model for the target mining area is constructed based on local displacement information, stress distribution information, slope seepage information, and crack prediction information. Predicting the slope risk information of the target mining area based on the slope risk prediction model includes the following steps:

[0178] Based on the pre-obtained slope risk assessment index, the degree of direct influence among local displacement information, stress distribution information, slope seepage information and crack prediction information is assigned using the scaling method.

[0179] Local displacement information, stress distribution information, slope seepage information, and crack prediction information are used as the core influencing factors of the slope in the target mining area. Based on the assignment of direct influence degree, a slope direct influence matrix of the core influencing factors is constructed. The slope direct influence matrix is ​​S=[s ij ] 4×4 , where s ij This indicates the degree of influence of core influencing factor i on core influencing factor j of the slope;

[0180] The direct impact matrix of the slope is normalized to obtain a standardized matrix.

[0181] Multiple decreasing matrix sequences are generated based on the standardized matrix to serve as the indirect influence matrix of the slope;

[0182] A comprehensive slope influence matrix is ​​established by combining the direct slope influence matrix and all indirect slope influence matrices.

[0183] The influence degree and affected degree of the core influencing factors of the slope are calculated based on the comprehensive influence matrix of the slope. The centrality and causality of the core influencing factors of the slope are then calculated based on the influence degree and affected degree.

[0184] A slope risk prediction model is established by combining centrality and causality and based on the coupling coordination function. The slope risk information of the target mining area is obtained based on the slope risk prediction model.

[0185] In this embodiment, the four core slope influencing factors are compared in pairs based on the pre-acquired slope risk assessment index to determine their direct influence relationship. The 0-5 scale is used to assign values ​​to the degree of direct influence among the four core slope influencing factors, with 0 representing no direct influence, 1 representing extremely weak direct influence, 2 representing relatively weak direct influence, 3 representing moderate direct influence, 4 representing relatively strong direct influence, and 5 representing extremely strong direct influence. The degree of direct influence is determined by the proportion of influence that core slope influencing factor i has on core slope influencing factor j: 0% = 0, 1%–20% = 1, 21%–40% = 2, 41%–60% = 3, 61%–80% = 4, and 81%–100% = 5. Based on the assignment results, a direct influence matrix for the four core influencing factors of slope—local displacement information, stress distribution information, slope seepage information, and crack prediction information—is established. The direct influence matrix for slope is as follows:

[0186]

[0187] In this context, the number entered in the empty space in the i-th row and j-th column represents the influence of the i-th core influencing factor on the j-th core influencing factor of the slope, for example, S 12 This represents the degree of influence of the first core influencing factor on the second core influencing factor of the slope.

[0188] The direct impact matrix of the slope is normalized using a standardized calculation formula to obtain a standardized matrix. The standardized calculation formula is as follows:

[0189] a = S / F

[0190] Where S is the direct influence matrix of the slope, and F is the maximum sum of the elements in each row of the direct influence matrix of the slope.

[0191] Based on the standardized matrix, a series of decreasing matrix sequences are generated as the indirect influence matrix of the slope. These decreasing matrix sequences are derived from a. 2 a 3 ...an constitutes the following formula:

[0192]

[0193] Based on the direct influence matrix and all indirect influence matrices of the slope, a comprehensive influence matrix of the slope is established. The formula for calculating the comprehensive influence matrix K of the slope is as follows:

[0194] K = a + a 2 +a 3 +......+a n =a(1-a) -1

[0195] The influence degree of the four core slope influencing factors is obtained by summing each row of the comprehensive slope influence matrix K, and the influence degree of the four core slope influencing factors is obtained by summing each column of the comprehensive slope influence matrix K. The centrality of the core slope influencing factors is obtained by summing the influence degree and the influence degree. The causality of the core slope influencing factors is obtained by subtracting the influence degree from the influence degree. The centrality represents the degree of influence of the core slope influencing factor on other core slope influencing factors and the total degree of influence of the core slope influencing factor on other core slope influencing factors. The causality represents the degree of influence of the core slope influencing factor on other core slope influencing factors or the total degree of influence of the core slope influencing factor on other core slope influencing factors. The centrality is used as the indicator weight required to construct the slope risk prediction model. The slope risk prediction model is established by combining the centrality and causality and based on the coupling coordination degree function. The risk coupling degree of the slope risk area is calculated according to the slope risk prediction model. The risk level of the slope risk area is divided according to the risk coupling degree. The location information and risk level of all slope risk areas are integrated to obtain the slope risk information.

[0196] In one embodiment, a slope risk prediction model is established by combining centrality and causality and based on a coupling coordination function. Obtaining slope risk information of the target mining area based on the slope risk prediction model includes the following steps:

[0197] The weights of the core influencing factors of the slope are obtained by assigning weights to the core influencing factors of the slope based on the centrality corresponding to the local displacement information, stress distribution information, slope seepage information and crack prediction information.

[0198] A four-quadrant diagram is constructed based on the centrality and causality of the core influencing factors of the slope. The core influencing factors of the slope are then divided into causal factors and outcome factors based on the four-quadrant diagram.

[0199] A slope risk prediction model is established based on the weights and coupling coordination function corresponding to the core influencing factors of the slope. The slope risk prediction model is as follows:

[0200]

[0201] Where γ is the risk coupling degree, Let i be the weight of the core influencing factor of the i-th slope. This is the core influencing factor of the nth slope.

[0202] By combining the causal and consequential factors of slope slopes and utilizing a slope risk prediction model, slope risk information for the target mining area can be obtained.

[0203] In this embodiment, the weights of four core slope influencing factors are assigned based on the centrality corresponding to local displacement information, stress distribution information, slope seepage information, and crack prediction information. Then, the centrality of the core slope influencing factors is used as the horizontal axis, the causality of the core slope influencing factors is used as the vertical axis, and the mean of the centrality and causality is used as the horizontal and vertical dividing lines to construct a four-quadrant diagram. The local displacement information and crack prediction information located in the first and second quadrants of the four-quadrant diagram are regarded as the causal factors of the slope, which are the core slope influencing factors that will directly lead to slope collapse. The stress distribution information and slope seepage information located in the third and fourth quadrants are regarded as the outcome factors of the slope. Subsequently, the slope risk area is divided according to the slope causal factors, and the slope risk level is calculated according to the slope outcome factors.

[0204] A slope risk prediction model is established based on the weights of the core influencing factors of the slope and the coupling coordination function, which is:

[0205]

[0206] Where Cn is the coupling degree of the n-ary system; u1...un are the contribution rates of the first to the nth subsystems to the order of the total system, respectively.

[0207] In one embodiment, obtaining slope risk information of a target mining area using a slope risk prediction model by combining slope causal factors and slope outcome factors includes the following steps:

[0208] Based on the three-dimensional model of the mining area, the slope area is divided into multiple slope sub-regions;

[0209] Based on the three-dimensional model of the mining area, the sub-regions of slopes with potential causes of slope problems are screened out to obtain the slope risk areas.

[0210] The slope risk area is analyzed based on the slope result factors, and the results of the analysis are used to determine whether there is stress concentration and seepage in the slope risk area.

[0211] If there is no stress concentration and / or seepage in the slope risk area, the slope risk area is determined to be a low-risk area.

[0212] If stress concentration and seepage phenomena exist simultaneously in the slope risk area, the weights corresponding to local displacement information, stress distribution information, slope seepage information and crack prediction information are input into the slope risk prediction model to obtain the risk coupling degree of the slope risk area.

[0213] If the risk coupling degree is greater than the preset risk coupling degree threshold, the slope risk area will be marked as a high-risk area;

[0214] If the risk coupling degree is less than or equal to the risk coupling degree threshold, the slope risk area is marked as a low-risk area.

[0215] Based on the three-dimensional model of the mining area, the location information of all high-risk and low-risk areas is obtained, and the locations of high-risk and low-risk areas are obtained.

[0216] By integrating the locations of all high-risk and low-risk areas, the slope risk information of the target mining area is obtained.

[0217] In this embodiment, the slope area is first divided into multiple sub-regions based on the 3D model of the mining area. Since the target mining area and the slope area are both sufficiently large, multiple sub-regions can be defined, allowing for individual monitoring of each sub-region. This results in more comprehensive and accurate monitoring of slope risk information. Then, sub-regions with slope cracks are identified based on the 3D model and designated as slope risk areas. This is because the slopes of the target mining area are inherently prone to landslides and collapses. The presence of cracks indicates a high likelihood of a collapse, thus these areas are directly designated as slope risk areas for focused monitoring.

[0218] The determination of whether stress concentration and seepage will occur in the current slope risk area is based on stress distribution information and slope seepage information. This is primarily determined by the probability level and seepage rate level in the stress distribution and seepage information. If no stress concentration or seepage occurs in the slope risk area, it can be directly classified as a low-risk area. Low-risk areas will still undergo risk mitigation, but with a lower priority compared to high-risk areas. If both stress concentration and seepage occur in the current slope risk area, the weights corresponding to local displacement information, stress distribution information, slope seepage information, and crack prediction information are input into the slope risk prediction model. The model outputs a risk coupling degree, which measures the probability of a dangerous accident occurring in the slope risk area. A higher risk coupling degree indicates a greater likelihood of collapses, landslides, or other accidents, and a higher risk level for the slope risk area. Slope risk areas with a risk coupling degree greater than the preset risk coupling degree threshold are marked as high-risk areas, and risk investigation will be carried out on high-risk areas first. Slope risk areas with a coupling degree less than or equal to the coupling degree threshold are marked as low-risk areas. After the risk elimination work of high-risk areas is completed, risk investigation work will be carried out on low-risk areas immediately.

[0219] Based on the 3D model of the mining area, the location information of all high-risk and low-risk areas is obtained, and these locations are integrated to obtain the slope risk information of the target mining area. The locations of high-risk and low-risk areas are directly marked in the 3D model of the mining area and displayed intuitively in the digital twin model of the mining area. This facilitates the subsequent risk assessment work of the target mine slope area by the mining area staff, enabling timely elimination of safety hazards in the target mine and ensuring the personal safety of the target mine staff.

[0220] This application also discloses a data risk analysis system based on the Internet of Things, characterized in that it includes:

[0221] The memory is configured to store instructions; and

[0222] The processor is configured to retrieve instructions from memory and, when executing those instructions, to implement the aforementioned method for data risk analysis based on the Internet of Things.

[0223] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.

[0224] The memory can be an internal storage unit of a computer device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) provided on the computer device. Furthermore, the memory can be a combination of internal storage units and external storage devices of a computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0225] This application also provides a machine-readable storage medium storing instructions that cause a machine to perform the above-described method for data risk analysis based on the Internet of Things.

[0226] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0227] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0228] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0229] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0230] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0231] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0232] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0233] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0234] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data risk analysis method based on the Internet of Things, characterized in that, The method includes the following steps: Acquire lidar point cloud data collected by drones in the target mining area; Sensor information of the target mining area is collected based on multiple types of sensors preset in the target mining area, including stress sensors and groundwater level sensors; A three-dimensional model of the target mining area is constructed using the lidar point cloud data. Based on the three-dimensional model of the mining area, the slope crack information of the target mining area is calculated using the point cloud computing method. A distribution strategy for crack monitoring points in the slope area of ​​the target mining area is generated by combining the three-dimensional model of the mining area and the slope crack information. According to the monitoring point distribution strategy, multiple displacement sensors are deployed in the target mining area. The displacement sensors are used to monitor the local displacement of all the slope cracks in the slope area to obtain local displacement information. Obtain the blasting information of the target mining area according to the preset mining plan; Based on the blasting information and local displacement information of the mining area, the slope crack information is analyzed for change trends to obtain crack prediction information of the target mining area in the future time period; Based on the crack location information and the three-dimensional model of the mining area, and using the threshold method to analyze the stress distribution of the rock mass stress information collected by the stress sensor, the stress distribution information of the target mining area is obtained. The groundwater prediction information for the target mining area is estimated based on the precipitation information for the future time period obtained in advance and the groundwater information collected by the groundwater level sensor. Based on the crack prediction information and the groundwater prediction information, and using the threshold method to analyze the seepage rate level of the target mining area, the slope seepage information of the target mining area is obtained. Based on the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information, a slope risk prediction model for the target mining area is constructed, and the slope risk information of the target mining area is predicted based on the slope risk prediction model. A digital twin model of the target mining area is constructed by combining the three-dimensional model of the mining area and the slope risk prediction model, and the slope risk information is visualized through the digital twin model of the mining area.

2. The method according to claim 1, characterized in that, The process of constructing a three-dimensional model of the target mining area using the lidar point cloud data, and calculating the slope crack information of the target mining area based on the three-dimensional model using the point cloud computing method, includes the following steps: The lidar point cloud data of each target area in the target mining area are preprocessed, and the target area includes slope areas; The preprocessed lidar point cloud data is fitted with a surface to obtain multiple fitted surfaces, and the multiple fitted surfaces are combined to construct a three-dimensional model of the target mining area. The fitted surfaces include the slope fitted surfaces corresponding to the slope area. Calculate the residual values ​​between all slope point clouds belonging to the slope region in the lidar point cloud data and the slope fitting surface, and integrate all slope point clouds whose residual values ​​are greater than a preset first residual threshold into multiple suspected crack point cloud regions. For each suspected crack point cloud region, calculate the angle between the normal vectors of each slope point cloud and the neighboring point cloud in the suspected crack point cloud region, where the neighboring point cloud is all point clouds within a preset neighborhood around the slope point cloud. If the included angle of the normal vector is greater than a preset included angle threshold and the residual value is less than a preset second residual threshold, then the corresponding slope point cloud is taken as the region edge point cloud of the suspected crack point cloud region, and the second residual threshold is less than the first residual threshold. The average curvature of the point cloud at the edge of all the aforementioned regions is calculated using the curvature calculation formula. If the average curvature is positive curvature, then the suspected crack point cloud region is taken as the initial crack point cloud region. The non-crack point cloud regions in the initial crack point cloud region are screened out using a region growing algorithm to obtain the target crack point cloud region. Based on the three-dimensional model of the mining area, the crack point cloud in the target crack point cloud area is mapped in multiple directions in two dimensions to obtain the two-dimensional point cloud coordinates of the crack point cloud in different directions. Based on the two-dimensional point cloud coordinates, the slope crack information of the target mining area is calculated.

3. The method according to claim 2, characterized in that, The step of using a region growing algorithm to filter out non-crack point clouds in the initial crack point cloud region to obtain the target crack point cloud region includes the following steps: The curvature of the initial crack point cloud is estimated by calculating the angle between the normal vectors of all initial crack point clouds in the initial crack point cloud region, and the principal curvature of all the initial crack point clouds is obtained. Construct an empty seed point sequence and a non-crack region point set, and add the initial crack point cloud with the smallest principal curvature as the seed point for the curvature region growth algorithm to the seed point sequence; Based on a preset neighborhood order and using the K-neighborhood algorithm, multiple seed neighbors of the seed point are identified, and the normal angle between the seed point and each of the seed neighbors is calculated respectively. If all the included angles of the normals are greater than the included angle threshold, then the region growth is considered complete. If any one or more of the normal angles are less than a preset normal angle threshold, then the corresponding seed neighborhood point is added to the non-crack region point set. Calculate the curvature value of each of the seed neighborhood points in the non-crack region point set; If any one or more of the curvature values ​​are less than a preset curvature value threshold, the corresponding seed neighborhood point is added to the seed point sequence as a new seed point for region growth, and the original seed points in the seed point sequence are removed. If all the curvature values ​​are greater than the curvature value threshold or the seed point sequence is an empty set, then the region growth is determined to be complete. If the region growth is completed, the non-crack region point set is removed from the initial crack point cloud region to obtain the target crack point cloud region.

4. The method according to claim 2, characterized in that, The step of performing multi-directional two-dimensional mapping of the crack point cloud within the target crack point cloud area based on the three-dimensional model of the mining area to obtain the two-dimensional point cloud coordinates of the crack point cloud in different directions, and calculating the slope crack information of the target mining area based on the two-dimensional point cloud coordinates, includes the following steps: For each target fracture point cloud region, the three-dimensional coordinate set of all fracture point clouds in the target fracture point cloud region is obtained according to the three-dimensional model of the mining area. Based on the three-dimensional coordinate set of the point cloud, all the crack point clouds in the target crack point cloud region are mapped in two dimensions in three mapping directions: x-axis-y-axis plane, y-axis-z-axis plane, and x-axis-z-axis plane, to obtain two-dimensional point clouds in the three mapping directions; Based on the coordinates of the two-dimensional point clouds in the three mapping directions, the crack width, crack length, and crack depth of the local cracks in the slope corresponding to the target crack point cloud region are calculated. The location of the local crack in the slope corresponding to the target crack point cloud region is calculated using the three-dimensional coordinate set of the point cloud. The crack width, crack length, crack depth, and crack location of all the target crack point cloud regions corresponding to the local cracks on the slope are integrated into the slope crack information of the target mining area.

5. The method according to claim 1, characterized in that, The step of analyzing the trend of slope crack information based on the blasting information and local displacement information in the mining area to obtain crack prediction information for the target mining area in the future time period includes the following steps: The blasting influence radius of the target mining area is calculated based on the blasting information of the mining area. The degree of blasting influence on the slope crack is assessed based on the blasting influence radius. The assessment result of the degree of blasting influence is used as the first influence factor. The displacement impact degree of all slope cracks is assessed based on the local displacement information and the pre-constructed displacement crack digital model, and the displacement impact degree assessment result is used as the second impact factor. The grey relational analysis model is used to analyze the degree of influence of the first influence factor and the second influence factor on the slope cracks, and weights are assigned to the first influence factor and the second influence factor according to the degree of influence. The least squares method is used to perform linear regression analysis on all the first and second influencing factors after weight allocation and the fracture information of the mining area, and a fracture prediction model is constructed based on the results of the linear regression analysis. Based on the crack prediction model, crack changes are predicted for the slope cracks to obtain crack prediction information for all slope cracks in the target mining area in the future time period.

6. The method according to claim 1, characterized in that, The step of constructing a slope risk prediction model for the target mining area based on the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information, and predicting the slope risk information of the target mining area based on the slope risk prediction model, includes the following steps: Based on the pre-acquired slope risk assessment index, the degree of direct influence is assigned to the local displacement information, the stress distribution information, the slope seepage information and the crack prediction information using the scaling method. The local displacement information, stress distribution information, slope seepage information, and crack prediction information are used as the core influencing factors of the slope in the target mining area. Based on the direct influence degree assignment results, a slope direct influence matrix of the core influencing factors is constructed. The slope direct influence matrix is ​​as follows: ,in, This indicates the degree of influence of the core influencing factor i on the core influencing factor j of the slope; The slope direct influence matrix is ​​normalized to obtain a standardized matrix. Based on the standardized matrix, a series of decreasing matrix sequences are generated as the indirect influence matrix of the slope; A comprehensive slope influence matrix is ​​established by combining the direct slope influence matrix and all the indirect slope influence matrices. The influence degree and the degree of being influenced by the core influencing factors of the slope are calculated based on the comprehensive influence matrix of the slope, and the centrality and causality of the core influencing factors of the slope are calculated based on the influence degree and the degree of being influenced. A slope risk prediction model is established by combining the centrality and causality and based on the coupling coordination function. The slope risk information of the target mining area is obtained according to the slope risk prediction model.

7. The method according to claim 6, characterized in that, The process of establishing a slope risk prediction model by combining the centrality and causality and based on the coupling coordination function, and obtaining slope risk information of the target mining area based on the slope risk prediction model, includes the following steps: The weights of the core influencing factors of the slope are obtained by assigning weights to the centrality corresponding to the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information. A four-quadrant diagram is constructed based on the centrality and causality of the core influencing factors of the slope, and the core influencing factors of the slope are divided into causal factors and outcome factors based on the four-quadrant diagram. A slope risk prediction model is established based on the weights and coupling coordination function corresponding to the core influencing factors of the slope. The slope risk prediction model is as follows: ， in, For risk coupling degree, The weight of the i-th core influencing factor of the slope is... This refers to the nth core influencing factor of the slope, where n is the total number of core influencing factors of the slope. By combining the causal factors and outcome factors of the slope and using the slope risk prediction model, the slope risk information of the target mining area is obtained.

8. The method according to claim 7, characterized in that, The process of combining the causal factors and outcome factors of the slope and using the slope risk prediction model to obtain the slope risk information of the target mining area includes the following steps: Based on the three-dimensional model of the mining area, the slope region is divided into multiple slope sub-regions; Based on the three-dimensional model of the mining area, the sub-regions of slopes containing the aforementioned slope causative factors are screened out to obtain the slope risk areas; The slope risk area is analyzed based on the slope result factors, and the presence of stress concentration and seepage phenomena in the slope risk area is determined based on the analysis results. If the slope risk area does not have the stress concentration phenomenon and / or the seepage phenomenon, then the slope risk area is determined to be a low-risk area; If the slope risk area simultaneously exhibits the stress concentration phenomenon and the seepage phenomenon, then the weights corresponding to the local displacement information, the stress distribution information, the slope seepage information, and the crack prediction information are input into the slope risk prediction model to obtain the risk coupling degree of the slope risk area. If the risk coupling degree is greater than the preset risk coupling degree threshold, the slope risk area is marked as a high-risk area; If the risk coupling degree is less than or equal to the risk coupling degree threshold, then the slope risk area is marked as the low-risk area; Based on the three-dimensional model of the mining area, the location information of all the high-risk areas and the low-risk areas is obtained, and the locations of the high-risk areas and the low-risk areas are obtained. The slope risk information of the target mining area is obtained by integrating all the locations of the high-risk areas and the low-risk areas.

9. A data risk analysis system based on the Internet of Things, characterized in that, include: The memory is configured to store instructions; as well as A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement an Internet of Things-based data risk analysis method according to any one of claims 1 to 8.

Images