A building ground subsidence early warning method and system based on a knowledge graph

Abstract

The application discloses a building ground subsidence early warning method and system based on a knowledge graph, and belongs to the technical field of safety early warning. Detectors are arranged at a plurality of monitoring points in a subsidence monitoring area to detect the subsidence amount of each monitoring point; laser surveying and mapping data of the subsidence monitoring area are acquired to obtain topographic information of the subsidence monitoring area; whether each monitoring point in the monitoring point area is interfered with is compared according to the topographic information of the subsidence monitoring area, laser detection data of a group of monitoring points without damage of non-natural factors are filtered, and the filtered laser detection data are compared with a preset deviation to judge the authenticity of subsidence and the comprehensive subsidence amount of a subarea; the subsidence amount of each monitoring point and the comprehensive subsidence amount of the subarea are combined, early warning and visualization are carried out based on the subsidence amount and the subsidence rate respectively; whether the subsidence rate of the subsidence monitoring area meets an expectation is judged based on the knowledge graph, and an influencing factor most conforming to the current subsidence rate is calculated. The application can accurately and timely present the subsidence trend of the subsidence monitoring area and early warning.

Description

Technical Field

[0001] This invention relates to the field of safety early warning technology, and in particular to a method and system for early warning of building ground settlement based on knowledge graph. Background Technology

[0002] In existing construction projects, ground settlement monitoring has always been a key monitoring indicator. Due to the presence of groundwater below the ground, ground settlement problems can occur due to underground cavities.

[0003] In existing technologies, probe technology and satellite remote sensing are commonly used for ground settlement monitoring, each with its own limitations. Probe technology monitors soil displacement and deformation in real time by installing sensors on or below ground. Common probes include settlement gauges, inclinometers, and strain gauges. In low-rise building complexes, probe technology is typically used for ground settlement monitoring, but it can only detect localized deformation at the installation point, making it difficult to comprehensively reflect large-scale ground settlement. This can lead to significant discrepancies between detected values ​​near roadsides or factories and actual values, making it difficult for the system to effectively filter out such discrepancies. Satellite remote sensing technology uses sensors onboard satellites to acquire information on electromagnetic waves reflected or emitted by the ground, and then analyzes ground deformation. Common remote sensing technologies include synthetic aperture radar (SAR) and optical remote sensing. In high-rise buildings, remote sensing is typically used for ground settlement detection, which results in slow detection of ground settlement. Ground settlement may only be detected when there is a noticeable shift in the building, making it impossible to identify it through the system in a short time.

[0004] Therefore, both probe and satellite remote sensing technologies have their limitations. Probe technology cannot be deployed in areas with significant ground fluctuations or soft ground; remote sensing technology typically performs well on tall buildings but is not effective for low-rise structures. Solving the problems of inaccurate data and untimely monitoring of ground subsidence caused by environmental factors is an urgent technical challenge. Summary of the Invention

[0005] To overcome the above problems, this invention provides a knowledge graph-based method and system for early warning of building ground settlement, and the technical solution adopted is as follows:

[0006] In a first aspect, the present invention provides a building ground settlement early warning method based on knowledge graphs, comprising the following steps:

[0007] (1) Detectors are set up at multiple monitoring points in the settlement monitoring area. Laser is emitted into the settlement monitoring area. The detectors in the area receive the laser signal and return the signal to obtain laser detection data and calculate the settlement of each monitoring point.

[0008] (2) Obtain laser mapping data of the settlement monitoring area to obtain the topographic information of the settlement monitoring area;

[0009] (3) Based on the topographic information of the settlement monitoring area, compare whether each monitoring point in the monitoring area is disturbed, and filter to obtain a set of laser detection data of the monitoring points without non-natural factors;

[0010] (4) Compare the laser detection data of a set of monitoring points that have not been damaged by non-natural factors with the pre-set deviation to determine the authenticity of the settlement and the comprehensive settlement of the sub-region;

[0011] (5) Based on the settlement amount of each monitoring point and the comprehensive settlement amount of the sub-region, early warning and visualization are provided based on the settlement amount and settlement rate respectively;

[0012] (6) Based on the knowledge graph, determine whether the settlement rate of the settlement monitoring area meets the expectations, and calculate the influencing factors that best match the current settlement rate.

[0013] Furthermore, in step (1), the laser detection data includes the laser emission distance and the vertical height of the detector relative to the laser emission device.

[0014] Furthermore, the laser emission distance is calculated based on the laser return time, and the detector position is calculated by combining the laser emission angle. The detector position is then compared with the previously obtained detector position to calculate whether the detector position has settled and the amount of settlement.

[0015] Further, step (2) includes:

[0016] (2-1) A laser pulse is emitted vertically downward by a laser. The laser beam illuminates the earth surface and returns. The distance between each survey point and the laser is obtained. Multiple measurements are taken to obtain the three-dimensional coordinates of a large number of points on the earth surface in the settlement monitoring area.

[0017] (2-2) Perform noise reduction and filtering on the collected raw point data to remove noise points and outliers;

[0018] (2-3) Divide the processed point data into different categories, including ground points, building points, and vegetation points;

[0019] (2-4) Extract ground points from the point data, use interpolation algorithm to generate a regular grid based on the elevation data of the ground points to obtain a digital elevation model, combine the classification results of the point data to identify and label building points and vegetation points in the area, and obtain the topographic information of the settlement monitoring area.

[0020] Furthermore, the laser integrates a positioning system and an inertial measurement unit, which are used to acquire position and attitude information, respectively.

[0021] Further, step (3) includes:

[0022] (3-1) Obtain the location of each monitoring point in the settlement monitoring area;

[0023] (3-2) Based on the current topographic information and the previous topographic information of the settlement monitoring area, compare whether the fluctuation amplitude of each monitoring point is greater than the threshold. If so, it is determined that the monitoring point is disturbed. After clearing the interference, the data of the monitoring point is re-mapped. When the interference cannot be cleared, the data of the monitoring point is directly removed to obtain a set of laser detection data of the monitoring point without non-natural factors.

[0024] If not, a set of laser detection data for monitoring points that are not damaged by non-natural factors can be obtained directly.

[0025] Further, step (4) includes:

[0026] (4-1) Perform local spatial autocorrelation analysis between the monitoring point and the surrounding monitoring points. If the settlement trend of a certain monitoring point is significantly negatively correlated with that of the surrounding monitoring points, it is judged as a suspected anomaly point; or, compare the settlement of two adjacent monitoring points. If the difference in settlement between a certain monitoring point and more than three adjacent monitoring points exceeds 2 times the standard deviation, it is judged as a suspected anomaly point.

[0027] (4-2) For suspected anomalies, combine the historical settlement curve of the monitoring point to determine whether the current data of the monitoring point is a sudden change point. If so, mark the monitoring point as faulty; otherwise, treat it as a normal monitoring point and continue to process it.

[0028] (4-3) Perform dynamic spatial clustering on normal monitoring points, extract the cumulative settlement, average settlement rate and second derivative of settlement curve of each monitoring point as clustering features, and divide sub-regions with consistent settlement patterns based on spatiotemporal feature similarity using density clustering algorithm, and calculate the comprehensive settlement of each sub-region.

[0029] Further, step (5) includes:

[0030] When the settlement rate of a monitoring point exceeds the preset settlement rate, or when the total settlement of a monitoring point exceeds the preset maximum settlement, a warning for dangerous monitoring points will be issued.

[0031] When the average settlement rate of a sub-region exceeds the preset settlement rate, or when the total settlement of a sub-region exceeds the preset maximum settlement, a warning of the danger zone is issued.

[0032] The settlement rate, average settlement rate, hazard monitoring points, and hazard range are visualized.

[0033] Further, step (6) includes:

[0034] (6-1) Constructing a knowledge graph: The factors affecting the settlement rate are divided into natural factors and anthropogenic factors, and both natural and anthropogenic factors contain several secondary factors;

[0035] (6-2) By fitting the relationship between each factor and the settlement rate using historical data, the preset weights of each factor are obtained;

[0036] (6-3) Investigate the influencing factors of the settlement monitoring area, calculate the expected settlement rate according to the preset weights, and determine whether the actual settlement rate in the settlement monitoring area meets the expected settlement rate.

[0037] If the expected results are met, the influencing factors obtained from the survey are considered to be actual factors.

[0038] If it does not meet expectations, proceed with (6-4);

[0039] (6-4) Calculate based on the current settlement rate obtained in step (5) and the influencing factors obtained from the survey. Arrange and combine the various influencing factors obtained from the survey to obtain the combination that is closest to the current settlement rate as the actual factor.

[0040] Secondly, this invention proposes a knowledge graph-based building ground settlement early warning system to implement the aforementioned knowledge graph-based building ground settlement early warning method.

[0041] The beneficial effects of this invention are:

[0042] This invention employs laser detection technology combined with laser mapping technology for ground subsidence monitoring. It can quickly and efficiently obtain subsidence amounts at various monitoring points and topographic information of the monitoring area by accumulating data over a short period. It identifies interference points, avoids their influence, and further assesses the authenticity of the subsidence and the overall subsidence amount of sub-regions. This results in a set of relatively accurate, intuitive, and visualized monitoring data. Early warnings are issued based on both subsidence amount and subsidence rate, promptly presenting ground subsidence phenomena. Furthermore, it uses a knowledge graph to determine whether the subsidence rate in the monitoring area meets expectations and calculates the influencing factors most consistent with the current subsidence rate, providing guidance for subsidence management. Attached Figure Description

[0043] Figure 1 This is a schematic diagram illustrating the framework of a knowledge graph-based early warning method for building ground settlement, as shown in an embodiment of the present invention.

[0044] Figure 2 This is a schematic flowchart illustrating a knowledge graph-based early warning method for building ground settlement according to an embodiment of the present invention.

[0045] Figure 3 This is a schematic diagram of a knowledge graph shown in an embodiment of the present invention. Detailed Implementation

[0046] The present invention will be further described and illustrated below with reference to specific embodiments. The embodiments described are merely examples of the content of this disclosure and do not limit the scope of the invention. The technical features of each embodiment in the present invention can be combined accordingly, provided that there is no mutual conflict.

[0047] The accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0048] The flowchart shown in the attached diagram is merely an illustrative example and does not necessarily include all steps. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0049] Figure 1 The diagram shows a framework diagram of a knowledge graph-based early warning method for building ground settlement according to the present invention. It introduces laser ranging, laser mapping, positioning system and settlement factors to achieve visualization and early warning of settlement speed, settlement range, etc., as well as to determine whether the treatment plan is effective and analyze the most suitable influencing factors.

[0050] like Figure 2 As shown, the specific implementation process mainly includes the following steps:

[0051] S1. Multiple detectors are deployed in the settlement monitoring area. Lasers are emitted into the settlement monitoring area, and the detectors in the area receive the laser signals and return the signals to obtain laser detection data and calculate the settlement at each monitoring point.

[0052] The laser detection data includes the laser emission distance and the vertical height of the detector relative to the laser emitting device.

[0053] The laser's emission distance is calculated based on the laser's return time, combined with the laser's emission angle. The detector position can be calculated, and by comparing it with the detector position obtained in the previous detection, it can be determined whether the detector position has shifted and the vertical shift angle. Here, the detector is fixed on the monitoring point on the ground of the settlement monitoring area and will settle together with the monitoring point on the ground.

[0054] In one specific embodiment of the present invention, a laser transmitter emits a laser signal to detectors arranged in a settlement monitoring area. The detectors receive the laser signal and return a signal. The time t from emission to reception of the laser signal is measured, and the emission distance of the laser can be calculated based on the signal velocity (generally considered to be the speed of light c) and the time difference. :

[0055]

[0056] Here, dividing by 2 is because the laser signal needs to travel back and forth once; to improve accuracy, multiple measurements can be taken and the average value taken.

[0057] Using trigonometric relationships, the vertical height of the detector relative to the laser emitting device is calculated:

[0058]

[0059] The distance data from each measurement is stored in the data storage unit, including both current and historical data. To analyze the settlement at the detector location, the previous height is read from the historical data in the data storage unit. The settlement at the detector location is equal to the difference in the vertical height of the detector between the two measurements. .

[0060] The measurement results can be corrected due to factors such as the angle measurement error of the laser emitter, the influence of atmospheric refraction during laser propagation, and the positional deviation of the detector. For the influence of atmospheric refraction, a refraction correction coefficient can be calculated using an atmospheric optical model based on meteorological data (such as temperature, air pressure, and humidity) to correct the measurement distance. For the angle measurement error of the laser emitter and the positional deviation of the detector, errors can be reduced by periodically calibrating the equipment, increasing the number of measurement points, and averaging the data.

[0061] This step allows for the preliminary acquisition of settlement data at various monitoring points within the monitoring area.

[0062] S2, acquire laser mapping data of the settlement monitoring area to obtain the topographic information of the settlement monitoring area.

[0063] Laser mapping technology is a technique that obtains ground distances and shapes by emitting laser pulses and measuring their return time. It is widely used in topographic surveying, building modeling, forestry surveys, urban planning, and disaster monitoring. By emitting laser pulses vertically downwards from a laser, the laser beam illuminates the earth's surface and returns. Based on the principle of laser detection similarity, the distance between each survey point and the laser can be obtained. Through multiple measurements, a large amount of point data on the earth's surface in the subsidence monitoring area is acquired, recording information such as the time, angle, and reflection intensity of the laser from emission to reception. Simultaneously, combined with the laser's positioning and attitude information obtained from the BeiDou Navigation Satellite System and inertial measurement units, three-dimensional coordinate data for each laser point is generated. The acquired raw laser data undergoes denoising and filtering to remove noise points and outliers caused by equipment errors, environmental interference, and other factors, improving data quality. Subsequently, machine learning and geometric feature analysis methods are used to classify the laser point cloud data into different categories, such as ground points, building points, and vegetation points. This technique is common knowledge in the field and will not be elaborated further here.

[0064] Ground points are extracted from laser point cloud data. Interpolation algorithms, such as Kriging interpolation and spline interpolation, are used to generate a regular grid based on the elevation data of the ground points to obtain a digital elevation model, which intuitively reflects the topographic relief of the area. Combined with the classification results of laser point cloud data, information on major land features such as buildings and vegetation points in the area is identified and extracted, and they are classified and labeled to obtain the topographic information of the settlement monitoring area.

[0065] Here, the laser can be an airborne, vehicle-mounted, or ground-based laser scanner, with airborne or vehicle-mounted equipment being preferred. Flight or driving routes are planned in advance. Airborne equipment can be carried by drones and fly along the planned route, while vehicle-mounted equipment can be carried by vehicles and drive along the planned route. Both airborne and vehicle-mounted equipment can combine the BeiDou positioning system and inertial measurement units to obtain positioning and attitude information.

[0066] S3 uses the BeiDou positioning system to obtain the location of each monitoring point in the settlement monitoring area, and compares the monitoring point area with the topographic information of the settlement monitoring area to determine whether the monitoring point is being interfered with.

[0067] This step is used to determine whether the monitoring point has been damaged by non-natural factors, such as human interference or damage from vegetation. If the current mapping data of the monitoring point differs significantly from the previously mapped data, the laser detection data of that monitoring point can be determined to be invalid. By calculating these two data points, a set of laser detection data indicating that the monitoring point has not been damaged by non-natural factors can be obtained.

[0068] Interference with monitoring points should be reported to staff for handling. Once the issue is resolved, the surveying process can be restarted for a second survey. If staff do not take action, the data from the erroneous monitoring point will be set as interference, and monitoring of the erroneous monitoring point will be suspended.

[0069] S4 compares the laser detection data of the monitoring points after interference elimination with the pre-set deviation to determine the authenticity of the settlement and the overall settlement amount.

[0070] Verification of authenticity: Local spatial autocorrelation analysis is performed between the monitoring point and surrounding monitoring points to calculate Moran's I index. If a monitoring point has a significantly negative correlation (p<0.05) with the settlement trend of surrounding monitoring points, it is identified as a suspected anomaly. The actual settlement curve should conform to the laws of geomechanics. Further analysis is conducted by combining the historical vertical height curve (settlement curve) of the monitoring point to determine whether the current data of the monitoring point is a sudden change point. In this embodiment, Bayesian variable point analysis is used to identify sudden changes caused by non-geological factors (such as equipment failure). If so, the monitoring point is marked as faulty and reported to the staff for handling; otherwise, it is treated as a normal monitoring point and processing continues.

[0071] In addition to the above methods, those skilled in the art can also compare the settlement of two adjacent monitoring points. If the settlement of a certain monitoring point differs from that of more than three adjacent nodes by more than twice the standard deviation, then the monitoring point is identified as a suspected anomaly. Similarly, the historical vertical height curve (settlement curve) of the monitoring point is used to further determine whether the monitoring point is faulty.

[0072] Dynamic spatial clustering is performed on the monitoring points that are determined to be real, and the cumulative settlement, average settlement rate, and second derivative (acceleration) of the curve of each monitoring point are extracted as clustering features. The density clustering (OPTICS) algorithm is used to divide the sub-regions with consistent settlement patterns based on the similarity of spatiotemporal features, and the statistical indicators of each sub-region are calculated.

[0073] In this embodiment, weights are assigned based on the density of monitoring points and geological sensitivity (such as the thickness of soft soil) within a sub-region, and the weighted average cumulative settlement is calculated to represent the comprehensive settlement of the sub-region.

[0074] S5 provides early warning and visualization of settlement.

[0075] The settlement rate of the monitoring point is calculated by calculating the settlement data detected in the recent period.

[0076] When the settlement rate of a monitoring point exceeds the preset settlement rate, or when the total settlement of a monitoring point exceeds the preset maximum settlement, a warning for dangerous monitoring points will be issued.

[0077] When the average settlement rate of a sub-region exceeds the preset settlement rate, or when the total settlement of the sub-region exceeds the preset maximum settlement, a warning of the danger zone is issued.

[0078] The aforementioned settlement rate, hazard monitoring points, and hazard range are visualized.

[0079] In one specific embodiment of this invention, high-resolution satellite imagery or vector maps (generated using GIS tools such as QGIS or ArcGIS) are used as the base map to mark each monitoring point within the area. Circles represent normal monitoring points, triangles represent hazardous monitoring points, and polygons mark sub-area boundaries. Sub-areas within hazardous zones are marked with a semi-transparent red color, and a color gradient represents the average settlement rate. Through visualization technology, users can intuitively identify high-risk settlement areas, trace spatiotemporal evolution patterns, and directly determine the effectiveness of settlement treatment measures in the monitored area.

[0080] S6. Based on the knowledge graph, determine whether the settlement rate of the settlement monitoring area meets the expectations, and calculate the influencing factors that best match the current settlement rate.

[0081] like Figure 3 As shown, a knowledge graph is constructed: the factors affecting the settlement rate are divided into natural factors and anthropogenic factors. Natural factors include primary factors (underground cave collapse, groundwater alteration, earthquake, animal digging, plant rooting) and secondary factors (reduction in groundwater flow, groundwater diversion, small animal digging, large animal digging, large perennial plants, large annual plants); anthropogenic factors include primary factors (surface engineering, underground engineering) and secondary factors (surface excavation, deep surface excavation, surface reinforcement, subway construction, well digging, basement excavation, underground reinforcement).

[0082] By fitting the relationship between various factors and settlement rate using historical data, the preset weights of each factor are obtained. By manually detecting the influencing factors in the area, the expected settlement rate is calculated, which can determine whether the settlement rate of the monitored area meets the expectations and whether the treatment plan is effective. If it does not meet the expectations, the settlement rate is obtained through S5 and calculated with the determined settlement factors. Multiple preset influencing factors are arranged and combined to obtain the combination most similar to the current settlement rate as the influencing factor that best matches the current settlement rate, providing guidance for formulating settlement treatment measures.

[0083] Based on the same inventive concept, this embodiment also provides a knowledge graph-based building ground settlement early warning system, which is used to implement the above embodiments. The terms "module," "unit," etc., used below can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible.

[0084] In this embodiment, a knowledge graph-based building ground settlement early warning system includes:

[0085] A laser detection module is used to emit a laser to a settlement monitoring area. Multiple monitoring points in the settlement monitoring area are equipped with detectors. The detectors receive the laser signal and return the signal, acquire laser detection data, and calculate the settlement amount of each monitoring point.

[0086] The laser mapping module is used to acquire laser mapping data of the settlement monitoring area and obtain the topographic information of the settlement monitoring area;

[0087] The filtering module is used to compare the monitoring points in the settlement monitoring area with the topographic information of the monitoring area to see if there is any interference, and to filter out a set of laser detection data of the monitoring points that are not damaged by non-natural factors.

[0088] The data analysis and visualization module is used to compare laser detection data from a set of monitoring points without any non-natural damage with a pre-set deviation to determine the authenticity of the settlement and the overall settlement of the sub-region; combining the settlement of each monitoring point and the overall settlement of the sub-region, it provides early warnings and visualizations based on settlement amount and settlement rate respectively.

[0089] The knowledge graph module is used to determine whether the settlement rate of the settlement monitoring area meets expectations based on the knowledge graph, and to calculate the influencing factors that best match the current settlement rate.

[0090] For the system embodiments, since they basically correspond to the method embodiments, relevant details can be found in the descriptions of the method embodiments; the implementation methods of the remaining modules will not be repeated here. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0091] The system embodiments of the present invention can be applied to any device with data processing capabilities, such as a computer or other similar device. The system embodiments can be implemented in software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device loading the corresponding computer program instructions from non-volatile memory into memory for execution.

[0092] The above examples are merely specific embodiments of the present invention. Obviously, the present invention is not limited to the above embodiments and many variations are possible. All variations that can be directly derived or conceived by those skilled in the art from the disclosure of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A knowledge graph-based method for early warning of building ground settlement, characterized in that, Includes the following steps: (1) Detectors are set up at multiple monitoring points in the settlement monitoring area. Laser is emitted into the settlement monitoring area. The detectors in the area receive the laser signal and return the signal to obtain laser detection data and calculate the settlement of each monitoring point. (2) Obtain laser mapping data of the settlement monitoring area to obtain the topographic information of the settlement monitoring area; (3) Based on the topographic information of the settlement monitoring area, compare whether each monitoring point in the monitoring area is disturbed, and filter to obtain a set of laser detection data of the monitoring points without non-natural damage; Step (3) includes: (3-1) Obtain the location of each monitoring point in the settlement monitoring area; (3-2) Based on the current topographic information and the previous topographic information of the settlement monitoring area, compare whether the fluctuation amplitude of each monitoring point is greater than the threshold. If so, it is determined that the monitoring point is disturbed. After clearing the interference, the data of the monitoring point is re-mapped. When the interference cannot be cleared, the data of the monitoring point is directly removed to obtain a set of laser detection data of the monitoring point without non-natural factors. If not, a set of laser detection data for monitoring points that are not damaged by non-natural factors will be obtained directly; (4) Compare the laser detection data of a set of monitoring points that have not been damaged by non-natural factors with the pre-set deviation to determine the authenticity of the settlement and the comprehensive settlement of the sub-region; Step (4) includes: (4-1) Perform local spatial autocorrelation analysis between the monitoring point and the surrounding monitoring points. If the settlement trend of a certain monitoring point is significantly negatively correlated with that of the surrounding monitoring points, it is judged as a suspected anomaly point; or, compare the settlement of two adjacent monitoring points. If the difference in settlement between a certain monitoring point and more than three adjacent monitoring points exceeds 2 times the standard deviation, it is judged as a suspected anomaly point. (4-2) For suspected anomalies, combine the historical settlement curve of the monitoring point to determine whether the current data of the monitoring point is a sudden change point. If so, mark the monitoring point as faulty; otherwise, treat it as a normal monitoring point and continue to process it. (4-3) Perform dynamic spatial clustering on normal monitoring points, extract the cumulative settlement, average settlement rate and second derivative of settlement curve of each monitoring point as clustering features, and divide sub-regions with consistent settlement patterns based on spatiotemporal feature similarity using density clustering algorithm, and calculate the comprehensive settlement of each sub-region. (5) Based on the settlement amount of each monitoring point and the comprehensive settlement amount of the sub-region, early warning and visualization are provided based on the settlement amount and settlement rate respectively; (6) Based on the knowledge graph, determine whether the settlement rate of the settlement monitoring area meets the expectations, and calculate the influencing factors that best match the current settlement rate.

2. The knowledge graph-based early warning method for building ground settlement according to claim 1, characterized in that, In step (1), the laser detection data includes the laser emission distance and the vertical height of the detector relative to the laser emission device.

3. The knowledge graph-based early warning method for building ground settlement according to claim 2, characterized in that, The laser emission distance is calculated based on the laser return time. The detector position is calculated by combining the laser emission angle. The detector position is compared with the detector position obtained in the previous detection to calculate whether the detector position has settled and the amount of settlement.

4. The knowledge graph-based early warning method for building ground settlement according to claim 1, characterized in that, Step (2) includes: (2-1) A laser pulse is emitted vertically downward by a laser. The laser beam illuminates the earth surface and returns. The distance between each survey point and the laser is obtained. Multiple measurements are taken to obtain the three-dimensional coordinates of a large number of points on the earth surface in the settlement monitoring area. (2-2) Perform noise reduction and filtering on the collected raw point data to remove noise points and outliers; (2-3) Divide the processed point data into different categories, including ground points, building points, and vegetation points; (2-4) Extract ground points from the point data, use interpolation algorithm to generate a regular grid based on the elevation data of the ground points to obtain a digital elevation model, combine the classification results of the point data to identify and label building points and vegetation points in the area, and obtain the topographic information of the settlement monitoring area.

5. The knowledge graph-based early warning method for building ground settlement according to claim 4, characterized in that, The laser integrates a positioning system and an inertial measurement unit, which are used to acquire position and attitude information, respectively.

6. The knowledge graph-based early warning method for building ground settlement according to claim 1, characterized in that, Step (5) includes: When the settlement rate of a monitoring point exceeds the preset settlement rate, or when the total settlement of a monitoring point exceeds the preset maximum settlement, a warning for dangerous monitoring points will be issued. When the average settlement rate of a sub-region exceeds the preset settlement rate, or when the total settlement of a sub-region exceeds the preset maximum settlement, a warning of the danger zone is issued. The settlement rate, average settlement rate, hazard monitoring points, and hazard range are visualized.

7. The knowledge graph-based early warning method for building ground settlement according to claim 1, characterized in that, Step (6) includes: (6-1) Constructing a knowledge graph: The factors affecting the settlement rate are divided into natural factors and anthropogenic factors, and both natural and anthropogenic factors contain several secondary factors; (6-2) By fitting the relationship between each factor and the settlement rate using historical data, the preset weights of each factor are obtained; (6-3) Investigate the influencing factors of the settlement monitoring area, calculate the expected settlement rate according to the preset weights, and determine whether the actual settlement rate in the settlement monitoring area meets the expected settlement rate. If the expected results are met, the influencing factors obtained from the survey are considered to be actual factors. If it does not meet expectations, proceed with (6-4); (6-4) Calculate based on the current settlement rate obtained in step (5) and the influencing factors obtained from the survey. Arrange and combine the various influencing factors obtained from the survey to obtain the combination that is closest to the current settlement rate as the actual factor.

8. A knowledge graph-based building ground settlement early warning system, used to implement the method of claim 1; characterized in that, The system includes: A laser detection module is used to emit a laser to a settlement monitoring area. Multiple monitoring points in the settlement monitoring area are equipped with detectors. The detectors receive the laser signal and return the signal, acquire laser detection data, and calculate the settlement amount of each monitoring point. The laser mapping module is used to acquire laser mapping data of the settlement monitoring area and obtain the topographic information of the settlement monitoring area; The filtering module is used to compare the monitoring points in the settlement monitoring area with the topographic information of the monitoring area to see if there is any interference, and to filter out a set of laser detection data of the monitoring points that are not damaged by non-natural factors. The data analysis and visualization module is used to compare laser detection data from a set of monitoring points without any non-natural damage with a pre-set deviation to determine the authenticity of the settlement and the overall settlement of the sub-region; combining the settlement of each monitoring point and the overall settlement of the sub-region, it provides early warnings and visualizations based on settlement amount and settlement rate respectively. The knowledge graph module is used to determine whether the settlement rate of the settlement monitoring area meets expectations based on the knowledge graph, and to calculate the influencing factors that best match the current settlement rate.

Images