Urban ground collapse risk assessment method and device

Abstract

The invention relates to the field of geological risk analysis, in particular to an urban ground collapse risk assessment method and device. According to the method, the attribute grid table associated with the risk factors is formed by acquiring and preprocessing the multi-source urban geological environment data, information of geology, environment and the like from different sources is integrated, and the problems of single detection means and data fragmentation are solved. Secondly, calculating the information amount value of each risk factor based on the attribute grid table, determining a weight set, quantifying the risk influence degree in a data driving mode, and replacing subjective experience judgment; and then, a comprehensive risk value is obtained by summing the information amount values of the risk factors of the grids, so that the risk evolution caused by dynamic changes of the city can be reflected in time, and the evaluation timeliness is improved. And finally, dividing risk levels according to frequency distribution inflection points, and generating a visual risk partition map, thereby realizing visual presentation and unified management of risk results, and effectively integrating data and governance actions, thereby realizing dynamic and precise prevention and control of underground space risks.

Description

Technical Field

[0001] This invention relates to the field of geological risk analysis, specifically to a method and apparatus for assessing urban ground collapse risk. Background Technology

[0002] Urban ground collapse, as a typical "urban disease," has complex causes, is highly concealed, and is prone to sudden occurrence. Current prevention and control efforts are fragmented, and there is a lack of a unified platform to integrate data, knowledge, and actions from departments such as water resources, housing and construction, and planning. Risk assessments rely heavily on historical case statistics or expert experience, which are highly subjective and fail to reflect the dynamic changes caused by urban construction activities in a timely manner.

[0003] In existing technologies, single geophysical detection methods can only obtain "snapshot" results, which cannot reflect the dynamic development of cavities, and are costly and inefficient; pipeline endoscopic detection methods can only assess the condition of the pipeline itself, and cannot quantify the overall risk of its coupling with the external environment; historical data statistical methods ignore the dynamic changes in the city, and the assessment results are easily outdated. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and apparatus for assessing urban ground collapse risks, in order to solve the problems of limited detection methods and lack of dynamic monitoring capabilities, strong subjectivity and insufficient timeliness in risk assessment, fragmented data and governance actions from various departments, and difficulty in achieving dynamic prevention and control of underground space risks.

[0005] In a first aspect, embodiments of the present invention provide a method for assessing urban ground collapse risk, the method comprising:

[0006] Multi-source urban geological environment data is acquired and preprocessed to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events. Based on the key assessment data in the attribute grid table, the information content value of each risk factor is calculated to obtain a set of factor weights that reflect the risk pattern. The information values ​​of all risk factors within each grid are algebraically summed to obtain the comprehensive risk value for each grid. Statistical analysis is performed on the comprehensive risk values ​​of all grids, and risk levels are classified based on the inflection points of the frequency distribution curves to generate a visualized risk zoning map.

[0007] Furthermore, the urban geological environment data is preprocessed to obtain an attribute grid table of associated risk factors, including: Spatial registration is performed on the urban geological environment data corresponding to each data source to obtain a spatially aligned multi-source dataset. Based on the multi-source dataset, the study area is divided into regular grids, and the data in the multi-source dataset are associated with the corresponding grids to obtain the initial grid dataset with associated original attributes; The qualitative data in each grid of the initial grid dataset is numerically encoded, and the quantitative data is divided into hierarchical intervals to obtain the target grid dataset. Each grid contains qualitative and quantitative data corresponding to its spatial characteristics. The qualitative data is used to represent the categorical geological environment and engineering characteristics of the grid, and the quantitative data is used to represent the numerical surface deformation, pipeline network and engineering parameters of the grid. For each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table of associated risk factors.

[0008] Furthermore, for each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table of associated risk factors, including: Based on the target grid dataset, qualitative and quantitative data for each grid are extracted to obtain the feature data corresponding to each grid. The feature data is mapped to the corresponding ground collapse risk factors to obtain a mapped dataset; Based on the mapping dataset, the historical collapse label information corresponding to each grid is associated to obtain the fused dataset; Based on the fused dataset, the structured data is organized to obtain an attribute grid table of associated risk factors.

[0009] Furthermore, based on the key assessment data in the attribute grid table, the information content value of each risk factor is calculated to obtain a factor weight set reflecting the risk pattern, including: By filtering the risk factors and collapse labels for each grid in the current time period from the attribute grid table, key assessment data is obtained; Based on the key assessment data, the number of collapsed grids, the total grid area, the overall number of collapsed grids in the region, and the total area of ​​the region corresponding to each risk factor are statistically analyzed to obtain factor probability statistics. Calculate the information content value of each risk factor based on the aforementioned factor probability statistics; The weight of each grid is determined based on the information content value of each risk factor, and a set of factor weights reflecting the risk pattern is constructed based on the weight of each grid.

[0010] Furthermore, statistical analysis is performed on the comprehensive risk values ​​of all grids, and risk levels are classified based on the inflection points of the frequency distribution curves to generate a visualized risk zoning map, including: The overall risk value of all grids is obtained and statistically analyzed to obtain the frequency distribution data of the overall risk value; Based on the frequency distribution data of the comprehensive risk value, a frequency distribution curve is plotted and the inflection point of the curve is identified to obtain the boundary point of the risk level. Based on the risk level boundary points, the comprehensive risk value of each grid is classified into different levels to obtain a grid-risk level mapping table; Based on the grid-risk level mapping table and the spatial information of the study area, spatial visualization rendering is performed to obtain the risk zoning map.

[0011] Furthermore, the method also includes: Monitor whether the current data update or timed trigger conditions are met; If the data update or timed trigger conditions are met, the newly added data of various types is acquired and preprocessed to obtain the updated attribute grid table. Based on the updated attribute grid table, the comprehensive risk value of all grids is calculated and the latest risk zoning map is generated. The latest risk zoning map is then compared with the risk zoning map to obtain the risk assessment results. Based on the risk assessment results, target areas with increased risk levels are identified, a risk trend early warning report is obtained, and corresponding early warning information is pushed out based on the risk trend early warning report.

[0012] Furthermore, the method also includes: Based on the risk zoning map, match the prevention and control strategy entries corresponding to the risk level in the knowledge base; Based on the aforementioned prevention and control strategy items, corresponding monitoring, engineering, and management measures are matched in batches according to the risk level of each grid to obtain a differentiated prevention and control strategy list for each grid. Integrate the list of differentiated prevention and control strategies from all grids to generate a report recommending differentiated prevention and control strategies.

[0013] Secondly, embodiments of the present invention provide an urban ground collapse risk assessment device, the device comprising: The acquisition module is used to acquire multi-source urban geological environment data and preprocess the urban geological environment data to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events. The calculation module is used to calculate the information content value of each risk factor based on the key assessment data in the attribute grid table, and obtain the factor weight set that reflects the risk pattern. The processing module is used to algebraically sum the information values ​​of all risk factors in each grid to obtain the comprehensive risk value of each grid. The statistics module is used to perform statistical analysis on the comprehensive risk value of all grids, classify risk levels based on the inflection points of the frequency distribution curves, and generate a visual risk zoning map.

[0014] Thirdly, embodiments of the present invention provide a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that cause a computer to perform the method described in the first aspect or any of its corresponding embodiments.

[0016] This application acquires and preprocesses multi-source urban geological and environmental data to form an attribute grid table of associated risk factors, integrating geological and environmental information from different sources and solving the problems of single detection methods and fragmented data. Secondly, based on the attribute grid table, the information content value of each risk factor is calculated and a weight set is determined, quantifying the degree of risk impact in a data-driven manner to replace subjective experience-based judgment. Then, by summing the information content values ​​of risk factors in each grid, a comprehensive risk value is obtained, which can promptly reflect the risk evolution brought about by dynamic urban changes and improve the timeliness of assessment. Finally, risk levels are divided according to the inflection points of frequency distribution, and a visual risk zoning map is generated, enabling intuitive presentation and unified management of risk results, effectively integrating data and governance actions, thereby achieving dynamic and precise prevention and control of underground space risks. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for assessing urban ground collapse risk according to some embodiments of the present invention; Figure 2 This is a flowchart illustrating a method for assessing urban ground collapse risk according to some embodiments of the present invention; Figure 3 This is a flowchart illustrating a method for assessing urban ground collapse risk according to some embodiments of the present invention; Figure 4 This is a structural block diagram of an urban ground collapse risk assessment device according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] According to an embodiment of the present invention, an example of a method and apparatus for assessing urban ground collapse risk is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0021] This embodiment provides a method for assessing urban ground collapse risk. Figure 1 This is a flowchart of a method for assessing urban ground collapse risk according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain multi-source urban geological environment data and preprocess the urban geological environment data to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events.

[0022] In this embodiment, the process of acquiring multi-source urban geological environment data involves systematically collecting multi-dimensional information related to ground collapse risk from various authoritative channels. First, digital elevation models (DEMs) and geological maps are obtained from natural resources or surveying departments to extract basic geographical features such as topographic relief and soil layer types (e.g., reclaimed areas, first-level terraces). Simultaneously, GIS data of water supply and drainage networks is obtained from water utilities, comprehensively collecting key network attributes such as pipe material, diameter, construction year, and burial depth. Subsequently, coordination with housing and construction, transportation, and subway departments is undertaken to collect engineering construction data such as coordinates, construction scope, and timelines for foundation pits, tunnels, pipe jacking, and municipal excavation projects. Satellite radar images are processed using PS-InSAR technology to generate deformation data on large-scale surface subsidence rates and cumulative subsidence. Finally, historical collapse events recorded by urban emergency or geological departments are compiled, extracting information such as location, time, scale, and preliminary cause assessment, thus forming a multi-source data set covering natural geography, underground facilities, engineering activities, surface deformation, and historical disasters.

[0023] In this embodiment of the application, urban geological environment data is preprocessed to obtain an attribute grid table of associated risk factors, including: Step A1 involves spatially registering the urban geological environment data corresponding to each data source to obtain a spatially aligned multi-source dataset.

[0024] First, the original coordinate systems of multi-source data, including physical geography, underground pipe networks, engineering construction, surface deformation, and historical collapses, were analyzed, and a unified spatial benchmark (such as WGS84UTMZone49N) was selected as the registration target. Coordinate transformations were performed on vector and raster data of different formats, and georeferencing tools were used to unify the spatial coordinates of satellite imagery, GIS pipe network layers, geological maps, and other data under this benchmark, eliminating spatial offsets caused by projection and benchmark differences between different data sources. Finally, a multi-source dataset with all data precisely aligned in space was obtained, ensuring spatial consistency for subsequent grid association and overlay analysis.

[0025] Step A2: Based on the multi-source dataset, the study area is divided into regular grids, and the data in the multi-source dataset are associated with the corresponding grids to obtain the initial grid dataset with associated original attributes.

[0026] Based on spatially aligned multi-source datasets, and considering the study area's scope and assessment accuracy requirements, a regular grid size (e.g., 50m × 50m) is set. A spatial gridding tool is used to divide the entire study area into continuous, non-overlapping grid cells. Spatial overlay analysis is performed on vector features (e.g., pipeline network, project scope) and raster features (e.g., DEM, settlement rate) from the multi-source datasets, associating the original attributes of each feature (e.g., pipe type, project time, settlement value) with the grid cells it spatially covers. Finally, an initial grid dataset is generated, with each grid cell carrying its corresponding original attributes, providing the basic units for subsequent attribute standardization.

[0027] Step A3 involves numerically encoding the qualitative data in each grid of the initial grid dataset and dividing the quantitative data into hierarchical intervals to obtain the target grid dataset. Each grid contains qualitative and quantitative data corresponding to its spatial characteristics. The qualitative data is used to represent the categorical geological environment and engineering characteristics of the grid, while the quantitative data is used to represent the numerical surface deformation, pipeline network, and engineering parameters of the grid.

[0028] For the initial grid dataset, qualitative attributes (such as geological type and pipe material) are numerically encoded, assigning a unique numerical identifier to each attribute category (e.g., reclamation area = 1, cast iron pipe = 2), transforming textual categorical data into a computable numerical format. For quantitative attributes (such as settlement rate and pipeline burial depth), grading intervals are defined based on statistical distribution or operational experience (e.g., settlement rate < -10 mm / year, -10~0 mm / year, etc.), converting continuous values ​​into discrete levels. The final target grid dataset is obtained, where each grid contains both encoded qualitative features and graded quantitative parameters, providing standardized input for risk factor mapping.

[0029] Step A4: For each grid in the target grid dataset, integrate the corresponding risk factors and collapse label information to obtain the attribute grid table of associated risk factors.

[0030] Specifically, for each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table of associated risk factors. This includes: extracting qualitative and quantitative data for each grid based on the target grid dataset to obtain feature data for each grid; mapping the feature data to the corresponding ground collapse risk factors to obtain a mapping dataset; associating the historical collapse label information corresponding to each grid with the mapping dataset to obtain a fused dataset; and organizing the structured data based on the fused dataset to obtain an attribute grid table of associated risk factors.

[0031] Based on the target grid dataset, the process first traverses each grid cell, separating qualitative and quantitative data from the standardized attribute fields. For qualitative data, categorical information with completed numerical coding is extracted, such as geological type coding and pipe material type coding. For quantitative data, discretized parameters with completed classification are extracted, such as settlement rate levels and pipeline burial depth ranges. This information is then aggregated by grid cell to ensure that each grid contains qualitative and quantitative information corresponding to its spatial characteristics, ultimately yielding the feature data for each grid.

[0032] For each grid's feature data, standardized qualitative and quantitative features are transformed into corresponding ground collapse risk factors according to pre-defined risk factor mapping rules. For example, "Geological type code = 1" is mapped to the risk factor "located in a reclamation area," "settlement rate level = 4" is mapped to the risk factor "settlement rate > 10 mm / year," and "whether in the construction buffer zone = yes" is mapped to the risk factor "within the engineering influence range." After completing the feature-to-risk factor transformation for all grids, a mapping dataset containing a list of risk factors corresponding to each grid is formed, realizing the transformation from basic attributes to risk-driving factors.

[0033] Based on the mapped dataset, the risk factor list for each grid is spatially correlated with historical collapse data. A label indicating whether a collapse has occurred is added to each grid, along with historical event attributes such as the number of collapses and their scale, forming a fused dataset that integrates risk factors and collapse labels. The fused dataset is then structured, constructing a two-dimensional table with grids as rows and risk factors and collapse labels as columns. Each row represents a grid cell, and each column corresponds to a risk factor or collapse label, ultimately generating an attribute grid table associated with risk factors.

[0034] Step S102: Calculate the information content value of each risk factor based on the key assessment data in the attribute grid table to obtain the factor weight set that reflects the risk pattern.

[0035] In this embodiment of the application, the information content value of each risk factor is calculated based on the key assessment data in the attribute grid table to obtain a factor weight set reflecting the risk pattern, including: Step B1: Filter the risk factors and collapse labels for each grid in the current time period from the attribute grid table to obtain key assessment data.

[0036] First, the generated attribute grid table is filtered according to a preset current time period (e.g., the past 3 years). All risk factors corresponding to each grid within this time range, as well as the "whether a collapse has occurred" label information, are extracted. This process filters out historical data that exceeds the time range, retaining only recent data that meets the requirements of dynamic calculation. Ultimately, this yields key assessment data for information content calculation, ensuring that subsequent probability statistics reflect the latest risk patterns.

[0037] Step B2: Based on the key assessment data, statistically analyze the number of collapsed grids, the total grid area, the overall number of collapsed grids in the region, and the total area of ​​the region corresponding to each risk factor to obtain factor probability statistics.

[0038] Based on key assessment data, for each risk factor, the number of grids that recently met the criteria for that factor and collapsed, as well as the total area of ​​all grids that met the criteria for that factor, are counted. Simultaneously, the total number of grids that recently collapsed and the total area of ​​the entire study area are also counted. For example, for the factor "pipe material is cast iron," the number of all grids containing cast iron pipes that collapsed, as well as the total area of ​​all grids containing cast iron pipes, are counted. These statistical results are then compiled into structured factor probability statistics.

[0039] Step B3: Calculate the information content value of each risk factor based on the factor probability statistics.

[0040] Based on factor probability statistics, conditional probability and prior probability are calculated for each risk factor. The conditional probability is the ratio of the number of collapsed grids under that factor to the total area of ​​the grids covered by that factor, while the prior probability is the ratio of the total number of collapsed grids within the region to the total area of ​​the region. Substituting both into the information content formula and taking the natural logarithm of the ratio of conditional probability to prior probability, the information content value of the factor is obtained. If the information content value is greater than 0, it indicates that the factor is a risk-promoting factor; less than 0, it is a risk-inhibiting factor; and equal to 0, it is irrelevant to risk.

[0041] Step B4: Determine the corresponding weight of each grid based on the information content value of each risk factor, and construct a factor weight set that reflects the risk pattern based on the weight of each grid.

[0042] The information content values ​​of each risk factor are directly used as their corresponding weights, as the sign and magnitude of the information content value already reflect the direction and intensity of the factor's impact on collapse risk. Subsequently, for each grid, the information content values ​​of all risk factors within it are used as the factor weights for that grid. Integrating the weight information of all grids constructs a factor weight set reflecting the current risk patterns. This weight set supports dynamic updates; when new data is input, the information content values ​​can be recalculated to update the weights, thereby continuously optimizing the accuracy of risk assessment.

[0043] Understandable, for a certain factor (For example, the classification of "distance from the foundation pit is 0-100m") contains a large amount of information. The calculation formula is:

[0044] :factor The information content value. >0 indicates that the factor is a risk-enhancing factor; <0 indicates that the factor is a risk-inhibiting factor; =0 indicates that the factor is not related to risk.

[0045] : In factor Under the conditions that the ground collapse event occurs The conditional probability of occurrence.

[0046] Ground collapse events throughout the study area The prior probability of occurrence.

[0047] In the near term (e.g., 2019-2021), all factors that meet the requirements... The number of grids in the grid where ground collapse occurred.

[0048] All factors satisfying the study area The total area of ​​the grid.

[0049] The number of all grids in the entire study area where ground collapse occurred in the near future.

[0050] : The total area of ​​the entire study area.

[0051] Every certain period (such as every quarter or every year), use new ,S, , The data was recalculated for all factors. This enables dynamic updating of model weights.

[0052] Step S103: The information values ​​of all risk factors in each grid are summed algebraically to obtain the comprehensive risk value of each grid.

[0053] In this embodiment of the application, within each evaluation grid, the overall risk value R is the algebraic sum of the information content of all factors within that grid:

[0054] R is the overall risk value of this grid; a higher value indicates a higher risk. n is the total number of risk factors that affect this grid. Let be the information content value of the i-th factor within this grid.

[0055] As an example, grid J contains four high-risk factors, and its combined risk value R = 0.23 + 0.29 + 0.24 + 0.49 = 1.25.

[0056] Step S104: Perform statistical analysis on the comprehensive risk value of all grids, classify the risk level based on the inflection point of the frequency distribution curve, and generate a visualized risk zoning map.

[0057] In this embodiment of the application, statistical analysis is performed on the comprehensive risk value of all grids, and risk levels are classified according to the inflection points of the frequency distribution curves to generate a visualized risk zoning map, including: Step C1: Obtain the comprehensive risk value of all grids and perform statistical analysis to obtain the frequency distribution data of the comprehensive risk value.

[0058] First, the comprehensive risk value assessment results table for all grids is read, and the comprehensive risk values ​​R of all grids are extracted to form a one-dimensional numerical sequence. Statistical analysis is performed on this sequence, grouping the comprehensive risk values ​​according to a certain interval width, counting the number of grids falling into each interval and their corresponding frequencies, and calculating the frequency density or frequency distribution for each interval to form a complete frequency distribution table. By calculating the maximum, minimum, mean, median, and standard deviation of the comprehensive risk values, the overall distribution characteristics of the risk values ​​are comprehensively understood, ultimately obtaining the frequency distribution data of the comprehensive risk values. This provides basic data support for subsequent frequency distribution curve plotting and determination of level boundary points.

[0059] Step C2: Based on the frequency distribution data of the comprehensive risk value, plot the frequency distribution curve and identify the inflection point of the curve to obtain the boundary point of the risk level.

[0060] Based on the frequency distribution data of the comprehensive risk value, a frequency distribution curve is plotted with the comprehensive risk value on the horizontal axis and frequency or frequency density on the vertical axis, visually presenting the distribution pattern of the risk value. By observing the changing trend of the curve, the inflection points where the slope of the curve changes significantly are identified. These inflection points correspond to the natural dividing points of the comprehensive risk value distribution and can objectively reflect the abrupt changes in the risk level.

[0061] By combining the geological conditions, intensity of engineering activities and historical collapse patterns of the study area, the rationality of the identified inflection points was verified and fine-tuned, and the boundary thresholds that can distinguish different risk levels were determined. Finally, the boundary points used to classify risk levels were obtained, providing a clear basis for subsequent grid risk level classification.

[0062] Step C3: Based on the risk level boundary, classify the comprehensive risk value of each grid into a grid-risk level mapping table.

[0063] Based on the obtained risk level boundary points, risk level classification rules are established, mapping the comprehensive risk value range to four risk levels: extremely high, high, medium, and low. The comprehensive risk values ​​of all grids are iterated, and the risk level of each grid is determined according to the classification rules. The grid number is then matched with the corresponding risk level.

[0064] The classification results are checked for consistency to ensure that each grid belongs to only one risk level and that there are no omissions or misclassifications. Finally, a grid-risk level mapping table is formed, which includes grid number, comprehensive risk value and corresponding risk level, providing attribute basis for spatial visualization rendering.

[0065] Step C4: Based on the grid-risk level mapping table and the spatial information of the study area, perform spatial visualization rendering to obtain a risk zoning map.

[0066] Based on the grid-risk level mapping table and the spatial coordinate information of the study area, risk level attributes are associated with grid spatial locations to construct a spatial visualization data layer. Different visualization styles such as colors, symbols, or transparency are configured for different risk levels, making the differences in risk levels intuitively presented in space.

[0067] By using GIS spatial rendering tools, each grid is colored or symbolized according to its risk level, and background information such as the geographical base map, main roads, and water systems of the study area are overlaid to improve the readability and usability of the risk zoning map. The final result is a complete urban ground collapse risk zoning map, clearly showing the spatial distribution pattern of risks in different areas, providing an intuitive basis for the formulation of differentiated prevention and control strategies.

[0068] In the embodiments of this application, such as Figure 2 As shown, the method also includes: Step S201: Monitor whether the current data update or timed trigger conditions are met.

[0069] On the one hand, in response to the data update triggering conditions, the system continuously monitors the multi-source data access channels and monitors in real time whether it receives new InSAR surface subsidence data, new project commencement / completion filing information, new underground pipeline inspection reports (including inspection results such as pipe aging and damage), and new ground collapse event records (including detailed information such as location, scale, and cause). Each time a new type of data is received, it is automatically marked as a data update trigger signal.

[0070] On the other hand, for timed triggering conditions, the system presets a fixed update cycle of quarterly or semi-annual, and monitors the countdown using a built-in timer. When the preset time node is reached, a timed trigger signal is automatically generated. At the same time, the system will verify the validity of the trigger signal, eliminating interference factors such as duplicate data and invalid data, and finally determine whether any triggering condition is met.

[0071] In step S202, if the data update or timed trigger conditions are met, the newly added data of various types is acquired and preprocessed to obtain the updated attribute grid table.

[0072] Once the triggering conditions are met, the data update and preprocessing process begins. First, according to the preset data access protocol, various newly added urban geological environment data are acquired in batches, including but not limited to new InSAR settlement rate and cumulative settlement data, coordinate range and time information of newly added projects, updated attribute data of pipeline network detection, and complete records of newly occurred collapse events. The acquired new data is then subjected to integrity verification and format standardization processing, and data with missing key information or incorrect format is removed.

[0073] Subsequently, following the preprocessing specifications described above, spatial registration (unifying to a unified coordinate system), gridding (associating with a 50m×50m regular grid), and attribute standardization (qualitative data numerical encoding, quantitative data hierarchical interval division) were performed on the new data. Simultaneously, the new data was merged with historical data in the existing attribute grid table, updating the risk factor information corresponding to each grid. Finally, through spatial association and data verification, the completeness and accuracy of attribute information in all grids were ensured, ultimately generating an updated attribute grid table.

[0074] Step S203: Based on the updated attribute grid table, calculate the comprehensive risk value of all grids and generate the latest risk zoning map. Compare the latest risk zoning map with the previous risk zoning map to obtain the risk assessment results.

[0075] First, the dynamic information content method is used to extract the risk factor information of each grid in the attribute grid table. The key parameters such as the number of collapsed grids, the total grid area, the number of collapsed grids in the region, and the total area of ​​the region corresponding to each risk factor are statistically analyzed in the recent period. These parameters are then substituted into the information content calculation formula to calculate the information content value (i.e., weight) of each risk factor. Finally, the information content values ​​of all risk factors in each grid are algebraically summed to obtain the latest comprehensive risk value of all grids.

[0076] Subsequently, statistical analysis was performed on the latest comprehensive risk values, frequency distribution curves were plotted, inflection points were identified to determine risk level boundaries, and each grid was classified into extremely high, high, medium, and low risk levels. Combined with spatial information of the study area, visualization rendering was completed to generate the latest risk zoning map.

[0077] Finally, the historical risk zoning map (the result generated in the last update) is used, and methods such as spatial overlay analysis and risk level change comparison are employed to compare the differences between the latest risk level and the historical risk level grid by grid. Grid areas where the risk level has increased, decreased, or remained unchanged are marked, and the spatial distribution characteristics and overall trend of risk level changes are sorted out. Finally, a risk assessment result containing the latest risk zoning map, historical comparative analysis, and risk change statistics is generated.

[0078] Step S204: Based on the risk assessment results, determine the target areas where the risk level is rising, obtain a risk trend warning report, and push out corresponding warning information based on the risk trend warning report.

[0079] First, from the obtained risk assessment results, grid areas with significantly increased risk levels are selected, and the scope of the target area (such as specific grid number and geographical boundaries), the changes in risk level (such as jumping from medium risk to extremely high risk), and the key risk factors involved (such as sudden increase in settlement rate, impact of new engineering construction, etc.) are clearly defined. At the same time, combined with historical collapse data, regional geological conditions and other information, the potential causes of the increased risk level are preliminarily analyzed.

[0080] Subsequently, the information of the target area was organized in a structured manner, and a risk trend early warning report was compiled. The report clearly defines the basic information of the target area, details of risk changes, potential risks and hidden dangers, and key investigation recommendations.

[0081] Finally, based on the preset early warning push rules, the system matches the local management departments, industry authorities (such as housing and construction, transportation, water affairs, etc.) and relevant responsible units corresponding to the target area. Through various means such as system messages, SMS, and email, the system pushes the risk trend early warning report and targeted early warning prompts to the corresponding units, prompting them to pay close attention to the target area, conduct special investigations, and take timely prevention and control measures to prevent ground collapse incidents, thus forming a closed-loop early warning mechanism of "identification-reporting-push-handling".

[0082] In the embodiments of this application, such as Figure 3 As shown, the method also includes: Step S301: Match prevention and control strategy entries corresponding to the risk level in the knowledge base based on the risk zoning map.

[0083] First, the system reads the final generated risk zoning map, analyzes the risk level (extremely high, high, medium, low) corresponding to each grid, and establishes a mapping relationship between grids and risk levels. Then, the system calls upon its built-in prevention and control strategy knowledge base, which has pre-organized and stored standardized prevention and control strategy entries corresponding one-to-one with each risk level, covering multiple dimensions such as monitoring and detection, engineering management, and management control. The system uses risk level as a correlation keyword to accurately match the risk level of each grid in the risk zoning map with entries in the knowledge base: for example, when a grid is identified as belonging to an extremely high-risk area, it automatically matches monitoring entries such as "high-frequency quarterly ground-penetrating radar scanning, annual pipeline endoscopic inspection"; engineering entries such as "priority renovation, engineering-linked third-party monitoring"; and management entries such as "daily manual inspection, development of emergency plans"; for medium and low-risk areas, it matches corresponding lower-frequency monitoring, maintenance-oriented engineering measures, and routine inspection management measures. During the matching process, the system will verify the matching results to ensure that each risk level can be associated with a complete prevention and control strategy item, avoiding omissions or mismatches. In the end, a dataset of associations between risk levels and prevention and control strategy items will be formed, providing a basis for the subsequent generation of grid-level differentiated strategies.

[0084] Step S302: Based on the prevention and control strategy items, batch match the corresponding monitoring, engineering and management measures according to the risk level of the grid to obtain a differentiated prevention and control strategy list for each grid.

[0085] First, traverse all grids in the risk zoning map, using each grid as a basic unit, and extract the corresponding monitoring, engineering, and management measures from the associated dataset based on its risk level.

[0086] For example, for grids in extremely high-risk areas, the monitoring measures include "high frequency: quarterly ground-penetrating radar scanning; key areas: annual pipeline endoscopic inspection (CCTV); real-time access to foundation pit monitoring data", the engineering measures include "priority renovation: inclusion in the pipeline network renovation priority plan; engineering coordination: strict requirements for third-party monitoring of surrounding projects", and the management measures include "key inspection: daily manual inspection; emergency plan: development of detailed emergency response plans". For grids in high-risk areas, the following monitoring measures are extracted: "Medium frequency: semi-annual ground-penetrating radar scanning; routine: pipeline inspection according to plan"; "Timely modification: arrange treatment according to the detection results; enhanced protection: put forward higher protection requirements for construction activities"; and "Enhanced inspection: weekly manual inspection".

[0087] During the batch matching process, an independent set of strategy entries is generated for each grid to ensure that the prevention and control strategy of each grid accurately corresponds to its risk level. At the same time, the spatial identification information of the grid is retained, and finally a differentiated prevention and control strategy list is formed, which includes grid number, risk level and corresponding monitoring, engineering and management measures, so as to realize the implementation of specific measures from risk level to grid level.

[0088] Step S303: Integrate the list of differentiated prevention and control strategies for all grids and generate a report recommending differentiated prevention and control strategies.

[0089] First, the list of differentiated prevention and control strategies for all grids was structured and integrated. The grids were then classified and grouped according to risk level, and the distribution range, number proportion and overall spatial characteristics of the grids corresponding to the four risk levels of extremely high, high, medium and low were sorted out.

[0090] Subsequently, for each risk level, the monitoring, engineering, and management measures of all grids under that level are integrated to form a comprehensive prevention and control strategy framework based on different levels. For example, in the extremely high-risk area, the high-frequency monitoring requirements, priority engineering measures, and key management measures for the area are summarized, and priority recommendations for strategy implementation are supplemented by background information such as regional geological conditions, pipeline distribution, and engineering activities. In the medium- and low-risk areas, measures such as low-frequency investigation, hidden danger management, and routine inspections are integrated to clarify the key directions for daily maintenance.

[0091] Simultaneously, common strategies across regions and risk levels will be extracted, and conflicting or overlapping measures will be optimized and adjusted to ensure the consistency and feasibility of the report content. Finally, the system will format the integrated content according to modules such as "risk level distribution, risk level prevention and control strategies, implementation suggestions, and matching of responsible parties," adding auxiliary content such as spatial location diagrams and measure frequency comparison tables, ultimately generating a differentiated prevention and control strategy recommendation report.

[0092] This embodiment also provides an urban ground collapse risk assessment device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] This embodiment provides a device for assessing the risk of urban ground collapse, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire multi-source urban geological environment data and preprocess the urban geological environment data to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events. The calculation module 402 is used to calculate the information value of each risk factor based on the key assessment data in the attribute grid table, and obtain the factor weight set that reflects the risk pattern. Processing module 403 is used to algebraically sum the information values ​​of all risk factors in each grid to obtain the comprehensive risk value of each grid. The statistics module 404 is used to perform statistical analysis on the comprehensive risk value of all grids, classify risk levels based on the inflection point of the frequency distribution curve, and generate a visual risk zoning map.

[0094] In this embodiment, the acquisition module 401 is used to spatially register the urban geological environment data corresponding to each data source to obtain a spatially aligned multi-source dataset. Based on the multi-source dataset, the study area is divided into regular grids, and the data in the multi-source dataset is associated with the corresponding grids to obtain an initial grid dataset with associated original attributes. The qualitative data in each grid of the initial grid dataset is numerically encoded, and the quantitative data is hierarchically divided into intervals to obtain a target grid dataset. Each grid contains qualitative and quantitative data corresponding to its spatial characteristics. The qualitative data is used to represent the categorical geological environment and engineering characteristics of the grid, and the quantitative data is used to represent the numerical surface deformation, pipeline network, and engineering parameters of the grid. For each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table with associated risk factors.

[0095] In this embodiment of the application, the acquisition module 401 is used to extract qualitative and quantitative data of each grid based on the target grid dataset to obtain feature data corresponding to each grid; map the feature data to the corresponding ground collapse risk factors to obtain a mapping dataset; associate the historical collapse label information corresponding to each grid based on the mapping dataset to obtain a fused dataset; and organize the structured data based on the fused dataset to obtain an attribute grid table of associated risk factors.

[0096] In this embodiment, the calculation module 402 is used to filter the risk factors and collapse labels of each grid in the current time period from the attribute grid table to obtain key assessment data; based on the key assessment data, it calculates the number of grids containing collapse, the total grid area, the total number of collapse grids in the region, and the total area of ​​the region corresponding to each risk factor to obtain factor probability statistics; it calculates the information value of each risk factor based on the factor probability statistics; it determines the corresponding weight of each grid based on the information value corresponding to each risk factor; and it constructs a factor weight set reflecting the risk pattern based on the weight of each grid.

[0097] In this embodiment of the application, the statistics module 404 is used to obtain the comprehensive risk value of all grids and perform statistics to obtain the frequency distribution data of the comprehensive risk value; based on the frequency distribution data of the comprehensive risk value, a frequency distribution curve is plotted and the inflection point of the curve is identified to obtain the boundary point of the risk level; according to the boundary point of the risk level, the comprehensive risk value of each grid is classified into levels to obtain a grid-risk level mapping table; based on the grid-risk level mapping table and the spatial information of the study area, spatial visualization rendering is performed to obtain a risk zoning map.

[0098] In this embodiment, the device further includes: a monitoring module, used to monitor whether the current data update or timed triggering conditions are met; if the data update or timed triggering conditions are met, the newly added data of various types is acquired and preprocessed to obtain an updated attribute grid table; based on the updated attribute grid table, the comprehensive risk value of all grids is calculated and a latest risk zoning map is generated, and the latest risk zoning map is compared with the risk zoning map to obtain risk assessment results; based on the risk assessment results, the target area with the increased risk level is determined, a risk trend warning report is obtained, and corresponding warning information is pushed based on the risk trend warning report.

[0099] In this embodiment of the application, the device further includes: a generation module, used to match prevention and control strategy entries corresponding to risk levels in the knowledge base based on the risk zoning map; to batch match corresponding monitoring, engineering and management measures according to the risk level of the grid based on the prevention and control strategy entries, so as to obtain a differentiated prevention and control strategy list for each grid; and to integrate the differentiated prevention and control strategy lists of all grids to generate a differentiated prevention and control strategy recommendation report.

[0100] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0101] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0102] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0103] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0104] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0105] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0106] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0107] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for assessing urban ground collapse risk, characterized in that, The method includes: Multi-source urban geological environment data is acquired and preprocessed to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events. Based on the key assessment data in the attribute grid table, the information content value of each risk factor is calculated to obtain a set of factor weights that reflect the risk pattern. The information values ​​of all risk factors within each grid are algebraically summed to obtain the comprehensive risk value for each grid. Statistical analysis is performed on the comprehensive risk values ​​of all grids, and risk levels are classified based on the inflection points of the frequency distribution curves to generate a visualized risk zoning map.

2. The method according to claim 1, characterized in that, The urban geological environment data is preprocessed to obtain an attribute grid table of associated risk factors, including: Spatial registration is performed on the urban geological environment data corresponding to each data source to obtain a spatially aligned multi-source dataset. Based on the multi-source dataset, the study area is divided into regular grids, and the data in the multi-source dataset are associated with the corresponding grids to obtain the initial grid dataset with associated original attributes; The qualitative data in each grid of the initial grid dataset is numerically encoded, and the quantitative data is divided into hierarchical intervals to obtain the target grid dataset. Each grid contains qualitative and quantitative data corresponding to its spatial characteristics. The qualitative data is used to represent the categorical geological environment and engineering characteristics of the grid, and the quantitative data is used to represent the numerical surface deformation, pipeline network and engineering parameters of the grid. For each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table of associated risk factors.

3. The method according to claim 2, characterized in that, For each grid in the target grid dataset, the corresponding risk factors and collapse label information are integrated to obtain an attribute grid table associated with the risk factors, including: Based on the target grid dataset, qualitative and quantitative data for each grid are extracted to obtain the feature data corresponding to each grid. The feature data is mapped to the corresponding ground collapse risk factors to obtain a mapped dataset; Based on the mapping dataset, the historical collapse label information corresponding to each grid is associated to obtain the fused dataset; Based on the fused dataset, the structured data is organized to obtain an attribute grid table of associated risk factors.

4. The method according to claim 1, characterized in that, Based on the key assessment data in the attribute grid table, the information content value of each risk factor is calculated to obtain a set of factor weights reflecting the risk patterns, including: By filtering the risk factors and collapse labels for each grid in the current time period from the attribute grid table, key assessment data is obtained; Based on the key assessment data, the number of collapsed grids, the total grid area, the overall number of collapsed grids in the region, and the total area of ​​the region corresponding to each risk factor are statistically analyzed to obtain factor probability statistics. Calculate the information content value of each risk factor based on the aforementioned factor probability statistics; The weight of each grid is determined based on the information content value of each risk factor, and a set of factor weights reflecting the risk pattern is constructed based on the weight of each grid.

5. The method according to claim 1, characterized in that, Statistical analysis is performed on the comprehensive risk values ​​of all grids. Risk levels are classified based on the inflection points of the frequency distribution curves, and a visual risk zoning map is generated, including: The overall risk value of all grids is obtained and statistically analyzed to obtain the frequency distribution data of the overall risk value; Based on the frequency distribution data of the comprehensive risk value, a frequency distribution curve is plotted and the inflection point of the curve is identified to obtain the boundary point of the risk level. Based on the risk level boundary points, the comprehensive risk value of each grid is classified into different levels to obtain a grid-risk level mapping table; Based on the grid-risk level mapping table and the spatial information of the study area, spatial visualization rendering is performed to obtain the risk zoning map.

6. The method according to claim 1, characterized in that, The method further includes: Monitor whether the current data update or timed trigger conditions are met; If the data update or timed trigger conditions are met, the newly added data of various types is acquired and preprocessed to obtain the updated attribute grid table. Based on the updated attribute grid table, the comprehensive risk value of all grids is calculated and the latest risk zoning map is generated. The latest risk zoning map is then compared with the risk zoning map to obtain the risk assessment results. Based on the risk assessment results, target areas with increased risk levels are identified, a risk trend early warning report is obtained, and corresponding early warning information is pushed out based on the risk trend early warning report.

7. The method according to claim 1, characterized in that, The method further includes: Based on the risk zoning map, match the prevention and control strategy entries corresponding to the risk level in the knowledge base; Based on the aforementioned prevention and control strategy items, corresponding monitoring, engineering, and management measures are matched in batches according to the risk level of each grid to obtain a differentiated prevention and control strategy list for each grid. Integrate the list of differentiated prevention and control strategies from all grids to generate a report recommending differentiated prevention and control strategies.

8. A device for assessing the risk of urban ground collapse, characterized in that, The device includes: The acquisition module is used to acquire multi-source urban geological environment data and preprocess the urban geological environment data to obtain an attribute grid table of associated risk factors. The attribute grid table has multiple grids, and the risk factors are used to characterize the degree of influence of the spatial characteristics of the corresponding grid on the probability of ground collapse events. The calculation module is used to calculate the information content value of each risk factor based on the key assessment data in the attribute grid table, and obtain the factor weight set that reflects the risk pattern. The processing module is used to algebraically sum the information values ​​of all risk factors in each grid to obtain the comprehensive risk value of each grid. The statistics module is used to perform statistical analysis on the comprehensive risk value of all grids, classify risk levels based on the inflection points of the frequency distribution curves, and generate a visual risk zoning map.

9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images