Slope potential sliding body automatic identification method, system and electronic device

Abstract

This application provides an automatic method, system, and electronic device for identifying potential landslides on slopes. The automatic identification method for potential landslides involves collecting coordinate data from monitoring points deployed on the slope surface at multiple monitoring times and generating displacement time-series data for each monitoring point. Based on the displacement time-series data, the motion correlation strength between any two monitoring points is calculated. Based on the motion correlation strength, all monitoring points are clustered into one or more cooperative motion groups, where each cooperative motion group corresponds to a potential landslide block on the slope. The stability of each potential landslide block is assessed to determine its landslide risk. This method achieves automatic identification of potential landslide blocks.

Description

Technical Field

[0001] This application relates to the field of engineering monitoring technology, specifically to an automatic identification method, system, and electronic equipment for potential landslides on slopes. Background Technology

[0002] my country's geological environment is complex and diverse. Especially under the influence of natural factors such as heavy rainfall and earthquakes, slope instability and landslides occur frequently, posing a significant risk to infrastructure safety and the safety of people's lives and property. As the interface between engineering construction and the natural geological environment, the stability of slopes directly determines the safe operation of the engineering structure itself and also poses a potential threat to the surrounding ecological environment, residential areas, and transportation routes. Therefore, conducting systematic, accurate, and timely slope safety monitoring is of paramount importance for disaster early warning, risk prevention and control, and scientific management.

[0003] In current slope safety monitoring practices, equipment such as total stations, GPS, and surveying robots are typically used to periodically measure monitoring points deployed on the slope surface to obtain displacement data over different time periods. This data is then used as the basis for slope stability analysis and assessment. Existing analysis and assessment methods mainly include displacement contour maps, statistical analysis, and manual judgment; however, these methods all have certain limitations. Summary of the Invention

[0004] To address the aforementioned issues, this application provides an automatic identification method, system, electronic device, computer-readable storage medium, and computer program product for potential landslides on slopes, which can effectively improve the engineering practicality and reliability of slope monitoring.

[0005] According to a first aspect of this application, an automatic identification method for potential landslides on slopes is provided. The method includes: collecting coordinate data of each monitoring point deployed on the slope surface at multiple monitoring times, and generating displacement time-series data of each monitoring point; calculating the motion correlation strength between any two monitoring points based on the displacement time-series data; clustering all monitoring points based on the motion correlation strength, dividing all monitoring points into one or more cooperative motion groups, wherein each cooperative motion group corresponds to a potential landslide block on the slope; and conducting a block stability assessment for each potential landslide block to determine the landslide risk of each potential landslide block.

[0006] In one implementation of the first aspect, coordinate data of each monitoring point deployed on the slope surface at multiple monitoring times are collected, and displacement time-series data of each monitoring point are generated, including: acquiring the three-dimensional coordinates of each monitoring point at each monitoring time at multiple monitoring times; calculating the displacement of each monitoring point relative to a reference time at each monitoring time based on the three-dimensional coordinates; and calculating the time-series motion data of each monitoring point based on the displacement, wherein the time-series motion data is a displacement time series and / or a velocity time series.

[0007] In one implementation of the first aspect, the motion correlation strength between any two monitoring points is calculated based on displacement time series data, including: calculating the similarity measure between the displacement time series data corresponding to any two monitoring points based on displacement time series data, and using it as the motion correlation strength between any two monitoring points, wherein the motion correlation strength is at least one of Pearson correlation coefficient, Spearman rank correlation coefficient and dynamic time warping similarity.

[0008] In one implementation of the first aspect, all monitoring points are clustered based on the motion association strength to divide all monitoring points into one or more cooperative motion groups, including: constructing an association graph based on the motion association strength, wherein the nodes of the association graph are each monitoring point, and the weight of the connecting edge between any two nodes is the motion association strength between the two monitoring points corresponding to any two nodes; and performing community structure detection on the association graph to divide one or more communities, wherein each community is a cooperative motion group.

[0009] In one implementation of the first aspect, a correlation graph is constructed based on the motion correlation strength, including: obtaining a comprehensive correlation strength based on the motion correlation strength; and constructing a correlation graph based on the comprehensive correlation strength, wherein the nodes of the correlation graph are each monitoring point, and the weight of the connecting edge between any two nodes is the comprehensive correlation strength between the two monitoring points corresponding to any two nodes.

[0010] In one implementation of the first aspect, a correlation graph is constructed based on the motion correlation strength, including: when the motion correlation strength between two monitoring points is greater than or equal to a preset connection threshold, a connection edge is established between the corresponding two nodes in the correlation graph.

[0011] In one implementation of the first aspect, community structure detection is performed on the association graph to divide it into one or more communities, including: taking the association graph as input and using a community detection algorithm to perform automatic clustering to divide it into one or more communities.

[0012] In one implementation of the first aspect, a block stability assessment is performed on each potential sliding block to determine the sliding risk of each potential sliding block, including: calculating the block stability coefficient corresponding to each potential sliding block; if the block stability coefficient is less than a preset block stability coefficient threshold, the corresponding potential sliding block is determined to be a high-risk sliding block; otherwise, the corresponding potential sliding block is determined to be a low-risk sliding block.

[0013] According to the first aspect of this application, after clustering all monitoring points based on the motion association strength and dividing all monitoring points into one or more cooperative motion groups, before conducting block stability assessments on each potential sliding block to determine the sliding risk of each potential sliding block, the method further includes: for any cooperative motion group, if the number of monitoring points in the cooperative motion group is less than a preset minimum block size threshold, then the cooperative motion group is removed to perform minimum size filtering on each cooperative motion group.

[0014] According to the first aspect of this application, after clustering all monitoring points based on the intensity of motion association and dividing all monitoring points into one or more coordinated motion groups, and before conducting block stability assessments on each potential sliding block to determine the sliding risk of each potential sliding block, the method further includes: for any coordinated motion group, performing a spatial distribution continuity check on the coordinated motion group to obtain a check result, so as to confirm the spatial distribution of each monitoring point in the coordinated motion group on the slope; if the check result determines that the potential sliding block corresponding to the coordinated motion group is a spatially discontinuous block, then performing a split optimization operation on the coordinated motion group.

[0015] In one implementation of the first aspect, the spatial distribution continuity of the coordinated movement group is verified, including: calculating the spatial boundary of the coordinated movement group; counting the number of monitoring points located within the spatial boundary but not belonging to the coordinated movement group; if the ratio of the number to the total number of monitoring points within the spatial boundary exceeds a preset ratio threshold, then the potential sliding block corresponding to the coordinated movement group is determined to be a spatially discontinuous block; otherwise, the potential sliding block corresponding to the coordinated movement group is determined to be a spatially continuous block.

[0016] According to a second aspect of this application, an automatic identification system for potential landslides on slopes is provided. This system includes: a temporal motion data acquisition module for acquiring temporal motion data of each monitoring point on the slope surface at multiple consecutive monitoring times; a motion correlation strength measurement module for calculating and quantifying the motion correlation strength between any two monitoring points based on the temporal motion data; a potential landslide block identification module for clustering all monitoring points and classifying all monitoring points into one or more cooperative motion groups, wherein each cooperative motion group corresponds to a potential landslide block on the slope; and a block stability assessment module for performing block stability assessments on each potential landslide block to determine the landslide risk of each potential landslide block.

[0017] According to a third aspect of this application, an electronic device is provided, comprising a memory and a processor, the memory for storing a computer program, the processor for running the computer program to cause the electronic device to perform the automatic slope potential landslide identification method as provided in the first aspect of this application.

[0018] According to a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the automatic identification method for potential landslides on slopes as provided in the first aspect of this application.

[0019] According to a fifth aspect of this application, a computer program product is provided, the computer program product including instructions that, when executed by a processor of an electronic device provided in a third aspect of this application, enable the electronic device to implement the automatic identification method for potential landslides on slopes as provided in a first aspect of this application.

[0020] This application provides an automatic identification method, system, electronic device, computer-readable storage medium, and computer program product for potential landslides on slopes. The automatic identification method collects coordinate data of monitoring points deployed on the slope surface at multiple monitoring times and generates displacement time-series data for each monitoring point. Based on the displacement time-series data, it calculates the motion correlation strength between any two monitoring points. Based on the motion correlation strength, it clusters all monitoring points, classifying them into one or more cooperative motion groups, where each cooperative motion group corresponds to a potential landslide block on the slope. It then performs a stability assessment on each potential landslide block to determine its landslide risk. This method achieves automatic identification of potential landslide blocks, reducing analysis time from several days of manual judgment to minutes of computation. It also completely eliminates subjective bias caused by human error, ensuring the objectivity of the identification process and the repeatability of the results, thus providing high-quality input for accurate slope monitoring, risk assessment, and disaster prevention decision-making. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The diagram shown is a flowchart illustrating an automatic identification method for potential landslides on slopes according to an embodiment of this application.

[0023] Figure 2 The diagram shown is a flowchart illustrating a method for clustering all monitoring points according to an embodiment of this application.

[0024] Figure 3 The diagram shown is a flowchart illustrating a block stability assessment of a potential sliding block according to an embodiment of this application.

[0025] Figure 4 The diagram shown is a schematic diagram of an automatic identification system for potential landslides provided in an embodiment of this application.

[0026] Figure 5 The diagram shown is a block diagram of an exemplary electronic device provided in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0028] As mentioned earlier, existing methods for analyzing and assessing slope safety monitoring generally have certain limitations. Through in-depth analysis, the inventors have identified these limitations in the following aspects: While methods based on displacement contour maps can visually display the spatial distribution of displacement, they cannot identify potential sliding blocks with coordinated movement characteristics; statistical analysis methods, although able to identify local danger points through displacement thresholds, cannot identify the overall sliding trend. In other words, existing technologies are mostly limited to isolated analysis of single-point displacement data, lacking the ability to quantify and assess the consistency of movement sequence, morphology, and trend across different monitoring points, thus making it difficult to accurately define the scope and associated characteristics of potential sliding blocks. This results in the inability to effectively determine the degree of coordination of movement within potential sliding blocks, and also makes it difficult to distinguish between high-risk compacted sliding masses and low-risk loose areas, thereby hindering the scientific classification and precise management of slope risks.

[0029] Furthermore, relying on human experience to judge the coordinated movement of blocks usually requires engineers to visually compare a large number of displacement curves. This method is highly subjective, inefficient, and difficult to handle scenarios with a large number of monitoring points. On the other hand, clustering analysis methods based on pure mathematical similarity measures may incorrectly classify spatially discrete points into the same category, which violates the basic engineering common sense that sliding bodies should have spatial continuity in physics, resulting in low usability of the identification results in practical applications.

[0030] To address various problems encountered in existing technologies, this application provides an automatic method, system, electronic device, computer-readable storage medium, and computer program product for identifying potential landslides on slopes, enabling safety monitoring of slopes. The following will combine... Figures 1-3 This paper introduces an automatic method for identifying potential landslides on slopes.

[0031] Figure 1 The diagram shown is a flowchart illustrating an automatic method for identifying potential landslides on slopes, according to an embodiment of this application. Figure 1 As shown, the method includes the following steps: Step S110: Collect coordinate data of each monitoring point deployed on the slope surface at multiple monitoring times, and generate displacement time series data of each monitoring point.

[0032] In this context, a monitoring point refers to a physical location on the slope surface that needs to be monitored, where specialized measuring markers or sensors (such as GNSS receivers or total station prisms) have been pre-selected and deployed. Each monitoring point represents the spatial location of a small area on the slope surface. Numerous monitoring points form a spatial sampling network covering the entire slope to collectively reflect the overall deformation state of the slope.

[0033] It should be noted that the location and number of monitoring points can be designed according to actual engineering needs or according to industry standards; this application does not limit this.

[0034] In one embodiment of this application, step S110 may include the following steps: obtaining the three-dimensional coordinates of each monitoring point at each of the multiple monitoring times; calculating the displacement of each monitoring point relative to the reference time at each monitoring time based on the three-dimensional coordinates; and calculating the temporal motion data of each monitoring point based on the displacement.

[0035] Specifically, spatial coordinate acquisition equipment (e.g., total station, GNSS receiver, surveying robot, or 3D laser scanner) can be used to collect the 3D coordinates of each monitoring point deployed on the slope surface at multiple different monitoring times. For each monitoring point, using a certain monitoring time as a reference, the displacement of the point relative to that reference time at each subsequent monitoring time can be calculated. This displacement can be expressed in one or more forms (e.g., a displacement vector in 3D space or a sequence of 3D rectangular coordinate displacement components). Finally, for each monitoring point, its temporal motion data is calculated, where the temporal motion data is a displacement time series and / or a velocity time series.

[0036] Step S120: Based on displacement time series data, calculate the motion correlation strength between any two monitoring points among all monitoring points.

[0037] Among them, motion correlation strength is a quantitative indicator that measures the degree of similarity or synergy in displacement motion between different monitoring points on a slope. In this application, motion correlation strength specifically refers to the degree of statistical correlation or physical synergy exhibited by the displacement time series and / or velocity time series (including displacement, velocity, or acceleration) of two or more monitoring points in terms of changing trends, fluctuation patterns, and abrupt change sequences within a specific time period.

[0038] In one embodiment of this application, step S120 may include the following steps: based on displacement time series data, calculate the similarity metric between displacement time series data corresponding to any two monitoring points, and use it as the motion correlation strength between any two monitoring points.

[0039] Among them, the motion correlation strength is at least one of Pearson correlation coefficient, Spearman rank correlation coefficient and dynamic time warping (DTW) similarity.

[0040] Specifically, the Pearson correlation coefficient is used to measure the degree of linear correlation between two sequences in terms of magnitude and morphology; the Spearman rank correlation coefficient is used to assess the consistency of two sequences in terms of the order of change trends (monotonicity), and this coefficient is not sensitive to outliers; dynamic time warping similarity is used to measure the similarity of two displacement (or rate) time series in terms of overall morphology, and its advantage is that it can identify coordinated deformations that have a phase difference on the time axis (i.e., the deformation occurs at different times) but have the same evolution pattern.

[0041] It should be noted that the closer the absolute value of the Pearson correlation coefficient is to 1, the stronger the linear correlation between the two sequences involved in the calculation; the closer the value of the Spearman rank correlation coefficient is to 1, the stronger the linear correlation between the two sequences involved in the calculation. In contrast, the core indicator output by the dynamic time warping similarity algorithm is "distance" or "cost", not a direct similarity measure. Therefore, the larger the value of dynamic time warping, the greater the difference between the two sequences involved in the calculation, and the lower the similarity.

[0042] To ensure that the dynamic time warping similarity algorithm is consistent with indicators such as the Pearson correlation coefficient and / or Spearman rank correlation coefficient in terms of dimensions and trends (i.e., the larger the value, the greater the similarity), and to facilitate subsequent calculations, the calculation results of dynamic time warping similarity can be transformed using the following formula: in, The converted similarity score. This is the original calculation result (distance value) of the dynamic time warping similarity algorithm. For scale parameters greater than 0, adjustments can be made based on the sensitivity requirements of specific engineering projects (e.g., taking...). =0.07, and can fluctuate within a certain range, such as ±0.02). This formula maps the distance value (i.e., the calculation result of dynamic time-warped similarity) to the (0,1] interval, and maintains a monotonically decreasing relationship, thus obtaining a similarity score with consistent comparability. The converted value... This will be used as a component of the overall correlation strength and input into the subsequent steps of constructing the correlation graph model.

[0043] Step S130: Based on the motion correlation strength, cluster all monitoring points and divide all monitoring points into one or more cooperative motion groups, where each cooperative motion group corresponds to a potential sliding block of the slope.

[0044] In this context, a coordinated motion group is a subset of monitoring points defined from a data perspective, where the displacement time-series data of all monitoring points in this subset exhibit high synchronicity, correlation, or consistency. A potential sliding block is a physical entity inferred from a geomechanical and engineering perspective. This physical entity refers to a relatively intact soil or rock mass within the slope that possesses a potential unified sliding tendency. This physical entity has not yet experienced overall failure, but may move as a whole along a sliding surface upon instability. Therefore, a coordinated motion group can correspond to a potential sliding block of the slope.

[0045] Figure 2 The diagram shown is a flowchart illustrating a method for clustering all monitoring points according to an embodiment of this application. Figure 2 As shown, in one embodiment of this application, the method for clustering all monitoring points may include the following steps: Step S210: Construct a correlation graph based on the motion correlation strength.

[0046] In this graph, the nodes are the monitoring points, and the weight of the edge connecting any two nodes is the motion correlation strength between the two monitoring points corresponding to those two nodes.

[0047] To better quantify the overall correlation between any two monitoring points, a correlation map can be constructed by integrating the overall correlation strength, which can be obtained by fusing multiple indicators of motion correlation strength.

[0048] In one embodiment of this application, constructing a correlation graph based on motion correlation strength may include: obtaining a comprehensive correlation strength based on motion correlation strength; and constructing a correlation graph based on the comprehensive correlation strength.

[0049] In this graph, the nodes are the monitoring points, and the weight of the connecting edge between any two nodes is the overall correlation strength between the two monitoring points corresponding to those two nodes.

[0050] Specifically, based on the motion correlation strength, the method for obtaining the comprehensive correlation strength can be any one of the mean fusion strategy, weighted fusion strategy, or maximum value fusion strategy.

[0051] For example, if the motion correlation strength is the Pearson correlation coefficient, the Spearman rank correlation coefficient, and the dynamic time warp similarity after the above transformation, then the formula for obtaining the comprehensive correlation strength through the mean fusion strategy is: in, For any two monitoring points and The overall correlation strength between them The Pearson correlation coefficient is used. , where is the Spearman rank correlation coefficient. This represents the dynamic time-warped similarity after transformation.

[0052] For example, the formula for obtaining the overall correlation strength through a weighted fusion strategy is: in, For any two monitoring points and The overall correlation strength between them The Pearson correlation coefficient is used. , where is the Spearman rank correlation coefficient. This represents the dynamic time-warped similarity after transformation. The preset weighting coefficients, and For example, it can be set To emphasize the consistency of trends.

[0053] For example, the formula for obtaining the overall correlation strength through the maximum value fusion strategy is: in, For any two monitoring points and The overall correlation strength between them The Pearson correlation coefficient is used. , where is the Spearman rank correlation coefficient. This is the transformed dynamic time-warped similarity. This strategy tends to capture the most significant correlation signals.

[0054] The above formula integrates three indicators—Pearson correlation coefficient (measuring linear correlation), Spearman rank correlation coefficient (measuring trend consistency), and DTW similarity (measuring overall morphological similarity)—to obtain the comprehensive correlation strength. In other words, the comprehensive correlation strength can comprehensively quantify the motion correlation strength between two monitoring points from different dimensions. This multi-angle measurement method can simultaneously capture multiple collaborative modes such as synchronous deformation, trend-consistent deformation, and sequential deformation with phase differences. It can reveal the potential sliding mechanism more comprehensively and accurately than a single indicator or qualitative observation.

[0055] It should be noted that when the motion correlation strength or comprehensive correlation strength between two monitoring points is too low, it can be determined that there is insufficient correlation between the two monitoring points, and in this case, it is not necessary to establish a connection between the two monitoring points. Therefore, in one embodiment of this application, a connection edge can be established between the corresponding two nodes in the correlation graph only when the motion correlation strength meets certain conditions.

[0056] Specifically, when the motion correlation strength between two monitoring points is greater than or equal to a preset connection threshold, a connection edge is established between the corresponding two nodes in the correlation graph.

[0057] Furthermore, when the overall correlation strength between two monitoring points is greater than or equal to a preset connection threshold, a connection edge can be established between the corresponding two nodes in the correlation graph.

[0058] In one embodiment of this application, in order to further simplify the structure of the association graph and highlight strong associations, only the top k strongest connections of each node can be retained (for example, setting k to 5) to obtain an optimized association graph.

[0059] It should be noted that the methods for constructing the correlation graph shown in the various embodiments of step S210 can be flexibly selected according to actual needs: one method can be used alone to simplify the construction process, or multiple methods can be combined to construct a better correlation graph.

[0060] Through the above steps, an abstract set of monitoring points can be transformed into a concrete, weighted undirected graph G = (V, E, W), where V is the set of nodes, E is the set of edges, and W is the set of weights. This graph can be represented and stored in a computer using an adjacency matrix or an adjacency list.

[0061] Step S220: Perform community structure detection on the correlation graph to divide it into one or more communities, where each community is a cooperative movement group.

[0062] In step S220, the purpose of performing community structure detection on the correlation graph to divide it into one or more communities is to find a way to divide the nodes in the graph such that the sum of edge weights within each divided community (i.e., the set of monitoring points) is as high as possible, while the sum of edge weights between different communities is as low as possible.

[0063] In one embodiment of this application, step S220 can take the correlation graph as input and use a community detection algorithm to automatically cluster the data to divide one or more communities.

[0064] For example, the community detection algorithm can be the Louvain algorithm. The algorithm takes an association graph as input and outputs one or more communities, where each community corresponds to a potential sliding block.

[0065] The above step S130 can objectively and automatically identify possible independent deformation areas in the slope, thus providing key target areas for landslide early warning and precise management.

[0066] To improve the engineering applicability of the above preliminary identification results, post-processing optimization can be performed on the potential sliding blocks identified in the preliminary identification.

[0067] Specifically, after completing the initial identification in step S130, in order to improve the reliability of the results, the identification results can be analyzed from both statistical and engineering perspectives: from a statistical perspective, a "group" with too few members may be due to random fluctuations or accidental data associations, and its movement pattern lacks statistical robustness; from an engineering perspective, a block containing only scattered monitoring points is unlikely to constitute a meaningful potential sliding range in space, and its actual monitoring and governance value is limited.

[0068] Therefore, in one embodiment of this application, the following minimum block size filtering mechanism can be used to post-process and optimize the cooperative motion groups corresponding to the potential sliding blocks initially identified above: for any cooperative motion group, if the number of monitoring points in the cooperative motion group is less than the preset minimum block size threshold, the cooperative motion group is removed so as to perform minimum size filtering on each cooperative motion group.

[0069] For example, a user can set a minimum block size threshold N. min (e.g. N) min =3). For any member monitoring point number less than N. min The system treats potential sliding blocks as "noise blocks" and filters them out from the final results. This method ensures that the retained potential sliding blocks have sufficient statistical significance and engineering value.

[0070] The aforementioned minimum block size filtering mechanism, by automatically clustering monitoring points and eliminating small groups with no engineering significance, reduces the number of objects that need to be processed in subsequent steps. It also enables engineers to focus more on key blocks with practical value, improving the efficiency and relevance of the overall analysis process. More importantly, it ensures that each potential sliding block after processing is an analytical object with statistical basis, spatial scale, and practical value, thus providing high-quality input for subsequent accurate monitoring and disaster prevention decision-making.

[0071] In another embodiment of this application, after the clustering of all monitoring points is completed in step S130 above, in order to ensure that the potential sliding blocks identified by the algorithm are a real and reasonable whole in physical space, the following spatial continuity verification mechanism can be used to post-process and optimize the cooperative motion group corresponding to the initially identified potential sliding blocks: For any cooperative motion group, perform spatial distribution continuity verification on the cooperative motion group to obtain the verification result, so as to confirm the spatial distribution of each monitoring point in the cooperative motion group on the slope; if the verification result determines that the potential sliding block corresponding to the cooperative motion group is a spatially discontinuous block, then perform a split optimization operation on the cooperative motion group.

[0072] Specifically, the spatial distribution continuity of a coordinated movement group can be verified as follows: calculate the spatial boundary of the coordinated movement group; count the number of monitoring points located within the spatial boundary but not belonging to the coordinated movement group; if the ratio of the number to the total number of monitoring points within the spatial boundary exceeds a preset ratio threshold, then the potential sliding block corresponding to the coordinated movement group is determined to be a spatially discontinuous block; otherwise, the potential sliding block corresponding to the coordinated movement group is determined to be a spatially continuous block.

[0073] For example, the spatial boundary of the potential sliding block corresponding to the cooperative motion group can be calculated by the minimum convex hull. Then, through spatial query, all monitoring points located within this boundary are counted, and the proportion of external monitoring points that do not belong to the potential sliding block is calculated. If the proportion exceeds a preset proportion threshold (such as 20%), the potential sliding block is determined to be spatially discontinuous; otherwise, the potential sliding block is determined to be a spatially continuous block.

[0074] For any potential sliding block identified as spatially discontinuous, an automatic splitting and optimization process can be initiated. Specifically, a subgraph can be constructed first, that is, from the initial correlation graph model, all member monitoring points of the spatially discontinuous potential sliding block and the edges between them are extracted to form a subgraph; then, the subgraph is split.

[0075] In one embodiment of this application, a subgraph can be split as follows: identify candidate edges for splitting; perform splitting and verification.

[0076] For example, candidate edges for splitting can be identified by calculating the spatial distance weights of all edges in the subgraph. That is, for each edge, the actual spatial distance between the two monitoring points it connects is calculated. From an engineering perspective, a long spatial distance between two monitoring points means they are unlikely to slide together as components of a rigid or quasi-rigid whole; a low correlation between two monitoring points means that even if they exhibit some statistical correlation, the correlation itself is weak. In other words, these edges with relatively low correlation and long spatial distances are likely due to spurious strong correlations caused by data noise or macroscopic background conditions (such as regional earthquakes or gravitational waves), rather than a true reflection of physical and mechanical connections. Therefore, cutting off these edges with relatively low correlation and long spatial distances can be prioritized. To this end, a "distance-correlation ratio" (e.g., spatial distance / motion correlation strength) can be calculated. Edges with higher ratios are more likely to be "bridges" connecting two discontinuous subgroups and can be considered as candidate edges for splitting the subgraph.

[0077] For example, the splitting and verification can be performed as follows: directly remove one or more key candidate edges, and then check whether the atomic graph is split into two or more connected components (i.e., new subgraphs that are still internally connected but disconnected from each other), where each connected component is a new candidate sub-block.

[0078] The above method prioritizes cutting off edges with "low correlation strength and long spatial distance", so that the output new candidate sub-block is a spatially compact and mechanically tight block, thus ensuring its engineering practicality.

[0079] In another embodiment of this application, the subgraph can also be split in the following way: on the subgraph, a clustering algorithm that takes into account spatial constraints (such as a community detection algorithm that corrects edge weights using spatial distance) is used to repartition it, forcing it to generate spatially continuous subgroups.

[0080] While the above subgraph splitting method solves the obvious spatial discontinuity problem, the new candidate sub-blocks formed after splitting may still have spatially discontinuous regions. Therefore, to ensure that all potential sliding blocks in the final output are spatially continuous blocks, a recursive verification can be performed on each new candidate sub-block formed after the splitting. That is, for each new candidate sub-block formed after splitting, the spatial continuity verification is re-executed. If a new candidate sub-block is still discontinuous, the subgraph splitting process is recursively executed on it until each new candidate sub-block formed after splitting can pass the spatial continuity verification.

[0081] The aforementioned spatial continuity verification mechanism, based on the initial clustering of all monitoring points in step S130, recursively verifies the spatial continuity of each potential sliding block, ensuring that each final sliding block is a physically existing and continuous potential sliding block. This approach not only allows engineers to focus more on key blocks with practical value, improving the efficiency and relevance of the overall analysis process, but also reduces the number of objects to be processed in subsequent steps. More importantly, it ensures that each processed potential sliding block is an analytical object with statistical basis, spatial continuity, and practical value, thus providing high-quality input for subsequent accurate monitoring and disaster prevention decision-making.

[0082] It should be noted that the minimum block size filtering mechanism and spatial continuity verification mechanism mentioned above can be flexibly selected according to actual needs: one of them can be used alone for targeted optimization, or the two methods can be combined to identify the optimal potential sliding block that is more in line with engineering practice and geological laws.

[0083] Step S140: Conduct a block stability assessment for each potential sliding block to determine the risk of sliding of each potential sliding block.

[0084] Figure 3 The diagram shown is a flowchart illustrating a block stability assessment for a potential sliding block according to an embodiment of this application. In one embodiment of this application, as... Figure 3 As shown, the stability of a potential sliding block can be assessed through the following steps: Step S310: Calculate the block stability coefficient corresponding to each potential sliding block.

[0085] Among them, the block stability coefficient can comprehensively reflect the coordination and consistency of the internal motion of a potential sliding block.

[0086] For example, the block stability coefficient of a potential sliding block can be calculated using the following formula: Where m is the number of monitoring points in the potential sliding block; This represents the average weight of all edges within the block. The higher this value (the closer to 1), the better the coordination of movement trends among the monitoring points within the block. This represents the standard deviation of the weights of all edges within the block. The lower the value (the closer to 0), the more uniform the connections within the block are, and the fewer obvious weak points there are. Standard deviation can be converted into a consistency index; the smaller the standard deviation, the closer the consistency is to 1.

[0087] It should be noted that the BSC (Block Stability Coefficient) obtained by the above formula has a range between [0, 1]. If the BSC value is high (e.g., greater than 0.7), it means that the block not only has strong cooperative motion but also highly consistent motion patterns. Such high-risk blocks with tight structures and significant cooperative deformation characteristics should be given the highest level of attention. If the BSC value is moderate, it indicates that the block has some cooperativeness, but the internal motion is not completely consistent, and there may be multiple small deformation centers or deformation fronts. If the BSC value is low (e.g., less than 0.3), it indicates that the block has loose internal connections and poor cooperativeness, and may be a misjudged block or a potential risk area that is in a very early stage and has not yet formed a unified slip surface.

[0088] As can be seen from the formula above, the block stability coefficient comprehensively considers the average strength of the internal correlations (reflecting overall synergy) and its standard deviation (reflecting internal consistency) of the block. Therefore, a block with a high BSC value not only indicates that the movement of its internal monitoring points is highly coordinated and uniform, but also suggests that it is a potential sliding body with a complete structure and concentrated risks. The design of the block stability coefficient realizes a leap from the initial "identification of the existence of potential sliding bodies" to the quantitative assessment of their "risk quality," thereby providing an objective and refined decision-making basis for implementing risk classification management and determining the priority of monitoring and remediation.

[0089] The method described above for calculating the block stability coefficient combines the block stability coefficient with absolute values ​​such as displacement and velocity to form a graded early warning system, providing more accurate and forward-looking decision support for slope risk management.

[0090] Step S320: If the block stability coefficient is less than the preset block stability coefficient threshold, then the corresponding potential sliding block is determined to be a high-risk sliding block; otherwise, the corresponding potential sliding block is determined to be a low-risk sliding block.

[0091] Specifically, a block stability coefficient threshold can be preset (e.g., 0.7). If the block stability coefficient is less than the preset block stability coefficient threshold, the corresponding potential sliding block is identified as a high-risk sliding block, and the highest level of monitoring, early warning and emergency response mechanism should be activated, such as: evacuating potentially affected personnel, taking timely and effective engineering and non-engineering measures to control the development of risks, and comprehensively managing and eliminating or controlling risks in the long term.

[0092] To better manage the risk of potential sliding blocks falling, a multi-level early warning threshold system can be set up. For example, high-risk, medium-risk, and low-risk thresholds can be set to form a tiered early warning response system (e.g., >0.9 is stable, 0.7–0.9 is low risk requiring regular inspection, and <0.7 is high risk requiring emergency handling), thus achieving dynamic hierarchical management of risks.

[0093] The aforementioned automatic identification method for potential landslides on slopes automatically calculates the multi-dimensional temporal correlations between all monitoring point pairs, constructs a correlation graph model based on this, and then uses a community detection algorithm to automatically cluster and identify one or more potential landslide blocks. This approach transforms the entire identification process into repeatable mathematical calculations, thereby achieving automatic identification of potential landslide blocks. This method not only reduces the analysis time from several days of manual judgment to minutes of computation but also completely eliminates subjective biases caused by human differences, thus ensuring the objectivity of the identification process and the repeatability of the results. Furthermore, this automatic identification method for potential landslides on slopes optimizes the preliminarily identified potential landslide blocks through post-processing (minimum block size filtering mechanism and spatial distribution continuity verification). While eliminating small-scale groups with no engineering significance, it ensures that each potential landslide in the final output is a continuous or nearly continuous area in the slope space. This post-processing optimization step transforms basic geomechanical knowledge (such as the spatial integrity of landslides) into algorithmic logic, elevating the identification results from "mathematical grouping" to "physical geological units" that conform to engineering understanding. This not only reduces the number of objects that need to be processed in subsequent analysis and lowers the computational complexity, but also greatly improves the practicality of the method and the reliability of the output results, thus providing high-quality input basis for accurate slope monitoring, risk assessment, and disaster prevention decision-making.

[0094] The above is an introduction to the automatic identification method for potential landslides on slopes provided in the embodiments of this application. This method can be used by... Figure 4 The automatic identification system for potential landslides on the slope is shown.

[0095] Figure 4 The diagram shown is a schematic representation of an automatic slope potential landslide identification system according to an embodiment of this application. Figure 4 As shown, the system 400 includes: The temporal motion data acquisition module 410 is used to acquire temporal motion data of each monitoring point on the slope surface at multiple consecutive monitoring times; The motion correlation strength measurement module 420 is used to calculate and quantify the motion correlation strength between any two monitoring points based on time-series motion data. The potential sliding block identification module 430 is used to cluster all monitoring points and divide all monitoring points into one or more cooperative motion groups, wherein each cooperative motion group corresponds to a potential sliding block of the slope; The block stability assessment module 440 is used to assess the block stability of each potential sliding block to determine the risk of sliding of each potential sliding block.

[0096] Furthermore, as one implementation, when the time-series motion data acquisition module 410 collects the coordinate data of each monitoring point deployed on the slope surface at multiple monitoring times and generates the displacement time-series data of each monitoring point, it is also used to: acquire the three-dimensional coordinates of each monitoring point at each monitoring time at multiple monitoring times; calculate the displacement of each monitoring point relative to the reference time at each monitoring time based on the three-dimensional coordinates; and calculate the time-series motion data of each monitoring point based on the displacement, wherein the time-series motion data is a displacement time series and / or a velocity time series.

[0097] Furthermore, as one implementation, when calculating the motion association strength between any two monitoring points based on displacement time series data, the motion association strength measurement module 420 is also used to calculate the similarity measure value between the displacement time series data corresponding to any two monitoring points based on displacement time series data, and use it as the motion association strength between any two monitoring points. The motion association strength is at least one of Pearson correlation coefficient, Spearman rank correlation coefficient and dynamic time warping similarity.

[0098] Furthermore, as one implementation, when the potential sliding block identification module 430 clusters all monitoring points based on motion association strength and divides all monitoring points into one or more cooperative motion groups, it is also used to: construct an association graph based on motion association strength, wherein the nodes of the association graph are each monitoring point, and the weight of the connecting edge between any two nodes is the motion association strength between the two monitoring points corresponding to any two nodes; and perform community structure detection on the association graph to divide one or more communities, wherein each community is a cooperative motion group.

[0099] Furthermore, as one implementation, when constructing the correlation graph based on the motion correlation strength, the potential sliding block identification module 430 is also used to: obtain the comprehensive correlation strength based on the motion correlation strength; and construct the correlation graph based on the comprehensive correlation strength, wherein the nodes of the correlation graph are each monitoring point, and the weight of the connecting edge between any two nodes is the comprehensive correlation strength between the two monitoring points corresponding to any two nodes.

[0100] Furthermore, as one implementation, when constructing the correlation graph based on the motion correlation strength, the potential sliding block identification module 430 is also used to: establish a connection edge between the two corresponding nodes in the correlation graph when the motion correlation strength between two monitoring points is greater than or equal to a preset connection threshold.

[0101] Furthermore, as one implementation, when the potential sliding block identification module 430 performs community structure detection on the association graph to divide one or more communities, it is also used to: take the association graph as input and use a community detection algorithm to perform automatic clustering to divide one or more communities.

[0102] Furthermore, as one implementation, when the block stability assessment module 440 assesses the block stability of each potential sliding block to determine the risk of sliding of each potential sliding block, it is also used to: calculate the block stability coefficient corresponding to each potential sliding block; if the block stability coefficient is less than a preset block stability coefficient threshold, the corresponding potential sliding block is determined to be a high-risk sliding block; otherwise, the corresponding potential sliding block is determined to be a low-risk sliding block.

[0103] Furthermore, the system 400 also includes a minimum scale filtering module 450. After clustering all monitoring points based on the motion association strength and dividing all monitoring points into one or more cooperative motion groups, before performing block stability assessment on each potential sliding block to determine the sliding risk of each potential sliding block, the minimum scale filtering module 450 is used to remove the cooperative motion group if the number of monitoring points in the cooperative motion group is less than a preset minimum block size threshold, so as to perform minimum scale filtering on each cooperative motion group.

[0104] Furthermore, the system 400 also includes a spatial distribution continuity verification module 460. After clustering all monitoring points based on the motion correlation strength and dividing all monitoring points into one or more cooperative motion groups, before conducting block stability assessments on each potential sliding block to determine the sliding risk of each potential sliding block, the spatial distribution continuity verification module 460 is used to: for any cooperative motion group, perform spatial distribution continuity verification on the cooperative motion group, obtain verification results, and confirm the spatial distribution of each monitoring point in the cooperative motion group on the slope; if the verification results determine that the potential sliding block corresponding to the cooperative motion group is a spatially discontinuous block, then perform a splitting optimization operation on the cooperative motion group.

[0105] Furthermore, as one implementation method, when performing spatial distribution continuity verification on a coordinated motion group, the spatial distribution continuity verification module 460 is also used to: calculate the spatial boundary of the coordinated motion group; count the number of monitoring points located within the spatial boundary but not belonging to the coordinated motion group; if the ratio of the number to the total number of monitoring points within the spatial boundary exceeds a preset ratio threshold, then the potential sliding block corresponding to the coordinated motion group is determined to be a spatially discontinuous block; otherwise, the potential sliding block corresponding to the coordinated motion group is determined to be a spatially continuous block.

[0106] It should be understood that, for the sake of convenience and brevity, the specific working scenarios, processes, effects, and other details of each module in the above system 400 can be referred to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0107] This application also provides an electronic device. Figure 5 The diagram shown is a block diagram of an exemplary electronic device provided in an embodiment of this application. (Refer to...) Figure 5 The electronic device 500 includes a memory 510 and a processor 520. The memory 510 stores a computer program, and the processor 520 runs the computer program to enable the electronic device 500 to implement the automatic identification method for potential landslides on slopes provided in any of the foregoing embodiments.

[0108] Electronic device 500 may also include a power supply component configured to perform power management of electronic device 500, a wired or wireless network interface configured to connect electronic device 500 to a network, and an input / output (I / O) interface. Electronic device 500 can be operated based on an operating system stored in memory 510, such as Windows Server. TM Mac OSX TM Unix TM Linux TM FreeBSD TM Or similar.

[0109] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program in the storage medium is executed by the processor 520 of the electronic device 500, the electronic device 500 is able to implement the automatic identification method for potential landslides on slopes provided in any of the foregoing embodiments.

[0110] This application also provides a computer program product, which includes instructions that, when executed by the processor 520 of the electronic device 500, enable the electronic device 500 to implement the automatic identification method for potential landslides on slopes provided in any of the foregoing embodiments.

[0111] The prompting method in this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in this application are performed, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, network equipment, user equipment, core network equipment, OAM, or other programmable device.

[0112] The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Operational Information Management) system, or other programmable devices.

[0113] The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0114] It is understood that the specific examples provided in this application are only intended to help those skilled in the art better understand the embodiments of this application, and are not intended to limit the scope of the invention.

[0115] It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0116] It is understood that the various embodiments described in this application can be implemented individually or in combination, and the embodiments of this application are not limited in this respect.

[0117] Unless otherwise stated, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The term "and / or" as used in this application includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0118] It is understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0119] It is understood that the memory in the embodiments of this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Specifically, non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0120] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be indirect couplings or communication connections between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0122] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0124] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0125] The above description is merely a specific embodiment of this application, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for automatically identifying potential sliding bodies of a slope, characterized in that, include: The coordinate data of each monitoring point deployed on the slope surface at multiple monitoring times are collected, and the displacement time series data of each monitoring point are generated. Based on the displacement time series data, the motion correlation strength between any two monitoring points among all monitoring points is calculated respectively; Based on the motion correlation strength, all monitoring points are clustered and divided into one or more cooperative motion groups, wherein each cooperative motion group corresponds to a potential sliding block of the slope; Each potential sliding block is assessed for its stability to determine its risk of slippage.

2. The method of claim 1, wherein, The process involves collecting coordinate data from various monitoring points deployed on the slope surface at multiple monitoring times and generating displacement time-series data for each monitoring point, including: Obtain the three-dimensional coordinates of each monitoring point at each of the multiple monitoring times; Based on the three-dimensional coordinates, calculate the displacement of each monitoring point relative to the reference time at each monitoring time; Based on the displacement, the time-series motion data of each monitoring point is calculated, wherein the time-series motion data is a displacement time series and / or a velocity time series.

3. The method of claim 1, wherein, The step of calculating the motion correlation strength between any two monitoring points based on the displacement time series data includes: Based on the displacement time series data, a similarity metric between the displacement time series data corresponding to any two monitoring points is calculated, and used as the motion correlation strength between the two monitoring points. The motion correlation strength is at least one of Pearson correlation coefficient, Spearman rank correlation coefficient, and dynamic time warping similarity.

4. The method of claim 1, wherein, Based on the motion correlation strength, all monitoring points are clustered and divided into one or more cooperative motion groups, including: Based on the motion association strength, an association graph is constructed, wherein the nodes of the association graph are the monitoring points, and the weight of the connecting edge between any two nodes is the motion association strength between the two monitoring points corresponding to the two nodes. The correlation graph is used to detect community structure in order to divide one or more communities, where each community is a cooperative movement group.

5. The method of claim 4, wherein, The step of constructing a correlation graph based on the motion correlation strength includes: Based on the motion correlation strength, the comprehensive correlation strength is obtained; Based on the comprehensive correlation strength, a correlation graph is constructed, wherein the nodes of the correlation graph are the monitoring points, and the weight of the connecting edge between any two nodes is the comprehensive correlation strength between the two monitoring points corresponding to the two nodes.

6. The method of claim 4, wherein, The step of constructing a correlation graph based on the motion correlation strength includes: When the motion correlation strength between two monitoring points is greater than or equal to a preset connection threshold, a connection edge is established between the two corresponding nodes in the correlation graph.

7. The method of claim 4, wherein, The process of performing community structure detection on the association graph to divide it into one or more communities includes: Using the correlation graph as input, a community detection algorithm is employed for automatic clustering to identify one or more communities.

8. The method of claim 1, wherein, The step of conducting a block stability assessment on each potential sliding block to determine the risk of slippage for each potential sliding block includes: Calculate the block stability coefficient corresponding to each potential sliding block; If the block stability coefficient is less than a preset block stability coefficient threshold, the corresponding potential sliding block is determined to be a high-risk sliding block; otherwise, the corresponding potential sliding block is determined to be a low-risk sliding block.

9. The method of claim 1, wherein, After clustering all monitoring points based on the motion correlation strength to divide them into one or more cooperative motion groups, and before performing block stability assessments on each potential sliding block to determine the slip risk of each potential sliding block, the method further includes: For any coordinated movement group, if the number of monitoring points in the coordinated movement group is less than a preset minimum block size threshold, then the coordinated movement group is removed to perform minimum size filtering on each of the coordinated movement groups.

10. The method according to claim 1, characterized in that, After clustering all monitoring points based on the motion correlation strength to divide them into one or more cooperative motion groups, and before performing block stability assessments on each potential sliding block to determine the slip risk of each potential sliding block, the method further includes: For any coordinated movement group, the spatial distribution continuity of the coordinated movement group is verified to obtain the verification result, so as to confirm the spatial distribution of each monitoring point in the coordinated movement group on the slope. If the verification result determines that the potential sliding block corresponding to the cooperative motion group is a spatially discontinuous block, then a splitting optimization operation is performed on the cooperative motion group.

11. The method according to claim 10, characterized in that, The step of verifying the spatial distribution continuity of the coordinated movement group includes: Calculate the spatial boundary of the coordinated movement group; The number of monitoring points located within the spatial boundary but not belonging to the cooperative movement group is counted; If the ratio of the number to the total number of monitoring points within the spatial boundary exceeds a preset ratio threshold, then the potential sliding block corresponding to the cooperative motion group is determined to be a spatially discontinuous block; otherwise, the potential sliding block corresponding to the cooperative motion group is determined to be a spatially continuous block.

12. An automatic identification system for potential landslides on slopes, characterized in that, include: The temporal motion data acquisition module is used to acquire temporal motion data of each monitoring point on the slope surface at multiple consecutive monitoring times; The motion correlation strength measurement module is used to calculate and quantify the motion correlation strength between any two monitoring points based on the time-series motion data. The potential sliding block identification module is used to cluster all the monitoring points and divide all the monitoring points into one or more cooperative motion groups, wherein each cooperative motion group corresponds to a potential sliding block of the slope; The block stability assessment module is used to assess the stability of each potential sliding block to determine the risk of slippage of each potential sliding block.

13. An electronic device, comprising: include: Memory; A processor, the memory for storing a computer program, the processor running the computer program to cause the electronic device to perform the automatic identification method for potential landslides on slopes as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method for automatic identification of potential landslides on slopes as described in any one of claims 1 to 11.

Images