A landslide geological disaster monitoring and early warning method and device

Abstract

The application provides a landslide geological disaster monitoring and early warning method and device, and the method comprises the following steps: acquiring monitoring data of each monitoring point in a landslide monitoring area at each monitoring sampling time within a first preset time period before the current time; determining at least one target monitoring point from the monitoring points based on the first data difference of each monitoring point; determining corresponding target data from the monitoring data corresponding to the target monitoring point and each prediction data based on the first data difference corresponding to the target monitoring point and each second data difference; and determining a landslide geological disaster monitoring result of the landslide monitoring area by a preset landslide geological disaster prediction model based on the target data of each target monitoring point. According to the scheme, the target monitoring point is obtained by screening the monitoring points of the landslide monitoring area, so that the data amount can be reduced, the target data of the target monitoring point is obtained by interpolation, the data of the surrounding monitoring points is utilized, and the accuracy is ensured, so that the early warning accuracy is ensured and the timeliness of early warning is improved.

Description

Technical Field

[0001] This invention relates to the field of geological disaster monitoring technology, and in particular to a method and device for monitoring and early warning of landslide geological disasters. Background Technology

[0002] Landslide monitoring, a branch of natural disaster prevention and control, involves observing and analyzing various precursory phenomena and recording the landslide formation process. Key monitoring contents include: the development of cracks in different parts of the slope; soil and rock loosening and local collapses, settlement and uplift; various underground and surface deformation and displacement phenomena; groundwater levels, volume, and hydrochemical characteristics; tree tilting and deformation of various buildings; changes in the external environment such as rainfall and seismic activity; and abnormal animal activity. Through these efforts, relevant data and information are obtained to provide a basis for landslide forecasting and disaster prevention.

[0003] Currently, by setting up large monitoring points in the area to be monitored according to certain rules to collect various types of data, the landslide geological disaster monitoring and early warning platform obtains the data collected from these monitoring points, analyzes the data, and obtains landslide geological disaster monitoring results based on the analysis results.

[0004] However, the above scheme requires analyzing data from all monitoring points to obtain landslide geological hazard monitoring results, resulting in a large amount of data and poor timeliness of landslide geological hazard monitoring and early warning. Summary of the Invention

[0005] This invention provides a method and device for monitoring and early warning of landslide geological disasters, which solves the problem of poor timeliness in the monitoring and early warning of landslide geological disasters in the prior art.

[0006] On the one hand, the present invention provides a method for monitoring and early warning of landslide geological hazards, including: Acquire monitoring data for each monitoring point within the landslide monitoring area at each monitoring sampling time within the first preset time period prior to the current time; The monitoring data of each monitoring point is compared with the risk-free monitoring data of the corresponding second preset time period to obtain the first data difference of each monitoring point, and at least one target monitoring point is determined from each monitoring point based on the first data difference of each monitoring point; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide disaster occurs in the landslide monitoring area during the second preset time period. For each target monitoring point, based on the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data. The predicted data of each target monitoring point under various other data accuracies are compared with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. Based on the first data difference and the second data differences corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and the predicted data corresponding to the target monitoring point. Based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined by a preset landslide geological hazard prediction model.

[0007] According to the landslide geological disaster monitoring and early warning method provided by the present invention, the method compares the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period to obtain the first data difference for each monitoring point, including: For each monitoring point, the corresponding monitoring data curve is obtained based on the monitoring data of each monitoring point, and the corresponding risk-free monitoring data curve is obtained based on the risk-free monitoring data of each monitoring point. Compare the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve, and obtain the corresponding first data difference based on the similarity. The magnitude of the first data difference is inversely proportional to the magnitude of the similarity. Based on the data differences among the monitoring points, at least one target monitoring point is identified from all the monitoring points, including: The monitoring points whose first data difference is not less than the first preset threshold are identified as target monitoring points.

[0008] According to the landslide geological hazard monitoring and early warning method provided by the present invention, the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve is compared, including: Using a preset hash algorithm, obtain the hash signatures corresponding to each preset point on the monitoring data curve and the risk-free monitoring data curve, respectively; The edit distance between the preset points on the monitoring data curve and the corresponding preset points on the risk-free monitoring data curve is calculated based on the hash signature of each preset point on the monitoring data curve and the hash signature of the corresponding preset point on the risk-free monitoring data curve. The mean of the edit distances between each preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve is determined as the similarity.

[0009] According to the landslide geological disaster monitoring and early warning method provided by the present invention, at least two other data accuracies include a first data accuracies and a second data accuracies, wherein the second data accuracies are higher than the first data accuracies; Based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm, including: Interpolate the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time to obtain the predicted data of the first data accuracy corresponding to the monitoring sampling time of the target monitoring point; Interpolation is performed on the predicted data of other target monitoring points at each monitoring sampling time with the first data precision to obtain the predicted data of the target monitoring point with the second data precision at the monitoring sampling time.

[0010] According to the landslide geological disaster monitoring and early warning method provided by the present invention, interpolation is performed on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time to obtain predicted data with a first data precision corresponding to the monitoring sampling time of the target monitoring point, including: Obtain the distance between each monitoring point within the preset range and the target monitoring point, and determine the corresponding interpolation weight based on the distance between each monitoring point. The magnitude of the interpolation weight is inversely proportional to the magnitude of the corresponding distance. The monitoring data of each monitoring point at each monitoring sampling time within the first preset time period before the current time are weighted according to the corresponding interpolation weights to obtain the predicted data of the first data accuracy of the target monitoring point at the monitoring sampling time.

[0011] According to the landslide geological disaster monitoring and early warning method provided by the present invention, based on the target data of each target monitoring point, the landslide geological disaster monitoring results of the landslide monitoring area are determined by a preset landslide geological disaster prediction model, including: If the proportion of target monitoring points with target data of other precision is not less than the preset proportion, then the target data of each target monitoring point will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output. If the proportion of target monitoring points with target data of other precision is less than the preset proportion, then the target data of each target monitoring point and the monitoring data of each monitoring point within the preset range of each target monitoring point at each monitoring sampling time within the first preset time period before the current time will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output.

[0012] According to the landslide geological disaster monitoring and early warning method provided by the present invention, the monitoring data includes meteorological data, groundwater data and geomechanical dynamic data.

[0013] Secondly, the present invention also provides a landslide geological disaster monitoring and early warning device, comprising: The monitoring data acquisition module is used to acquire monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within the first preset time period before the current time; The target monitoring point determination module is used to compare the monitoring data of each monitoring point with the risk-free monitoring data within the corresponding second preset time period to obtain the first data difference for each monitoring point, and to determine at least one target monitoring point from each monitoring point based on the data difference of each monitoring point; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide disaster has occurred in the landslide monitoring area during the second preset time period. The prediction data acquisition module is used to obtain prediction data for each target monitoring point at at least two other data accuracies based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data. The target data acquisition module is used to compare the predicted data of each target monitoring point with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. Based on the first data difference and the second data differences corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and the predicted data corresponding to the target monitoring point. The monitoring result acquisition module is used to determine the landslide geological hazard monitoring results in the landslide monitoring area based on the target data of each target monitoring point and through a preset landslide geological hazard prediction model.

[0014] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the target monitoring point determination module is specifically used for: For each monitoring point, the corresponding monitoring data curve is obtained based on the monitoring data of each monitoring point, and the corresponding risk-free monitoring data curve is obtained based on the risk-free monitoring data of each monitoring point. Compare the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve, and obtain the corresponding first data difference based on the similarity. The magnitude of the first data difference is inversely proportional to the magnitude of the similarity. Based on the data differences among the monitoring points, at least one target monitoring point is identified from all the monitoring points, including: The monitoring points whose first data difference is not less than the first preset threshold are identified as target monitoring points.

[0015] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the target monitoring point determination module is further used for: Using a preset hash algorithm, obtain the hash signatures corresponding to each preset point on the monitoring data curve and the risk-free monitoring data curve, respectively; The edit distance between the preset points on the monitoring data curve and the corresponding preset points on the risk-free monitoring data curve is calculated based on the hash signature of each preset point on the monitoring data curve and the hash signature of the corresponding preset point on the risk-free monitoring data curve. The mean of the edit distances between each preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve is determined as the similarity.

[0016] According to the landslide geological disaster monitoring and early warning device provided by the present invention, at least two other data accuracies include a first data accuracies and a second data accuracies, wherein the second data accuracies are higher than the first data accuracies; The predictive data acquisition module is specifically used for: Interpolate the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time to obtain the predicted data of the first data accuracy corresponding to the monitoring sampling time of the target monitoring point; Interpolation is performed on the predicted data of other target monitoring points at each monitoring sampling time with the first data precision to obtain the predicted data of the target monitoring point with the second data precision at the monitoring sampling time.

[0017] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the prediction data acquisition module is further used for: Obtain the distance between each monitoring point within the preset range and the target monitoring point, and determine the corresponding interpolation weight based on the distance between each monitoring point. The magnitude of the interpolation weight is inversely proportional to the magnitude of the corresponding distance. The monitoring data of each monitoring point at each monitoring sampling time within the first preset time period before the current time are weighted according to the corresponding interpolation weights to obtain the predicted data of the first data accuracy of the target monitoring point at the monitoring sampling time.

[0018] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the monitoring result acquisition module is specifically used for: If the proportion of target monitoring points with target data of other precision is not less than the preset proportion, then the target data of each target monitoring point will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output. If the proportion of target monitoring points with target data of other precision is less than the preset proportion, then the target data of each target monitoring point and the monitoring data of each monitoring point within the preset range of each target monitoring point at each monitoring sampling time within the first preset time period before the current time will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output.

[0019] According to the present invention, a landslide geological disaster monitoring and early warning device is provided, and the monitoring data includes meteorological data, groundwater data and geomechanical dynamic data.

[0020] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the landslide geological disaster monitoring and early warning method as described above.

[0021] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the landslide geological disaster monitoring and early warning method as described above.

[0022] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the landslide geological disaster monitoring and early warning method as described above.

[0023] This invention provides a method and device for monitoring and early warning of landslide geological hazards. The method identifies target monitoring points by comparing their monitoring data with corresponding risk-free monitoring data using a first data difference algorithm. It then obtains predicted data for the accuracy of other data at each target monitoring point using a predictive interpolation algorithm. Finally, it determines the target data for each target monitoring point by comparing its monitoring data and the predicted longitude of other data with the corresponding risk-free monitoring data using a second data difference algorithm. Based on the target data, the method determines the landslide geological hazard monitoring results for the landslide monitoring area using a pre-set landslide geological hazard prediction model. This approach significantly reduces the amount of data to be processed by selecting monitoring points within the landslide monitoring area. Furthermore, by using interpolation to obtain the target data, it utilizes data from surrounding monitoring points, ensuring the accuracy of the prediction results. Therefore, this approach improves both the accuracy and timeliness of early warnings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating a landslide geological disaster monitoring and early warning method provided by the present invention; Figure 2 A structural block diagram of a landslide geological disaster monitoring and early warning device provided by the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0027] Figure 1 This is a flowchart illustrating a landslide geological disaster monitoring and early warning method provided by the present invention, as shown below. Figure 1 As shown, the method may include: S101, acquire monitoring data of each monitoring point within the landslide monitoring area at each monitoring sampling time within the first preset time period before the current time.

[0028] The landslide monitoring area is the region where landslide monitoring and early warning will be conducted. Multiple monitoring points will be pre-set within this area. These monitoring points can be understood as edge devices that collect monitoring data at regular intervals. In other words, each monitoring point can collect monitoring data at a specific sampling period, and the time of each sampling can be called the monitoring sampling time.

[0029] Specifically, at the current moment, historical monitoring data is acquired to predict landslide monitoring results. Here, historical monitoring data refers to monitoring data from the first preset time period prior to the current moment. Therefore, for each monitoring point, there are multiple monitoring data points from the first preset time period prior to the current moment.

[0030] It should be noted that the monitoring data includes meteorological data, groundwater data, and geomechanical dynamic data. In other words, each monitoring point within the landslide monitoring area can collect meteorological data, groundwater data, and geomechanical dynamic data. For ease of explanation in this embodiment, only one type of data is described; it is understood that the same processing procedure is performed on each type of data to obtain the final landslide geological hazard monitoring results.

[0031] S102, compare the monitoring data of each monitoring point with the risk-free monitoring data of the corresponding second preset time period to obtain the first data difference of each monitoring point, and determine at least one target monitoring point from each monitoring point based on the first data difference of each monitoring point; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide disaster occurs in the landslide monitoring area during the second preset time period.

[0032] Among them, the risk-free monitoring data of each monitoring point within the second preset time period are also the historical monitoring data of each monitoring point. For example, the monitoring data of monitoring point A is the monitoring data of each monitoring sampling time within the current time to 1 hour before the current time (i.e., the first preset time period). The risk-free monitoring data corresponding to monitoring point A can be the monitoring data of each monitoring sampling time within the current time to 2 hours before the current time (i.e., the second preset time period), and there is no landslide risk within the current time to 2 hours before the current time.

[0033] Specifically, for each monitoring point, the monitoring data within a first preset time period is compared with the risk-free monitoring data within a second preset time period to obtain the difference between the two, i.e., the first data difference. Then, based on the first data difference of each monitoring point, it is determined which monitoring points might detect anomalies, i.e., these are identified as target monitoring points. Specifically, the monitoring data of monitoring points detecting anomalies will differ significantly from the previously risk-free monitoring data; therefore, the target monitoring points can be selected from all monitoring points by comparing the obtained first differences.

[0034] S103, for each target monitoring point, based on the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data.

[0035] Among them, each monitoring point is within a preset range based on the target monitoring point, that is, each monitoring point within a circle centered on the target monitoring point and with a preset distance as the radius.

[0036] Here, different data precision can be understood as the longitude of data obtained based on different data acquisition methods.

[0037] Specifically, for each target monitoring point, the present invention first acquires the monitoring data at each monitoring sampling time within a first preset time period. In order to obtain data (i.e., predicted data) at different data longitudes, interpolation can be performed based on the monitoring data of the monitoring points surrounding the target monitoring point to obtain the predicted data of the target node at other data accuracies.

[0038] S104, compare the predicted data of each target monitoring point with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. Based on the first data difference and the second data differences corresponding to the target monitoring point, determine the corresponding target data from the monitoring data and the predicted data corresponding to the target monitoring point.

[0039] Specifically, for each target monitoring point's monitoring data and predicted data with different other data accuracies, the differences between the other data accuracies of that target monitoring point and the corresponding risk-free monitoring data (i.e., the second data difference) are further obtained. Then, based on the first data difference and the second data differences corresponding to that target monitoring point, the target data corresponding to that target monitoring point is determined. Specifically, the data (including monitoring data and predicted data) corresponding to the largest difference between the first data difference and the second data differences is determined as the target data. That is, for a target monitoring point, ultimately, one of its monitoring data and the predicted data with different other data accuracies may be determined as the target data.

[0040] S105, based on the target data of each target monitoring point, determine the landslide geological hazard monitoring results of the landslide monitoring area through a preset landslide geological hazard prediction model.

[0041] Specifically, after acquiring the target data for each target monitoring point, the landslide geological hazard monitoring results for the landslide monitoring area are determined based on a pre-trained landslide geological hazard prediction model. If the landslide geological hazard monitoring results indicate a landslide risk, an alarm message is issued.

[0042] This invention provides a landslide geological disaster monitoring and early warning method. It determines target monitoring points by identifying the first data difference between the monitoring data of each monitoring point and the corresponding risk-free monitoring data. A predictive interpolation algorithm is used to obtain the predicted accuracy of other data for each target monitoring point. The target data for each target monitoring point is then determined by identifying the second data difference between the predicted longitude data of each target monitoring point and the corresponding risk-free monitoring data. Finally, based on the target data of each target monitoring point, a pre-set landslide geological disaster prediction model is used to determine the landslide geological disaster monitoring results for the landslide monitoring area. This scheme significantly reduces the amount of data to be processed by selecting monitoring points within the landslide monitoring area. Furthermore, by using interpolation to obtain the target data of the target monitoring points, it utilizes data from surrounding monitoring points, ensuring the accuracy of the prediction results. Therefore, this scheme improves both the accuracy and timeliness of early warning.

[0043] In an optional embodiment of the present invention, the first data difference corresponding to each monitoring point is obtained by comparing the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period, including: For each monitoring point, the corresponding monitoring data curve is obtained based on the monitoring data of each monitoring point, and the corresponding risk-free monitoring data curve is obtained based on the risk-free monitoring data of each monitoring point. Compare the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve, and obtain the corresponding first data difference based on the similarity. The magnitude of the first data difference is inversely proportional to the magnitude of the similarity. Based on the data differences among the monitoring points, at least one target monitoring point is identified from all the monitoring points, including: The monitoring points whose first data difference is not less than the first preset threshold are identified as target monitoring points.

[0044] Specifically, when comparing the monitoring data at each monitoring point with the corresponding risk-free monitoring data, the curves for both are obtained: the monitoring data curve and the risk-free monitoring data curve. These two curves are then compared to obtain the corresponding similarity score. Finally, the magnitude of the first data difference is determined based on the similarity score. A higher similarity score corresponds to a smaller first data difference, and vice versa.

[0045] By obtaining target monitoring points through the above process, the number of monitoring points that need to be processed when predicting subsequent early warning results can be reduced, which means reducing the amount of data that needs to be processed when predicting subsequent early warning results.

[0046] In an optional embodiment of the present invention, comparing the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve includes: Using a preset hash algorithm, obtain the hash signatures corresponding to each preset point on the monitoring data curve and the risk-free monitoring data curve, respectively; The edit distance between the preset points on the monitoring data curve and the corresponding preset points on the risk-free monitoring data curve is calculated based on the hash signature of each preset point on the monitoring data curve and the hash signature of the corresponding preset point on the risk-free monitoring data curve. The mean of the edit distances between each preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve is determined as the similarity.

[0047] Specifically, a preset hash algorithm is used to obtain the similarity between two curves. The preset points can be set according to the sampling time or in other ways; this invention does not limit this setting.

[0048] It should be noted that the principle for obtaining the second data difference is the same as that for obtaining the first data difference, indicating that the monitoring data will be replaced with the predicted data.

[0049] In an optional embodiment of the present invention, at least two other data precisions include a first data precision and a second data precision, wherein the second data precision is higher than the first data precision; Based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm, including: Interpolate the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time to obtain the predicted data of the first data accuracy corresponding to the monitoring sampling time of the target monitoring point; Interpolation is performed on the predicted data of other target monitoring points at each monitoring sampling time with the first data precision to obtain the predicted data of the target monitoring point with the second data precision at the monitoring sampling time.

[0050] Furthermore, based on the monitoring data of each monitoring point within a preset range within a first preset time period before the current time, interpolation is performed to obtain the predicted data of the target monitoring point at the monitoring sampling time with the first data precision, including: Obtain the distance between each monitoring point within the preset range and the target monitoring point, and determine the corresponding interpolation weight based on the distance between each monitoring point. The magnitude of the interpolation weight is inversely proportional to the magnitude of the corresponding distance. The monitoring data of each monitoring point at each monitoring sampling time within the first preset time period before the current time are weighted according to the corresponding interpolation weights to obtain the predicted data of the first data accuracy of the target monitoring point at the monitoring sampling time.

[0051] Specifically, by interpolating to obtain the predicted data of each target monitoring point, the data information of the monitoring points around the target monitoring point or the target monitoring point can be used to ensure the accuracy of the final target data, thereby ensuring the accuracy of the early warning results.

[0052] In an optional embodiment of the present invention, based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined by a preset landslide geological hazard prediction model, including: If the proportion of target monitoring points with target data of other precision is not less than the preset proportion, then the target data of each target monitoring point will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output. If the proportion of target monitoring points with target data of other precision is less than the preset proportion, then the target data of each target monitoring point and the monitoring data of each monitoring point within the preset range of each target monitoring point at each monitoring sampling time within the first preset time period before the current time will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output.

[0053] Specifically, when the proportion of target monitoring points with target data of other precision is less than the preset proportion, in order to further ensure the accuracy of the early warning prediction results (i.e., landslide geological disaster monitoring results), the monitoring data of each monitoring point within the preset range of each target monitoring point and the target data of each target monitoring point are used together as the input of the preset landslide geological disaster prediction model.

[0054] Figure 2 A structural block diagram of a landslide geological disaster monitoring and early warning device provided by the present invention is shown below. Figure 2 As shown, the device may include: The monitoring data acquisition module 201 is used to acquire monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within a first preset time period before the current time; The target monitoring point determination module 202 is used to compare the monitoring data of each monitoring point with the risk-free monitoring data within the corresponding second preset time period to obtain the first data difference corresponding to each monitoring point, and to determine at least one target monitoring point from each monitoring point based on the data difference of each monitoring point; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide disaster has occurred in the landslide monitoring area during the second preset time period. The prediction data acquisition module 203 is used to obtain prediction data of the target monitoring point at at least two other data accuracies for each target monitoring point, based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data. The target data acquisition module 204 is used to compare the predicted data of each target monitoring point under various other data accuracies with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. Based on the first data difference and the second data differences corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and the predicted data corresponding to the target monitoring point. The monitoring result acquisition module 205 is used to determine the landslide geological hazard monitoring results of the landslide monitoring area based on the target data of each target monitoring point and through a preset landslide geological hazard prediction model.

[0055] This invention provides a landslide geological disaster monitoring and early warning device. It determines target monitoring points by comparing the monitoring data from each monitoring point with the corresponding risk-free monitoring data (first data difference). It then obtains predicted data for the accuracy of other data at each target monitoring point using a predictive interpolation algorithm. Finally, it determines the target data for each target monitoring point by comparing the predicted longitude data of the monitoring data and other data at each target monitoring point with the corresponding risk-free monitoring data (second data difference). Based on the target data of each target monitoring point, it determines the landslide geological disaster monitoring results for the landslide monitoring area using a preset landslide geological disaster prediction model. This scheme significantly reduces the amount of data to be processed by selecting monitoring points within the landslide monitoring area to obtain target monitoring points. Furthermore, by using interpolation to obtain the target data of the target monitoring points and utilizing data from surrounding monitoring points, it ensures the accuracy of the prediction results. Therefore, this scheme improves both the accuracy and timeliness of early warnings.

[0056] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the target monitoring point determination module is specifically used for: For each monitoring point, the corresponding monitoring data curve is obtained based on the monitoring data of each monitoring point, and the corresponding risk-free monitoring data curve is obtained based on the risk-free monitoring data of each monitoring point. Compare the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve, and obtain the corresponding first data difference based on the similarity. The magnitude of the first data difference is inversely proportional to the magnitude of the similarity. Based on the data differences among the monitoring points, at least one target monitoring point is identified from all the monitoring points, including: The monitoring points whose first data difference is not less than the first preset threshold are identified as target monitoring points.

[0057] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the target monitoring point determination module is further used for: Using a preset hash algorithm, obtain the hash signatures corresponding to each preset point on the monitoring data curve and the risk-free monitoring data curve, respectively; The edit distance between the preset points on the monitoring data curve and the corresponding preset points on the risk-free monitoring data curve is calculated based on the hash signature of each preset point on the monitoring data curve and the hash signature of the corresponding preset point on the risk-free monitoring data curve. The mean of the edit distances between each preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve is determined as the similarity.

[0058] According to the landslide geological disaster monitoring and early warning device provided by the present invention, at least two other data accuracies include a first data accuracies and a second data accuracies, wherein the second data accuracies are higher than the first data accuracies; The predictive data acquisition module is specifically used for: Interpolate the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time to obtain the predicted data of the first data accuracy corresponding to the monitoring sampling time of the target monitoring point; Interpolation is performed on the predicted data of other target monitoring points at each monitoring sampling time with the first data precision to obtain the predicted data of the target monitoring point with the second data precision at the monitoring sampling time.

[0059] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the prediction data acquisition module is further used for: Obtain the distance between each monitoring point within the preset range and the target monitoring point, and determine the corresponding interpolation weight based on the distance between each monitoring point. The magnitude of the interpolation weight is inversely proportional to the magnitude of the corresponding distance. The monitoring data of each monitoring point at each monitoring sampling time within the first preset time period before the current time are weighted according to the corresponding interpolation weights to obtain the predicted data of the first data accuracy of the target monitoring point at the monitoring sampling time.

[0060] According to the landslide geological disaster monitoring and early warning device provided by the present invention, the monitoring result acquisition module is specifically used for: If the proportion of target monitoring points with target data of other precision is not less than the preset proportion, then the target data of each target monitoring point will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output. If the proportion of target monitoring points with target data of other precision is less than the preset proportion, then the target data of each target monitoring point and the monitoring data of each monitoring point within the preset range of each target monitoring point at each monitoring sampling time within the first preset time period before the current time will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output.

[0061] According to the present invention, a landslide geological disaster monitoring and early warning device is provided, and the monitoring data includes meteorological data, groundwater data and geomechanical dynamic data.

[0062] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a landslide geological disaster monitoring and early warning method. The method includes: acquiring monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within a first preset time period before the current time; comparing the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period to obtain a first data difference for each monitoring point, and determining at least one target monitoring point from the monitoring points based on the first data difference; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide disaster has occurred in the landslide monitoring area during the second preset time period; for each target monitoring point, based on the target monitoring point... The monitoring data of each monitoring point within a preset range at each monitoring sampling time within a first preset time period before the current time are used to obtain the predicted data of the target monitoring point at at least two other data accuracies through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data; the predicted data of each target monitoring point at each other data accuracies are compared with the corresponding risk-free monitoring data within a second preset time period to obtain the corresponding second data difference; based on the first data difference and each second data difference corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and each predicted data corresponding to the target monitoring point; based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined through a preset landslide geological hazard prediction model.

[0063] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, 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 the present invention. 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.

[0064] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the landslide geological disaster monitoring and early warning method provided by the above methods. The method includes: acquiring monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within a first preset time period before the current time; comparing the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period to obtain a first data difference for each monitoring point, and determining at least one target monitoring point from the monitoring points based on the first data difference; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and the landslide occurs within the second preset time period. No landslides have occurred in the slope monitoring area. For each target monitoring point, based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, a preset interpolation algorithm is used to obtain the predicted data of the target monitoring point at at least two other data accuracies. The other data accuracies are higher than the data accuracies of the monitoring data. The predicted data of each target monitoring point at each other data accuracies is compared with the corresponding risk-free monitoring data within a second preset time period to obtain the corresponding second data difference. Based on the first data difference and each second data difference corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and each predicted data corresponding to the target monitoring point. Based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined through a preset landslide geological hazard prediction model.

[0065] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the landslide geological disaster monitoring and early warning method provided by the above methods. The method includes: acquiring monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within a first preset time period before the current time; comparing the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period to obtain a first data difference corresponding to each monitoring point, and determining at least one target monitoring point from the monitoring points based on the first data difference of each monitoring point; the second preset time period is before the first preset time period, the second preset time period is not less than the first preset time period, and no landslide geological disaster has occurred in the landslide monitoring area during the second preset time period. For each target monitoring point, based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data; the predicted data of each target monitoring point at each other data accuracies are compared with the corresponding risk-free monitoring data within a second preset time period to obtain the corresponding second data difference; based on the first data difference and each second data difference corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and each predicted data corresponding to the target monitoring point; based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined through a preset landslide geological hazard prediction model.

[0066] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring and early warning of landslide geological hazards, characterized in that, include: Acquire monitoring data for each monitoring point within the landslide monitoring area at each monitoring sampling time within the first preset time period prior to the current time; The monitoring data of each monitoring point is compared with the risk-free monitoring data of the corresponding second preset time period to obtain the first data difference of each monitoring point, and at least one target monitoring point is determined from each monitoring point based on the first data difference of each monitoring point. The second preset time is before the first preset time period, the second preset time is not less than the first preset time period, and no landslide geological disaster occurs in the landslide monitoring area during the second preset time period; For each target monitoring point, based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, where the preset range refers to the range centered on the target monitoring point and with a preset distance as the radius, the predicted data of the target monitoring point at at least two other data accuracies are obtained through a preset interpolation algorithm; the preset interpolation algorithm refers to a spatial interpolation algorithm that determines the interpolation weight based on the distance between each monitoring point within the preset range and the target monitoring point; the other data accuracies are higher than the data accuracies of the monitoring data; The predicted data of each target monitoring point under various other data accuracies are compared with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. The data with the largest difference value among the first data difference and each second data difference is determined as the corresponding target data. Based on the target data of each target monitoring point, the landslide geological hazard monitoring results of the landslide monitoring area are determined by a preset landslide geological hazard prediction model.

2. The method according to claim 1, characterized in that, The monitoring data at each monitoring point is compared with the corresponding risk-free monitoring data within the second preset time period to obtain the first data difference for each monitoring point, including: For each monitoring point, a corresponding monitoring data curve is obtained based on the monitoring data of the monitoring point, and a corresponding risk-free monitoring data curve is obtained based on the risk-free monitoring data of the monitoring point. Compare the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve, and obtain the corresponding first data difference based on the similarity. The magnitude of the first data difference is inversely proportional to the magnitude of the similarity. The process of determining at least one target monitoring point from among the monitoring points based on the data differences of each monitoring point includes: The monitoring points whose first data difference is not less than a first preset threshold are identified as the target monitoring points.

3. The method according to claim 2, characterized in that, The comparison of the similarity between the monitoring data curve corresponding to each monitoring point and the risk-free monitoring data curve includes: Using a preset hash algorithm, obtain the hash signatures corresponding to each preset point on the monitoring data curve and the risk-free monitoring data curve, respectively; Based on the hash signature of each preset point on the monitoring data curve and the hash signature of the corresponding preset point on the risk-free monitoring data curve, calculate the edit distance between the preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve; The average of the edit distances between each preset point on the monitoring data curve and the corresponding preset point on the risk-free monitoring data curve is determined as the similarity.

4. The method according to claim 1, characterized in that, The at least two other data precisions include a first data precision and a second data precision, wherein the second data precision is higher than the first data precision; The method involves obtaining predicted data for the target monitoring point at at least two other data accuracies based on the monitoring data of each monitoring point within a preset range within a first preset time period prior to the current time, using a preset interpolation algorithm. This includes: Based on the monitoring data of each monitoring point within the preset range of the target monitoring point at each monitoring sampling time within the first preset time period before the current time, interpolation is performed to obtain the predicted data of the target monitoring point at the monitoring sampling time with the first data precision. Interpolation is performed on the predicted data of other target monitoring points at each monitoring sampling time with a first data precision to obtain the predicted data of the target monitoring point with a second data precision at the monitoring sampling time.

5. The method according to claim 4, characterized in that, The method involves interpolating the monitoring data of the target monitoring point at each monitoring sampling time within a first preset time period prior to the current time, based on the monitoring data of each monitoring point within the preset range within the preset range, to obtain the predicted data of the target monitoring point at the monitoring sampling time with a first data precision, including: The distance between each monitoring point within a preset range and the target monitoring point is obtained, and the corresponding interpolation weight is determined based on the distance between each monitoring point. The magnitude of the interpolation weight is inversely proportional to the magnitude of the corresponding distance. The monitoring data of each monitoring point at each monitoring sampling time within a first preset time period before the current time are weighted according to the corresponding interpolation weights to obtain the predicted data of the target monitoring point at the first data accuracy at the monitoring sampling time.

6. The method according to claim 1, characterized in that, The process of determining landslide geological hazard monitoring results for the landslide monitoring area based on target data from each target monitoring point and using a pre-set landslide geological hazard prediction model includes: If the proportion of target monitoring points with target data of other precision is not less than a preset proportion, then the target data of each target monitoring point will be input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area will be output. If the proportion of target monitoring points with target data of other precision is less than the preset proportion, then the target data of each target monitoring point and the monitoring data of each monitoring point within the preset range of each target monitoring point at each monitoring sampling time within the first preset time period before the current time are input into the preset landslide geological disaster prediction model, and the landslide geological disaster monitoring results of the landslide monitoring area are output.

7. The method according to any one of claims 1 to 6, characterized in that, The monitoring data includes meteorological data, groundwater data, and geomechanical dynamic data.

8. A landslide geological hazard monitoring and early warning device for use in any one of the methods described in claims 1-7, characterized in that, include: The monitoring data acquisition module is used to acquire monitoring data of each monitoring point in the landslide monitoring area at each monitoring sampling time within the first preset time period before the current time; The target monitoring point determination module is used to compare the monitoring data of each monitoring point with the corresponding risk-free monitoring data within a second preset time period to obtain the first data difference for each monitoring point, and to determine at least one target monitoring point from each monitoring point based on the first data difference for each monitoring point. The second preset time is before the first preset time period, the second preset time is not less than the first preset time period, and no landslide geological disaster occurs in the landslide monitoring area during the second preset time period; The prediction data acquisition module is used to, for each target monitoring point, obtain prediction data of the target monitoring point at at least two other data accuracies based on the monitoring data of each monitoring point within a preset range of the target monitoring point at each monitoring sampling time within a first preset time period before the current time, through a preset interpolation algorithm; the other data accuracies are higher than the data accuracies of the monitoring data. The target data acquisition module is used to compare the predicted data of each target monitoring point with the risk-free monitoring data within the corresponding second preset time period to obtain the corresponding second data difference. Based on the first data difference and the second data differences corresponding to the target monitoring point, the corresponding target data is determined from the monitoring data and the predicted data corresponding to the target monitoring point. The monitoring result acquisition module is used to determine the landslide geological hazard monitoring results of the landslide monitoring area based on the target data of each target monitoring point and through a preset landslide geological hazard prediction model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images