Geological disaster early warning method, device, equipment and storage medium

Abstract

The method, device, equipment and storage medium provided by the embodiment of the application, the method comprises: acquiring first geological environment factors and first influence factor factors of a region to be warned in a current preset time length; performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the region to be warned. The feature superposition analysis on the first geological environment factors and the first influence factor factors in the region to be warned realizes the combination of the geological environment factors and the influence factor factors, solves the problem of inaccurate geological disaster prediction, and aims to improve the accuracy of geological disaster prediction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a geological disaster early warning method, device and equipment and storage medium. BACKGROUND

[0002] With the continuous enhancement of human engineering activities, the geological conditions become more and more complex, and the geological disasters have a more and more serious impact on people's life. And the geological disaster early warning is the premise of preventing geological disasters and reducing the loss caused by geological disasters.

[0003] At present, the geological disasters are mainly warned by early warning models. The early warning models can be divided into statistical early warning models and dynamic early warning models. Among them, the statistical early warning model is based on mathematical statistical analysis method, and determines the geological disasters caused by climate based on the statistical analysis results of geological disasters and weather data. It does not fully consider the change process of weather and its influence on geology, resulting in the vulnerability of geological disaster early warning. Although the dynamic early warning model considers the influence of data change process on geological disasters, it mainly adopts simplification and abstraction of data change, which cannot fit the actual change of geological environment and the influence of influencing factors in the change process of geological environment on geological disasters, resulting in also unable to accurately predict geological disasters. SUMMARY

[0004] Therefore, the embodiments of the present application provide a geological disaster early warning method, device, equipment and storage medium to solve the problem of inaccurate prediction of geological disasters in the prior art, and aim to improve the accuracy of prediction of geological disasters.

[0005] The first aspect of the embodiments of the present application provides a geological disaster early warning method, which comprises:

[0006] Respectively acquiring first geological environment factors and first influence factor factors of a to-be-early-warned area within a current preset time length;

[0007] Respectively performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the to-be-early-warned area.

[0008] The second aspect of the embodiments of the present application provides a geological disaster early warning device, which comprises:

[0009] An acquisition module is configured to respectively acquire first geological environment factors and first influence factor factors of a to-be-early-warned area within a current preset time length;

[0010] An analysis module is configured to respectively perform feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the to-be-early-warned area.

[0011] The third aspect of the embodiment of the present application provides a geological disaster early warning device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the geological disaster early warning device, and the processor implements the steps of the geological disaster early warning method provided in the first aspect when executing the computer program.

[0012] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the geological disaster early warning method provided in the first aspect when executed by a processor.

[0013] The geological disaster early warning method provided in the first aspect of the embodiment of the present application, compared with the prior art, comprises: acquiring first geological environment factors and first influence factor factors of a region to be early warned in a current preset time length respectively; and performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the region to be early warned. By performing feature superposition analysis on the first geological environment factors and the first influence factor factors in the region to be early warned, the combination of the geological environment factors and the influence factor factors is realized, the problem of inaccurate geological disaster prediction is solved, and the accuracy of geological disaster prediction is improved.

[0014] The beneficial effects provided by the second aspect to the fourth aspect of the embodiment of the present application are the same as those provided by the first aspect of the embodiment of the present application, and will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is an implementation flowchart of the geological disaster early warning method provided by an embodiment of the present application;

[0017] Figure 2 is a scene schematic diagram of the geological disaster early warning method provided by an embodiment of the present application;

[0018] Figure 3 is Figure 1 a specific implementation flowchart of S102 in FIG. 1;

[0019] Figure 4 is Figure 1 another specific implementation flowchart of S102 in FIG. 1;

[0020] Figure 5 is a structural block diagram of a geological disaster early warning device provided by an embodiment of the present application.

[0021] Figure 6 is a structural block diagram of a geological disaster early warning device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0023] The geological disaster early warning method related by the embodiments of the present application can be executed by a geological disaster early warning device. The geological disaster early warning device includes but is not limited to a terminal or a server. The server can be a single server or a cloud server cluster, etc., and the terminal can be a personal digital device, a notebook, a desktop computer, a smart wearable device or a robot, etc. No specific limitation is made herein.

[0024] The geological disaster early warning method related by the embodiments of the present application is applied to a geological disaster early warning for a determined geographical area, so as to effectively prevent the damage caused by the geological disaster to the environment. Specifically, the geological disaster early warning method provided by the embodiments of the present application obtains a first geological environment factor and a first influence factor in a current preset time length of a region to be early warned, respectively; and performs feature superposition analysis on each of the first geological environment factor and the first influence factor, to obtain a geological disaster prediction result of the region to be early warned. The combination of the geological environment factor and the influence factor solves the problem of inaccurate geological disaster prediction, aiming to improve the accuracy of the geological disaster prediction.

[0025] The geological disaster early warning method provided by the embodiments of the present application will be described exemplarily in combination with the accompanying drawings.

[0026] Please refer to Figure 1 shown in the figure, Figure 1 is an implementation flowchart of a geological disaster early warning method provided by an embodiment of the present application. The geological disaster early warning method provided by the embodiments of the present application can be executed by a geological disaster early warning device. The geological disaster early warning device can be a terminal and / or a server. The terminal includes but is not limited to a personal notebook, a handheld terminal, a wearable smart watch or a robot, etc.; and the server can be a single server, a server cluster, a cloud server, etc. That is, the geological disaster early warning method provided by the embodiments of the present application can be applied to any device with data processing capability, and can also be completed by interaction of multiple devices with data processing capability.

[0027] Exemplarily, as Figure 2 shown, Figure 2 is a scene schematic diagram of a geological disaster early warning method provided by an embodiment of the present application. As Figure 2 can be seen, in the embodiment, the geological disaster early warning method can be realized by a terminal and a server in cooperation. Specifically, the terminal 202 is configured to collect first geological environment factors and first influence factor factors of a to-be-early-warned region in a current preset time length, and send the collected first preset number of first geological environment factors and first influence factor factors to the server 204. The server 204 respectively performs feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors, and obtains a geological disaster prediction result of the to-be-early-warned region. Further, after determining the geological disaster prediction result of the to-be-early-warned region, the server 204 can send the geological disaster prediction result of the to-be-early-warned region to the terminal 202, so that the terminal 202 notifies the corresponding staff of the geological disaster prediction result of the to-be-early-warned region through a preset interface or through a preset notification mode. In turn, the corresponding staff can take corresponding early warning measures according to the geological disaster prediction result of the to-be-early-warned region, effectively preventing property loss caused by corresponding geological disasters in the to-be-early-warned region.

[0028] It should be understood that, in specific implementation, if the terminal has strong data processing capability, the process of respectively performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors, and obtaining the geological disaster prediction result of the to-be-early-warned region can be directly completed by the terminal. If the data processing capability of the terminal is limited, in order to improve the prediction efficiency of the geological disaster of the to-be-early-warned region, the terminal can send the collected first preset number of first geological environment factors and first influence factor factors in the to-be-early-warned region to the server for processing. In addition, the first preset number of first geological environment factors and first influence factor factors in the to-be-early-warned region can also be directly collected by the server, and then respectively performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors, and obtaining the geological disaster prediction result of the to-be-early-warned region. Specifically, it needs to be determined according to the actual scene, and nothing is limited here.

[0029] As Figure 1 can be seen, the geological disaster early warning method provided by the embodiment includes steps S101 to S102. Details are as follows:

[0030] S101, respectively acquiring first geological environment factors and first influence factor factors of a to-be-early-warned region in a current preset time length.

[0031] In a specific implementation, the first geological environmental factors include, but are not limited to, geographical position information and geological environmental conditions related to geological conditions. For example, the first geological environmental factors include at least one of the following: geographical position information of the region to be warned, slope, slope direction, elevation, landform type, stratum lithology, distance to fault, and the like. Among them, the slope is usually represented by a preset angle range, for example, can be represented as 0° to 10°, 10° to 20°; 20° to 30°; 30° to 40°; or greater than or equal to 40°, and the like.

[0032] It should be understood that the slope in different preset angle ranges has different influences on different preset types of geological disasters, and the slope in different preset angle ranges will change correspondingly over time as the type of geological disaster changes. By collecting the slope of the region to be warned in the current preset time range, the problem that the slope changes caused by historical geological disasters can be effectively prevented, and the accuracy of the geological disaster warning can be ensured. For example, when the slope is in the range of 0° to 10°, the influence on the landslide disaster caused by heavy rain is small, but when the slope is greater than or equal to 40°, the influence on the landslide disaster caused by heavy rain is large.

[0033] In addition, the slope direction can also be represented by a preset angle range, the elevation can be represented by a preset length range; the landform type includes, but is not limited to, at least one of low mountains, medium mountains or high mountains; the stratum lithology includes, but is not limited to, at least one of loose accumulation layer, soft- semi-hard thin- medium stratiform rock group, semi-hard- hard thin- medium stratiform rock group, or hard- semi-hard medium- thick stratiform rock group; and the distance to the fault can also be represented by a preset distance range, such as 0 to 500 meters, 500 to 1000 meters, 1000 meters to 1500 meters, and the like.

[0034] In an embodiment, the first influence factor includes annual average rainfall of the region to be warned, distance to house, distance to road, distance to valley, historical disaster point number of the grid unit, current day rainfall, rainfall in a preset time range, and the like.

[0035] By obtaining the first geological environmental factors and the first influence factors of the region to be warned in the current preset time range, the first geological environmental factors and the first influence factors are combined to improve the accuracy of the geological disaster warning.

[0036] S102, respectively, the first geological environmental factors and the first influence factors are analyzed by feature superposition, and the geological disaster prediction result of the region to be warned is obtained.

[0037] The process of the feature superposition analysis is a process of performing a series of set operations on the first geological environment factors and the first influence factor to generate a new influence factor. Specifically, the feature superposition analysis process can be implemented by a pre-trained geological disaster early warning model, or can be implemented by performing feature superposition combination on the associated factors in the first geological environment factors and the first influence factor. The following will be described in combination with the accompanying Figure 3 The process of the feature superposition analysis is a process of performing a series of set operations on the first geological environment factors and the first influence factor to generate a new influence factor. Specifically, the feature superposition analysis process can be implemented by a pre-trained geological disaster early warning model, or can be implemented by performing feature superposition combination on the associated factors in the first geological environment factors and the first influence factor. The following will be described in combination with the accompanying Figure 4 The process of the feature superposition analysis is a process of performing a series of set operations on the first geological environment factors and the first influence factor to generate a new influence factor. Specifically, the feature superposition analysis process can be implemented by a pre-trained geological disaster early warning model, or can be implemented by performing feature superposition combination on the associated factors in the first geological environment factors and the first influence factor. The following will be described in combination with the accompanying

[0038] Please refer to Figure 3 , as shown in Figure 3 is Figure 1 a specific implementation flowchart of S102 in the embodiment. As can be seen from Figure 3 , in the embodiment, S102 includes S1021 and S1022. Details are as follows:

[0039] S1021, input each of the first geological environment factors and each of the first influence factor into a pre-trained geological disaster early warning model.

[0040] The training process of the pre-trained geological disaster early warning model includes: obtaining a preset number of second geological environment factors and a preset category of geological disasters corresponding to second influence factor factors in a preset time period; performing superposition analysis on the second geological environment factors and the second influence factor factors to obtain a preset proportion of positive samples and negative samples; and performing data-driven training on the preset geological disaster early warning model based on the positive samples and the negative samples to obtain the geological disaster early warning model.

[0041] The second geological environment factor is a factor related to the geological condition in different preset regions, which can include the same factors as the first geological environment factor, or more factors than the first geological environment factor. The specific implementation is not limited here. The second influence factor factor corresponds to a factor that has an influence on the geological condition in different preset regions, which can include the same factors as the first influence factor factor, or more factors than the first influence factor factor. The specific implementation is not limited here. In this embodiment, the second geological environment factor and the second influence factor factor are combined to perform superposition analysis to obtain a preset proportion of positive samples and negative samples, so as to improve the early warning accuracy of the trained geological disaster early warning model.

[0042] Specifically, by performing superposition analysis on the second geological environment factor, such as the geological environment factor, and the second influence factor factor, such as the rainfall inducing factor, and the early warning grid division unit, the geological environment feature library and the geological influence factor feature library are obtained, and then each factor in the geological environment feature library and the geological influence factor feature library is superimposed and analyzed to obtain positive samples and negative samples.

[0043] Exemplarily, the superimposed analysis on the second geological environment factors and the second influence factor factors obtains positive samples and negative samples in a preset proportion, including: respectively determining first influence weights of each of the second geological environment factors and each of the second influence factor factors on different preset categories of geological disasters, and an association relationship between each of the second geological environment factors and each of the second influence factor factors; determining first key geological environment factors and first key influence factor factors according to the first influence weights and the association relationship; and reclassifying the first key geological environment factors and the first key influence factor factors to obtain the positive samples and the negative samples in the preset proportion.

[0044] Specifically, the positive samples include: influence elements affecting geological disasters of different preset categories. For example, the positive samples are spatial geographic coordinates and time coordinates determined for historical landslide disaster points. The spatial geographic coordinates can be set, and the time coordinates require higher accuracy.

[0045] The negative samples include: buffer element information of the influence elements. For example, the negative samples are buffer radii of 3 times of a pre-warning grid unit randomly sampled outside a certain buffer zone of the positive samples. The corresponding preset proportion can be determined through experimental data. Experiments show that the number ratio of the positive samples to the negative samples is 1:2.

[0046] In addition, after obtaining the positive samples and the negative samples, missing value imputation, elimination, and outlier identification can be performed through feature attribute extraction and data cleaning techniques.

[0047] S1022, analyzing the first geological environment factors and the first influence factor factors based on the geological disaster early warning model to obtain a geological disaster prediction result of a region to be warned.

[0048] Specifically, the geological disaster early warning model can be a model with the highest accuracy and the best model generalization ability obtained through model parameter evaluation after training a random forest model, a nearest neighbor model, a decision tree model, a support vector machine model, a logistic regression model, or a neural network model based on training samples (including positive samples and negative samples in a preset proportion) by using a Bayesian optimization algorithm and a five-fold cross-validation method.

[0049] Please refer to Figure 4 , which is Figure 4 another specific implementation flowchart of S102 in Figure 1 . As can be seen, in the present embodiment, S102 includes S1023 to S1025. Details are as follows: Figure 4

[0050] ​S1023, respectively determine a second influence weight of each of the first geological environment factors and each of the first influence factor factors on different preset category geological disasters, and a second correlation between each of the first geological environment factors and each of the first influence factor factors.

[0051] S1024, according to the second influence weight and the second correlation, determining at least two second key geological environment factors and at least two second key influence factor factors.

[0052] S1025, data conversion is performed on each of the second key geological environment factors and each of the second key influence factor factors, and feature superposition combination is performed on the data obtained after conversion to obtain a geological disaster prediction result of the region to be warned.

[0053] Specifically, the determination process of the influence weight and the correlation is not limited in any specific way, and can use hierarchical method and optimal sequence diagram method, entropy method, information amount method, principal component method or factor analysis method, etc.

[0054] In addition, the process of data conversion on each of the second key geological environment factors and each of the second key influence factor factors includes: normalizing each of the second key geological environment factors and each of the second key influence factor factors to obtain factor relationship matrix data; and converting the factor relationship matrix data into factor column data. The factor column data represents the influence coefficient of the factor having a key influence on the geological disaster.

[0055] The feature superposition combination on the data obtained after conversion to obtain the geological disaster prediction result of the region to be warned includes: linear superposition of the influence coefficient represented by the factor column data based on a linear function to obtain the probability of occurrence of the geological disaster of the preset category and the warning level in the region to be warned.

[0056] Through the above analysis, it can be known that the geological disaster warning method provided by the embodiment of the application includes: acquiring first geological environment factors and first influence factor factors of a region to be warned within a preset time length; respectively performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the region to be warned. By performing feature superposition analysis on the first geological environment factors and the first influence factor factors in the region to be warned, the combination of the geological environment factors and the influence factor factors is realized, the problem of inaccurate prediction of the geological disaster is solved, and the accuracy of the prediction of the geological disaster is improved.

[0057] Please refer to Figure 5 as shown, Figure 5is a structural block diagram of a geological disaster early warning device provided by an embodiment of the present application. The geological disaster early warning device 500 in the embodiment can be deployed in a server or a terminal, and is used for predicting geological disasters in a region to be warned. Specifically, each module included in the geological disaster early warning device 500 is used to perform each step in the method embodiments. For details, please refer to Figures 1 to 4 the related description in the corresponding embodiments. The functions of the geological disaster early warning device 500 can be implemented by software or hardware inside the server or the terminal. Specifically, the functions of the geological disaster early warning device 500 can be logically divided into different modules. For the convenience of description, only the parts related to the present embodiment are shown. Referring to Figure 5 , the geological disaster early warning device 500 includes:

[0058] A first obtaining module 501 is configured to respectively obtain a region to be warned, first geological environment factors and first influence factor factors within a preset time length.

[0059] A first analysis module 502 is configured to respectively perform feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors, to obtain a geological disaster prediction result of the region to be warned.

[0060] In an embodiment, the analysis module 502 is specifically configured to:

[0061] input each of the first geological environment factors and each of the first influence factor factors into a pre-trained geological disaster early warning model to perform feature superposition analysis, to obtain the geological disaster prediction result of the region to be warned.

[0062] In an embodiment, the device 500 further includes:

[0063] A second obtaining module is configured to obtain a preset number of second geological environment factors and a preset category of geological disasters corresponding to second influence factor factors within a preset time period.

[0064] A second analysis module is configured to perform superposition analysis on the second geological environment factors and the second influence factor factors, to obtain positive samples and negative samples in a preset proportion.

[0065] A training module is configured to perform data-driven training on a preset geological disaster early warning model based on the positive samples and the negative samples, to obtain the geological disaster early warning model.

[0066] In an embodiment, the second analysis module includes:

[0067] The first determining unit is configured to determine first influence weights of each second geological environment factor and each second influence factor on different preset types of geological disasters, and an association relationship between the second geological environment factors and the second influence factors.

[0068] The second determining unit is configured to determine first key geological environment factors and first key influence factors according to the first influence weights and the association relationship.

[0069] The classifying unit is configured to reclassify the first key geological environment factors and the first key influence factors to obtain the positive samples and the negative samples in a preset proportion.

[0070] In an embodiment, the positive samples include influence elements affecting different preset types of geological disasters, and the negative samples include buffer element information of the influence elements.

[0071] In an embodiment, the first analysis module 502 includes:

[0072] The third determining unit is configured to determine second influence weights of each first geological environment factor and each first influence factor on different preset types of geological disasters, and a second association relationship between the first geological environment factors and the first influence factors.

[0073] The fourth determining unit is configured to determine at least two second key geological environment factors and at least two second key influence factors according to the second influence weights and the second association relationship.

[0074] The analysis unit is configured to perform data conversion on the second key geological environment factors and the second key influence factors, and perform feature superposition and combination on data obtained after the conversion to obtain a geological disaster prediction result of the region to be warned.

[0075] In an embodiment, the analysis unit includes:

[0076] The determining subunit is configured to determine influence degrees of each second key geological environment factor and each second key influence factor on disaster elements corresponding to different preset types of geological disasters.

[0077] The conversion subunit is configured to perform weight factor conversion on each second key geological environment factor and each second key influence factor according to the influence degrees to obtain different weight factors affecting different preset types of geological disasters.

[0078] The analysis subunit is configured to perform superposition and combination analysis on the different weight factors to obtain the geological disaster prediction result of the region to be warned.

[0079] It should be understood that, Figure 5 In the structural block diagram of the geological disaster early warning device 500 shown, each module is used to perform... Figures 1 to 4 The steps in the corresponding embodiments, and for Figures 1 to 4 The steps in the corresponding embodiments have been explained in detail in the above embodiments. Please refer to them for details. Figures 1 to 4 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0080] Please see Figure 6 As shown, Figure 6 This is a structural block diagram of the geological disaster early warning device provided in the embodiments of this application. For example... Figure 6 As shown, the geological disaster early warning device 600 of this embodiment includes: a processor 610, a memory 620, and a computer program 630 stored in the memory 620 and executable on the processor 610, such as a geological disaster early warning program. When the processor 610 executes the computer program 630, it implements the steps in the various embodiments of the above-described geological disaster early warning methods, for example... Figures 1 to 4 The steps shown. Alternatively, the processor 610 may implement the above when executing the computer program 630. Figure 5 The functions of each module or unit in the corresponding embodiments, for example, Figure 5 For details on the functions of modules 501 to 502 shown, please refer to [link / reference needed]. Figure 5 The relevant descriptions in the corresponding embodiments are not repeated here.

[0081] For example, the computer program 630 can be divided into one or more units, which are stored in the memory 620 and executed by the processor 610 to complete this application. The one or more units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 630 in the geological disaster early warning device 600. For example, the computer program 630 can be divided into: an acquisition module and an analysis module; the specific functions of each module are as follows: Figure 5 As stated above.

[0082] The geological disaster early warning device 600 may include, but is not limited to, a processor 610 and a memory 620. Those skilled in the art will understand that... Figure 4 This is merely an example of a geological disaster early warning device 600 and does not constitute a limitation on the geological disaster early warning device 600. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the geological disaster early warning device 600 may also include input / output devices, network access devices, buses, etc.

[0083] The processor 610 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0084] In one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps:

[0085] Obtaining a first geological environment factor and a first influence factor in a current preset time period in the region to be warned, respectively;

[0086] Performing feature superposition analysis on each of the first geological environment factors and each of the first influence factors to obtain a geological disaster prediction result of the region to be warned.

[0087] In one embodiment, the feature superposition analysis on each of the first geological environment factors and each of the first influence factors to obtain the geological disaster prediction result of the region to be warned includes:

[0088] Inputting each of the first geological environment factors and each of the first influence factors into a pre-trained geological disaster warning model to perform feature superposition analysis and obtain the geological disaster prediction result of the region to be warned.

[0089] In one embodiment, before the feature superposition analysis on each of the first geological environment factors and each of the first influence factors, the method further includes:

[0090] Obtaining a second geological environment factor of a preset number and a second influence factor of a preset category corresponding to a geological disaster in a preset time period;

[0091] Performing superposition analysis on the second geological environment factor and the second influence factor to obtain a positive sample and a negative sample of a preset proportion;

[0092] Performing data-driven training on a preset geological disaster warning model based on the positive sample and the negative sample to obtain the geological disaster warning model.

[0093] In an embodiment, the superimposed analysis of the second geological environment factors and the second influence factor factors obtains positive samples and negative samples of a preset proportion, including:

[0094] The first influence weight of each of the second geological environment factors and each of the second influence factor factors on different preset categories of geological disasters is determined, and the correlation between each of the second geological environment factors and each of the second influence factor factors is determined.

[0095] According to the first influence weight and the correlation, first key geological environment factors and first key influence factor factors are determined.

[0096] The first key geological environment factors and the first key influence factor factors are reclassified to obtain the positive samples and the negative samples of the preset proportion.

[0097] In an embodiment, the positive samples include influence elements affecting different preset categories of geological disasters, and the negative samples include buffer element information of the influence elements.

[0098] In an embodiment, the feature superimposed analysis of each of the first geological environment factors and each of the first influence factor factors obtains a geological disaster prediction result of the area to be warned, including:

[0099] The second influence weight of each of the first geological environment factors and each of the first influence factor factors on different preset categories of geological disasters is determined, and a second correlation between each of the first geological environment factors and each of the first influence factor factors is determined.

[0100] According to the second influence weight and the second correlation, at least two second key geological environment factors and at least two second key influence factor factors are determined.

[0101] Data conversion is performed on each of the second key geological environment factors and each of the second key influence factor factors, and feature superimposed combination is performed on data obtained after the conversion to obtain the geological disaster prediction result of the area to be warned.

[0102] In an embodiment, the data conversion of each of the second key geological environment factors and each of the second key influence factor factors and the feature superimposed combination of the converted data obtain the geological disaster prediction result of the area to be warned, including:

[0103] The influence degree of each of the second key geological environment factors and each of the second key influence factor factors on disaster elements corresponding to different preset categories of geological disasters is determined.

[0104] The second key geological environment factors and the second key influence factor are respectively converted into weight factors according to the influence degrees, so as to obtain different weight factors of geological disasters influencing different preset categories;

[0105] The different weight factors are superimposed and combined for analysis, so as to obtain a geological disaster prediction result of the area to be warned.

[0106] The memory 620 can be an internal storage unit of the geological disaster warning device 600, for example, a hard disk or a memory of the geological disaster warning device 600. The memory 620 can also be an external storage device of the geological disaster warning device 600, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the geological disaster warning device 600. Further, the memory 620 can include both the internal storage unit and the external storage device of the geological disaster warning device 600. The memory 620 is used to store the computer program and other programs and data required by the geological disaster warning device 600. The memory 620 can also be used to temporarily store data that has been output or will be output.

[0107] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program. The computer program includes program instructions. The processor executes the program instructions to realize the steps of the geological disaster warning method provided in the above embodiments.

[0108] The computer readable storage medium can be an internal storage unit of the geological disaster warning device, for example, a hard disk or a memory of the geological disaster warning device. The computer readable storage medium can also be an external storage device of the geological disaster warning device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the geological disaster warning device.

[0109] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the same. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features. The modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A geological disaster early warning method, characterized by, The method comprises: respectively acquiring first geological environment factors and first influence factor factors of a region to be prewarned in a preset time length; respectively performing feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain a geological disaster prediction result of the region to be prewarned; wherein the influence factor factors comprise: annual average rainfall of the region to be prewarned, distance from a house, distance from a road, distance from a valley, historical disaster point number of a grid unit, rainfall on the day, and rainfall in the preset time length range; the feature superposition analysis on each of the first geological environment factors and each of the first influence factor factors to obtain the geological disaster prediction result of the region to be prewarned comprises: determining second influence weights of each of the first geological environment factors and each of the first influence factor factors on different preset category geological disasters, and a second correlation relationship between each of the first geological environment factors and each of the first influence factor factors; determining at least two second key geological environment factors and at least two second key influence factor factors according to the second influence weights and the second correlation relationship; performing data conversion on each of the second key geological environment factors and each of the second key influence factor factors, and performing feature superposition combination on data obtained after the conversion to obtain the geological disaster prediction result of the region to be prewarned; the data conversion on each of the second key geological environment factors and each of the second key influence factor factors comprises: performing normalization processing on each of the second key geological environment factors and each of the second key influence factor factors to obtain factor relationship matrix data; and converting the factor relationship matrix data into factor column data, wherein the factor column data represents an influence coefficient of a factor having a key influence on a geological disaster; the feature superposition combination on the data obtained after the conversion to obtain the geological disaster prediction result of the region to be prewarned comprises: performing linear superposition on the influence coefficient represented by the factor column data based on a linear function to obtain a probability of occurrence of a preset category geological disaster and a prewarning level of the region to be prewarned.

2. The geological disaster early warning method according to claim 1, wherein The method further comprises: acquiring a preset number of second geological environment factors and second influence factor factors corresponding to a preset category of geological disasters in a preset time period; performing superposition analysis on the second geological environment factors and the second influence factor factors to obtain a preset proportion of positive samples and negative samples; performing data-driven training on a preset geological disaster prewarning model based on the positive samples and the negative samples to obtain the geological disaster prewarning model.

3. The geological disaster early warning method according to claim 2, wherein the superposition analysis on the second geological environment factors and the second influence factor factors to obtain the preset proportion of positive samples and negative samples comprises: determining first influence weights of each of the second geological environment factors and each of the second influence factor factors on different preset category geological disasters, and a correlation relationship between each of the second geological environment factors and each of the second influence factor factors; determining first key geological environment factors and first key influence factor factors according to the first influence weights and the correlation relationship; The first key geological environment factor and the first key influence factor are reclassified to obtain a preset proportion of the positive samples and the negative samples.

4. The geological disaster early warning method according to claim 3, wherein The positive samples include influence elements of geological disasters of different preset categories, and the negative samples include buffer element information of the influence elements.

5. The geological disaster early warning method of claim 1, wherein, The data conversion of each of the second key geological environment factors and each of the second key influence factors is performed, and the geological disaster prediction result of the area to be warned is obtained by performing feature superposition and combination on the converted data, including: The influence degree of each of the second key geological environment factors and each of the second key influence factors on disaster elements corresponding to geological disasters of different preset categories is determined respectively; According to the influence degree, each of the second key geological environment factors and each of the second key influence factors is converted by a weight factor to obtain different weight factors of geological disasters of different preset categories; The different weight factors are superimposed and combined to obtain the geological disaster prediction result of the area to be warned.

6. A geological disaster early warning device characterized by comprising: The device includes: An acquisition module is configured to acquire a first geological environment factor and a first influence factor in a current preset time period in an area to be warned. An analysis module is configured to perform feature superposition analysis on each of the first geological environment factors and each of the first influence factors to obtain a geological disaster prediction result of the area to be warned. The influence factor includes: annual average rainfall, distance from house, distance from road, distance from valley, historical disaster point number of grid unit, current day rainfall, and rainfall in a preset time period. The analysis module is further configured to: Determine a second influence weight of each of the first geological environment factors and each of the first influence factors on geological disasters of different preset categories, and a second correlation between each of the first geological environment factors and each of the first influence factors. According to the second influence weight and the second correlation, at least two second key geological environment factors and at least two second key influence factors are determined. Data conversion is performed on each of the second key geological environment factors and each of the second key influence factors, and feature superposition and combination are performed on the converted data to obtain the geological disaster prediction result of the area to be warned. The data conversion of each of the second key geological environment factors and each of the second key influence factors includes: normalizing each of the second key geological environment factors and each of the second key influence factors to obtain factor relationship matrix data; and converting the factor relationship matrix data into factor column data, wherein the factor column data represents an influence coefficient of a factor having a key influence on geological disasters. The feature superposition and combination of the converted data includes: performing linear superposition on the influence coefficient represented by the factor column data based on a linear function to obtain a probability of occurrence of a geological disaster of a preset category and a warning level in the area to be warned. 7.A geological disaster early warning device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the geological disaster early warning method as claimed in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program, when executed by the processor, implements the steps of the geological disaster early warning method as claimed in any one of claims 1 to 5.

Images