Geological disaster risk prediction method, device, equipment, medium and product

Abstract

The invention relates to a geological disaster risk prediction method and device, equipment, a medium and a product. The method comprises the following steps: acquiring target state information corresponding to a power grid tower in a target time interval, wherein the target state information comprises a target influence factor; a target risk index is obtained according to the target state information and a target risk prediction model, the target risk prediction model is obtained by screening according to the multicollinearity and importance of historical impact factors and importing an initial risk prediction model for training, and the historical impact factors are data corresponding to the target impact factors in a historical time interval; and obtaining a target risk level corresponding to the target area according to the target risk index. By adopting the method, the target risk level prediction accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of power grid towers, and in particular to a method, device, equipment, medium and product for predicting geological disaster risks. Background Art

[0002] With climate change and the increase in extreme weather events, areas where power grid towers are located are often threatened by geological disasters such as collapse and landslides.

[0003] In traditional technology, the geological disaster risk prediction method for power grid towers is based on manual surveys, statistical models or machine learning models, and the geological disaster risk of power grid towers in the target time interval is evaluated based on the geological disasters that have occurred.

[0004] However, the current geological disaster risk prediction methods have the problem of low accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a geological disaster risk prediction method, device, equipment, medium and product that can improve prediction accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for predicting geological disaster risks, the method comprising:

[0007] Methods include:

[0008] Obtaining target state information corresponding to the power grid tower within the target time interval, the target state information including the target influencing factor;

[0009] According to the target status information and the target risk prediction model, the target risk index is obtained. The target risk prediction model is obtained by screening according to the multicollinearity and importance of historical impact factors and importing the initial risk prediction model for training. The historical impact factor is the data corresponding to the target impact factor in the historical time interval;

[0010] According to the target risk index, the target risk level corresponding to the target area is obtained.

[0011] In one embodiment, the target state information also includes target disaster-prone body information, and the target risk prediction model includes a susceptibility prediction module and a vulnerability prediction module; a target risk index is obtained according to the target state information and the target risk prediction model, including:

[0012] Input the target impact factor into the susceptibility prediction module to obtain the susceptibility index;

[0013] Input the target disaster-bearing body information and target influencing factors into the vulnerability prediction module to obtain the vulnerability index;

[0014] The susceptibility index and vulnerability index are superimposed and coupled to obtain the target risk index.

[0015] In one embodiment, the susceptibility index and the vulnerability index are superimposed and coupled to obtain a target risk index, including: multiplying the susceptibility index and the vulnerability index to obtain the target risk index.

[0016] In one of the embodiments, obtaining a target risk level corresponding to a target area according to a target risk index includes: performing level matching processing on the target risk index according to a preset level matching condition to obtain the target risk level.

[0017] In one embodiment, the method further comprises:

[0018] Obtain historical impact factors, historical disaster information and initial risk prediction models;

[0019] Based on the multicollinearity and importance of historical impact factors, the characteristic impact factors are screened and determined from the historical impact factors;

[0020] Based on the characteristic influencing factors and historical disaster information, a training set is obtained;

[0021] The initial risk prediction model is trained using the training set to obtain the target risk prediction model.

[0022] In one embodiment, determining a characteristic impact factor from the historical impact factor based on multicollinearity and importance corresponding to the historical impact factor includes:

[0023] Perform collinearity analysis on the historical impact factors to obtain the collinearity index corresponding to the historical impact factors;

[0024] Calculate the importance of the historical impact factor to obtain the importance index corresponding to the historical impact factor;

[0025] When both the collinearity index and the importance index meet the preset conditions, the historical impact factor is used as the characteristic impact factor.

[0026] In a second aspect, the present application also provides a geological disaster risk prediction device, the device comprising:

[0027] An information acquisition module is used to acquire target state information corresponding to the power grid tower within a target time interval, wherein the target state information includes a target influencing factor;

[0028] The index prediction module is used to obtain the target risk index based on the target state information and the target risk prediction model. The target risk prediction model is obtained by screening based on the multicollinearity and importance of historical impact factors and importing the initial risk prediction model for training. The historical impact factor is the data corresponding to the target impact factor in the historical time interval;

[0029] The level matching module is used to obtain the target risk level corresponding to the target area according to the target risk index.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method of the first aspect are implemented.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the first aspect when the computer program is executed by a processor.

[0032] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the method of the first aspect when executed by a processor.

[0033] The above-mentioned geological disaster risk prediction method, device, equipment, medium and product, on the one hand, provides a geological disaster risk prediction method by obtaining the target state information corresponding to the power grid tower within the target time interval, the target state information includes the target impact factor; according to the target state information and the target risk prediction model, the target risk index is obtained, the target risk prediction model is screened according to the multicollinearity and importance of the historical impact factor, and imported into the initial risk prediction model for training, the historical impact factor is the data corresponding to the target impact factor within the historical time interval; according to the target risk index, the target risk level corresponding to the target area is obtained. In this way, the initial risk prediction model is trained according to the multicollinearity and importance of the historical impact factor to obtain the target risk prediction model, which can effectively improve the robustness and generalization ability of the target risk prediction model; using the target state information of the power grid tower and the target risk prediction model to predict the target risk index, it is possible to more accurately evaluate the disaster risk of the disaster address corresponding to the power grid tower in the target area, thereby improving the accuracy of the geological disaster risk prediction method. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 An application environment diagram of a geological disaster risk prediction method in an embodiment;

[0036] Figure 2 A schematic diagram of a flow chart of a method for predicting geological disaster risks in one embodiment;

[0037] Figure 3 A schematic diagram of a flow chart of a method for predicting geological disaster risks in another embodiment;

[0038] Figure 4 A structural block diagram of a geological disaster risk prediction device in one embodiment;

[0039] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction 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.

[0041] The geological disaster risk prediction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the target state information corresponding to the power grid tower in the target time interval from the terminal 102, and the target state information includes the target impact factor; according to the target state information and the target risk prediction model, the target risk index is obtained. The target risk prediction model is screened according to the multicollinearity and importance of the historical impact factor, and is imported into the initial risk prediction model for training. The historical impact factor is the data corresponding to the target impact factor in the historical time interval; according to the target risk index, the target risk level corresponding to the target area is obtained.

[0042] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices, and the portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0043] In an exemplary embodiment, Figure 2 As shown in the figure, a geological disaster risk prediction method is provided. Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 202 to 206. Among them:

[0044] Step 202: Obtain target state information corresponding to the power grid tower within the target time interval, where the target state information includes a target impact factor.

[0045] The target time interval refers to the time interval before or including the forecast time node. The target influencing factors related to disaster risks include terrain factors, geological factors, meteorological factors and seismic factors. Terrain factors can include elevation, slope, slope aspect, terrain moisture index and terrain undulation; geological factors can include soil type and rock structure; meteorological factors can include annual rainfall and wind speed; seismic factors can include ground peak acceleration.

[0046] Optionally, in the process of geological hazard risk prediction, the spatial resolution of the target influencing factors related to the disaster risk needs to be consistent to ensure the comparability of the data and the accuracy of the risk prediction results. Spatial resolution refers to the degree of refinement of geographic data, usually expressed as the actual ground area covered by each pixel. For example, the spatial resolution of the target influencing factors related to the disaster risk is 30 meters, that is, each pixel represents an area of ​​30 meters × 30 meters.

[0047] The target state information may also include the disaster-prone body information within the target time interval. The disaster-prone body information may include the geographical location, operation time, structure type, height, design bearing capacity, historical damage and maintenance records of the power grid towers in the target area. The geographical location may include the longitude and latitude coordinates of the power grid towers; the structure type may include the type of material used to construct the power grid towers, such as steel towers, iron towers or concrete towers.

[0048] Step 204, obtaining a target risk index according to the target state information and the target risk prediction model.

[0049] Among them, the target risk prediction model is obtained by screening according to the multicollinearity and importance of historical impact factors, and importing the initial risk prediction model for training. The historical impact factors are the data corresponding to the target impact factors in the historical time interval.

[0050] Among them, multicollinearity is used to evaluate the correlation between historical influencing factors. When multicollinearity exists, the value of an independent variable in the initial risk prediction model can be well predicted by the linear combination of other independent variables. For small disturbances in the training data, the regression coefficient may fluctuate greatly, and the model is difficult to explain and replicate. The independent variables have too much redundant information, and the model cannot effectively learn independent and meaningful features, which may cause the model to "overfit", thereby affecting the prediction effect of the target risk prediction model.

[0051] Among them, importance is used to evaluate the contribution of historical impact factors to the target risk index during the classification process. Historical impact factors with low importance have low contribution to the target risk index. In the process of training the initial risk prediction model, eliminating historical impact factors with low importance can reduce the model's over-learning of irrelevant features, reduce the time and memory required for model training, facilitate model optimization and parameter adjustment, and improve training efficiency.

[0052] In a possible implementation, the target state information also includes target disaster-prone body information, and the target risk prediction model includes a susceptibility prediction module and a vulnerability prediction module. Step 204 may further include: inputting the target impact factor into the susceptibility prediction module to obtain a susceptibility index S; inputting the target disaster-prone body information and the target impact factor into the vulnerability prediction module to obtain a vulnerability index V; and performing superposition coupling processing on the susceptibility index S and the vulnerability index V to obtain a target risk index R.

[0053] In a possible implementation, superimposing and coupling the susceptibility index S and the vulnerability index V means multiplying the susceptibility index S and the vulnerability index V to obtain a target risk index R. The target risk index R can be expressed as:

[0054] R=S·V.

[0055] Step 206, obtaining the target risk level corresponding to the target area according to the target risk index.

[0056] In a possible implementation, step 206 may further include: performing level matching processing on the target risk index according to a preset level matching condition to obtain a target risk level.

[0057] Exemplarily, the numerical range corresponding to the target risk index is 0-1, and the level matching conditions may include five risk levels. The target risk index is 0.8-1.0, and the target risk level is an extremely high risk area; the target risk index is 0.6-0.8, and the target risk level is a high risk area; the target risk index is 0.4-0.6, and the target risk level is a medium risk area; the target risk index is 0.2-0.4, and the target risk level is a low risk area; the target risk index is 0.0-0.2: the target risk level is an extremely low risk area.

[0058] In the above-mentioned geological disaster risk prediction method, the target state information corresponding to the power grid tower within the target time interval is obtained, and the target state information includes the target impact factor; according to the target state information and the target risk prediction model, the target risk index is obtained, and the target risk prediction model is obtained by screening according to the multicollinearity and importance of the historical impact factor, and importing the initial risk prediction model for training, and the historical impact factor is the data corresponding to the target impact factor within the historical time interval; according to the target risk index, the target risk level corresponding to the target area is obtained. In this way, the initial risk prediction model is trained according to the multicollinearity and importance of the historical impact factor to obtain the target risk prediction model, which can effectively improve the robustness and generalization ability of the target risk prediction model; using the target state information of the power grid tower and the target risk prediction model to predict the target risk index, it is possible to more accurately evaluate the disaster risk of the disaster address corresponding to the power grid tower in the target area, thereby improving the accuracy of the geological disaster risk prediction method.

[0059] In an exemplary embodiment, the provided method also includes: obtaining historical influencing factors, historical disaster information and an initial risk prediction model; screening and determining characteristic influencing factors from the historical influencing factors based on the multicollinearity and importance corresponding to the historical influencing factors; obtaining a training set based on the characteristic influencing factors and historical disaster information; and using the training set to train the initial risk prediction model to obtain a target risk prediction model.

[0060] Among them, historical disaster information includes historical disaster-prone body information and historical geological disaster information. Historical geological disaster information refers to the historical geological disasters in the target area, which can be obtained by combining the interpretation of high-resolution, low-cloud coverage optical remote sensing images in the target area and literature research. The selection criteria for high-resolution, low-cloud coverage optical remote sensing images should ensure that the resolution of the image is not less than 3 meters and the cloud coverage is less than 10% to ensure the clarity and accuracy of the image. The historical geological disasters may include but are not limited to landslides, mudslides, collapses and other types, as well as key information such as the location, boundaries, types, scales, and occurrence times of these geological disasters. Historical disaster-prone body information refers to the disaster-prone body information within the historical time interval.

[0061] Exemplarily, multicollinearity can be determined based on a correlation coefficient matrix by calculating the Pearson correlation coefficient between each historical impact factor to generate a correlation coefficient matrix. If the correlation coefficient between two historical impact factors is greater than a preset threshold, it means that they may be highly collinear.

[0062] For example, in tree-based models such as random forests and gradient boosting decision trees, the importance of historical impact factors can be evaluated based on mean decrease in mean square error (Mean Decrease in MSE) or mean decrease in accuracy (Mean Decrease in Accuracy); in models based on linear regression, logistic regression, and support vector machine algorithms, the importance of historical impact factors can be evaluated based on weight coefficients.

[0063] In one possible implementation, based on the multicollinearity and importance corresponding to the historical impact factors, the process of determining the characteristic impact factors from the historical impact factors may further include: performing collinearity analysis on the historical impact factors to obtain the collinearity index corresponding to the historical impact factors; performing importance calculation on the historical impact factors to obtain the importance index corresponding to the historical impact factors; and when both the collinearity index and the importance index meet preset conditions, using the historical impact factors as characteristic impact factors.

[0064] Among them, collinearity analysis refers to calculating the variance inflation factor (VIF) corresponding to the historical impact factor. The process of obtaining the collinearity index corresponding to the historical impact factor specifically includes: for each historical impact factor, linear regression processing is performed on the historical impact factor, using it as the target variable and other impact factors as independent variables. Variance inflation factor VIF corresponding to historical impact factor i i It can be expressed as:

[0065] ,

[0066] in, is the determination coefficient between historical impact factor i and other historical impact factors.

[0067] When the variance inflation factor VIF i When VIF is less than 10, it indicates that the collinearity problem of historical impact factor i is not serious and can be used to train the initial risk prediction model. i When ≥10, it means that the historical impact factor i has serious collinearity and is not suitable for training the initial risk prediction model.

[0068] Among them, the importance calculation process refers to calculating the Gini importance (GiniImportance) corresponding to the historical impact factor. The process of obtaining the importance index specifically includes: for each decision tree, calculating the Gini index GI before and after the node split. The calculation formula of the Gini index GI is:

[0069] ,

[0070] Among them, when the historical impact factor i is used to split a node in the decision tree, the change in the Gini index before and after the node split is calculated:

[0071] ,

[0072] For each tree, the changes in the Gini index of all nodes with historical impact factor i are accumulated to obtain the Gini importance IMi in the tree:

[0073] ,

[0074] Among them, j represents the total number of occurrences of impact factor i in the tree.

[0075] For all decision trees in the random forest, take the average value to obtain the overall Gini importance of historical impact factor i, that is, the importance index:

[0076] ,

[0077] Where N is the total number of decision trees in the random forest.

[0078] The larger the value of the importance index is, the greater the contribution of the historical impact factor i to the prediction effect of the model.

[0079] Exemplarily, the preset condition may include: taking a historical impact factor whose collinearity index is lower than a preset collinearity index threshold and whose importance index is greater than 0 as a characteristic impact factor.

[0080] In one possible implementation, the process of constructing a training set may include: constructing a disaster-prone body database based on characteristic influencing factors and historical disaster-prone body information in historical disaster information; constructing a disaster database based on characteristic influencing factors and historical geological disaster information in historical disaster information; extracting data from the disaster-prone body database and the disaster database according to a preset ratio to form a training set.

[0081] Optionally, in combination with the above-mentioned embodiment, the initial risk prediction model includes an initial susceptibility prediction module and an initial vulnerability prediction module. For the training set of the initial susceptibility prediction module, positive samples are selected from the disaster database in the area where geological disasters have occurred to construct a disaster sample set; negative samples are selected in the area with low risk or no risk of geological disasters to construct a non-disaster sample set. The ratio of positive samples to negative samples is consistent with the area ratio of the corresponding area, and both positive samples and negative samples are generated by randomly sampling points in the corresponding area. The training set data composed of positive samples and negative samples may account for 70% of the total data, and the remaining 30% is used as a test set. For the initial vulnerability prediction module, data is selected from the disaster-prone body database to construct a training set, and the historical disaster-prone body information corresponding to the damaged power grid tower is used as a positive sample, and the corresponding label is "vulnerable"; the historical disaster-prone body information corresponding to the undamaged or lightly damaged power grid tower is used as a negative sample, and the corresponding label is "non-vulnerable". The training set data composed of positive samples and negative samples may account for 70% of the total data, and the remaining 30% is used as a test set.

[0082] Among them, the initial risk prediction model and the target risk prediction model can be prediction models based on random forest, logistic regression, support vector machine or gradient boosting decision tree. The process of training the initial risk prediction model using the training set may include: standardizing or normalizing the historical impact factors to make the value range of each historical impact factor consistent, so as to prevent the model from errors caused by historical impact factors of different scales; writing code based on Python language to build the model, setting the initial parameters of the random forest model, including: the number of trees, maximum depth, and minimum number of sample splits; using the training set to train the random forest model; using the validation set or cross-validation to evaluate the performance of the model, and using the confusion matrix to evaluate the prediction accuracy; the AUC-ROC (Area Under Curve-Receiver Operating Characteristic curve, receiver operating characteristic-area under the line) curve evaluates the model's ability to distinguish different disaster levels; the recall rate and F1 score ensure the prediction accuracy of the model; when the evaluation results meet the preset conditions, the target risk prediction model is obtained.

[0083] In an exemplary embodiment, Figure 3 As shown in the figure, a geological disaster risk prediction method is provided. Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 301 to 306. Among them:

[0084] Step 301, obtaining historical impact factors, historical disaster information and an initial risk prediction model.

[0085] Step 302: Perform collinearity analysis on the historical impact factors to obtain collinearity indexes corresponding to the historical impact factors.

[0086] Step 303: perform importance calculation processing on the historical impact factor to obtain the importance index corresponding to the historical impact factor.

[0087] Step 304: When both the collinearity index and the importance index meet the preset conditions, the historical impact factor is used as the characteristic impact factor.

[0088] Step 305: obtaining a training set based on characteristic influencing factors and historical disaster information.

[0089] Step 306, using the training set to train the initial risk prediction model to obtain a target risk prediction model.

[0090] Step 307, obtaining target state information corresponding to the power grid tower within the target time interval, where the target state information includes a target impact factor.

[0091] The target state information also includes target disaster-prone body information, and the target risk prediction model includes a susceptibility prediction module and a vulnerability prediction module.

[0092] Step 308, input the target impact factor into the susceptibility prediction module to obtain the susceptibility index.

[0093] Step 309: input the target disaster-prone body information and the target impact factor into a vulnerability prediction module to obtain a vulnerability index.

[0094] Step 310, multiply the susceptibility index and the vulnerability index to obtain a target risk index.

[0095] Step 311, performing level matching processing on the target risk index according to a preset level matching condition to obtain a target risk level.

[0096] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a geological disaster risk prediction device for implementing the geological disaster risk prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more geological disaster risk prediction device embodiments provided below can refer to the limitations of the geological disaster risk prediction method above, and will not be repeated here.

[0098] In an exemplary embodiment, Figure 4 As shown, a geological disaster risk prediction device is provided, including: an information acquisition module 402, an index prediction module 404 and a level matching module 406, wherein:

[0099] An information acquisition module 402 is used to acquire target state information corresponding to a power grid tower within a target time interval, wherein the target state information includes a target impact factor;

[0100] Index prediction module 404, used to obtain a target risk index according to target state information and a target risk prediction model, wherein the target risk prediction model is obtained by screening based on multicollinearity and importance of historical impact factors and importing an initial risk prediction model for training, wherein the historical impact factor is data corresponding to the target impact factor within a historical time interval;

[0101] The level matching module 406 is used to obtain the target risk level corresponding to the target area according to the target risk index.

[0102] In one of the embodiments, the target state information also includes target disaster-prone body information, the target risk prediction model includes a susceptibility prediction module and a vulnerability prediction module, and the index prediction module 404 is also used to input the target impact factor into the susceptibility prediction module to obtain a susceptibility index; input the target disaster-prone body information and the target impact factor into the vulnerability prediction module to obtain a vulnerability index; and perform superposition coupling processing on the susceptibility index and the vulnerability index to obtain a target risk index.

[0103] In one embodiment, the index prediction module 404 is further configured to perform multiplication processing on the susceptibility index and the vulnerability index to obtain a target risk index.

[0104] In one of the embodiments, the level matching module 406 is further configured to perform level matching processing on the target risk index according to a preset level matching condition to obtain a target risk level.

[0105] In one embodiment, the provided device also includes a model training module, which is used to obtain historical influencing factors, historical disaster information and an initial risk prediction model; based on the multicollinearity and importance corresponding to the historical influencing factors, screen and determine characteristic influencing factors from the historical influencing factors; based on the characteristic influencing factors and historical disaster information, obtain a training set; use the training set to train the initial risk prediction model to obtain a target risk prediction model.

[0106] In one of the embodiments, the model training module is also used to perform collinearity analysis on the historical impact factors to obtain a collinearity index corresponding to the historical impact factors; perform importance calculation on the historical impact factors to obtain an importance index corresponding to the historical impact factors; and when both the collinearity index and the importance index meet preset conditions, the historical impact factors are used as characteristic impact factors.

[0107] Each module in the above-mentioned geological disaster risk prediction device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0108] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store target state information, target risk index and target risk level. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting geological disaster risks is implemented.

[0109] Those skilled in the art will understand that the structure shown in FIG. Y is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0112] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0113] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0115] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting geological disaster risks, characterized in that: The method comprises: Acquire target state information corresponding to the power grid tower within the target time interval, wherein the target state information includes a target influencing factor; According to the target state information and the target risk prediction model, a target risk index is obtained, wherein the target risk prediction model is obtained by screening according to the multicollinearity and importance of historical impact factors and importing the initial risk prediction model for training, and the historical impact factors are the data corresponding to the target impact factors in the historical time interval; According to the target risk index, a target risk level corresponding to the target area is obtained.

2. The method according to claim 1, characterized in that: The target state information also includes target disaster-prone body information, and the target risk prediction model includes a susceptibility prediction module and a vulnerability prediction module; The step of obtaining a target risk index according to the target state information and the target risk prediction model includes: Inputting the target impact factor into the susceptibility prediction module to obtain a susceptibility index; Inputting the target disaster-sustaining body information and the target impact factor into the vulnerability prediction module to obtain a vulnerability index; The susceptibility index and the vulnerability index are superimposed and coupled to obtain the target risk index.

3. The method according to claim 2, characterized in that The superposition coupling processing of the susceptibility index and the vulnerability index to obtain the target risk index includes: multiplication processing of the susceptibility index and the vulnerability index to obtain the target risk index.

4. The method according to claim 1, characterized in that: Obtaining a target risk level corresponding to the target area according to the target risk index includes: performing level matching processing on the target risk index according to a preset level matching condition to obtain the target risk level.

5. The method according to claim 1, characterized in that The method further comprises: Acquiring the historical impact factors, historical disaster information and the initial risk prediction model; Based on the multicollinearity and importance corresponding to the historical impact factors, screening and determining characteristic impact factors from the historical impact factors; Based on the characteristic influencing factors and the historical disaster information, a training set is obtained; The initial risk prediction model is trained using the training set to obtain the target risk prediction model.

6. The method according to claim 5, characterized in that The determining of characteristic impact factors from the historical impact factors based on the multicollinearity and importance corresponding to the historical impact factors includes: Performing collinearity analysis on the historical impact factors to obtain collinearity indexes corresponding to the historical impact factors; Performing importance calculation processing on the historical impact factor to obtain an importance index corresponding to the historical impact factor; When both the collinearity index and the importance index meet preset conditions, the historical impact factor is used as a characteristic impact factor.

7. A geological disaster risk prediction device, characterized in that: The device comprises: An information acquisition module is used to acquire target state information corresponding to a power grid tower within a target time interval, wherein the target state information includes a target influencing factor; An index prediction module is used to obtain a target risk index according to the target state information and a target risk prediction model, wherein the target risk prediction model is obtained by screening according to the multicollinearity and importance of historical impact factors and importing an initial risk prediction model for training, wherein the historical impact factors are data corresponding to the target impact factors within a historical time interval; The level matching module is used to obtain the target risk level corresponding to the target area according to the target risk index.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images