Risk assessment method and device for geological disasters along power grid and computer equipment

Abstract

The invention relates to a risk assessment method and device for geological disasters along a power grid and computer equipment. The method comprises the following steps: constructing a sample database according to historical geological disaster data in a target area along a power grid; based on the at least two environmental influence factors and the sample database, constructing a training sample database, and based on preset machine learning method parameters, training the training sample database to obtain at least two geological disaster risk assessment models; comparing the geological disaster risk assessment model to obtain a target risk assessment model; and performing geological disaster assessment on the target area through the target risk assessment model. The method can improve the accuracy of risk assessment of geological disasters along the power grid; the personnel cost and the time cost are obviously reduced, and the risk assessment efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of disaster prevention and mitigation, and in particular to a method, device and computer equipment for assessing geological disaster risks along power grids. Background Art

[0002] Sudden geological disasters can cause house collapse, traffic interruption, etc., seriously affecting the life and property safety of local residents. Among them, geological disasters along the power grid have a particularly huge impact on the safety of residents. Therefore, it is necessary to conduct risk assessment of geological disasters along the power grid to accurately predict the possibility and probability of geological disasters, and combine them with disaster carriers to quickly generate risk assessment results.

[0003] However, the traditional machine learning model geological disaster risk assessment method requires a lot of time and manpower costs, which greatly reduces the efficiency of risk assessment. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device and computer equipment for geological disaster risk assessment along the power grid that can reduce the time cost and personnel cost of risk assessment and improve the efficiency of risk assessment in response to the above technical problems.

[0005] In the first aspect, the present application provides a method for assessing geological disaster risks along a power grid. The method comprises:

[0006] Construct a sample database based on historical geological disaster data in the target area along the power grid;

[0007] Based on at least two environmental influencing factors and a sample database, a training sample database is constructed, and based on preset machine learning method parameters, the training sample database is trained to obtain at least two geological hazard risk assessment models;

[0008] Compare the geological disaster risk assessment model to obtain the target risk assessment model;

[0009] The geological hazards in the target area are assessed through the target risk assessment model.

[0010] In one embodiment, constructing a sample database based on historical geological disaster data in a target area along a power grid includes:

[0011] Based on the historical geological disaster data in the target area along the power grid, the geological disaster data and non-geological disaster data are randomly selected;

[0012] The geological disaster data and non-geological disaster data are respectively marked as geological disaster samples and non-geological disaster samples; a sample database is constructed based on the geological disaster samples and non-geological disaster samples.

[0013] In one embodiment, the method further comprises:

[0014] According to the evaluation results of the geological disaster risk assessment model corresponding to the sample database, the quantitative ratio of geological disaster samples and non-geological disaster samples is adjusted.

[0015] In one embodiment, based on at least two environmental influencing factors and a sample database, constructing a training sample database includes:

[0016] Conduct correlation analysis on at least two environmental impact factors of geological hazards to eliminate redundant features of environmental impact factors; environmental impact factors have the same resolution size;

[0017] Construct an environmental influencing factor database based on the environmental influencing factors after eliminating redundant features;

[0018] A training sample database is constructed based on the environmental influencing factor database and the sample database.

[0019] In one embodiment, the preset machine learning method parameters include training time, training task type, evaluation reference index and at least two machine learning models; based on the preset machine learning method parameters, training the training sample database to obtain at least two geological hazard risk assessment models include:

[0020] According to the format of the training sample database, obtain the training task type;

[0021] According to the training task type, obtain the corresponding evaluation reference indicators;

[0022] According to the training task type and evaluation reference indicators, each machine learning model is iteratively trained until the training time is reached, and at least two geological hazard risk assessment models are obtained.

[0023] In one embodiment, performing a geological hazard assessment on a target area according to a target risk assessment model includes:

[0024] Determine the geological disaster risk probability value of the target area through the target risk assessment model;

[0025] According to the geological disaster hazard probability value and the influence range of the power grid carrier, the geological disaster risk value along the power grid is obtained.

[0026] In the second aspect, the present application also provides a device for assessing geological disaster risks along a power grid. The device includes:

[0027] A data processing module is used to construct a sample database based on historical geological disaster data in the target area along the power grid;

[0028] A sample training module is used to construct a training sample database based on at least two environmental influencing factors and a sample database, and to train the training sample database based on preset machine learning method parameters to obtain at least two geological hazard risk assessment models;

[0029] Model comparison module, used to compare geological hazard risk assessment models and obtain the target risk assessment model;

[0030] The risk assessment module is used to conduct geological hazard assessment on the target area through the target risk assessment model.

[0031] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above method embodiment are implemented.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above method embodiment when executed by a processor.

[0033] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method embodiment are implemented.

[0034] The above-mentioned geological disaster risk assessment method, device, computer equipment, storage medium and computer program product along the power grid automatically selects high-order models, optimal training time, hyperparameter selection, analysis, adjustment and optimization, wherein high-order models are compared with each other, and the best performance risk assessment model is selected, which reduces the time and cost of manual processing and improves the accuracy, precision and performance of the model. At the same time, it can respond to, build, train and deploy high-order machine learning models with the best performance more quickly, adapt to the needs of real-time updates and changes in geological disaster data, and automatically combine with the power grid carrier, so that the best performance machine learning model can be applied to regional geological disaster risk assessment faster and better. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A diagram of the application environment of a method for assessing geological hazards along a power grid in one embodiment;

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

[0037] Figure 3 A schematic flow chart of the steps of constructing a sample database according to historical geological disaster data in a target area along a power grid in one embodiment;

[0038] Figure 4 A flowchart of a step of building a training sample database based on at least two environmental influencing factors and a sample database in one embodiment;

[0039] Figure 5 A flowchart of the steps of training a training sample database to obtain at least two geological hazard risk assessment models based on preset machine learning method parameters in an embodiment;

[0040] Figure 6 A schematic diagram of a process for evaluating geological hazards in a target area according to a target risk assessment model in one embodiment;

[0041] Figure 7 A schematic diagram of a design process for geological disaster risk assessment along a power grid in one embodiment;

[0042] Figure 8 A schematic diagram of a flow chart of a method for assessing geological disaster risks along a power grid in another embodiment;

[0043] Fig. 9 A structural block diagram of a device for assessing geological disaster risks along a power grid in one embodiment;

[0044] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] 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.

[0046] Sudden geological disasters can cause house collapse, traffic interruption, etc., seriously affecting the lives and property safety of local residents. Among them, the power system, as an infrastructure, has a heavy impact on the lives of residents. Therefore, it is necessary to assess the geological disaster risks along the power grid, identify and prevent potential geological disaster threats in advance, and ensure that the power grid facilities are protected from the impact of geological disasters during construction and operation, so as to ensure the safe and stable operation of the power system.

[0047] The occurrence of geological disasters is affected by many factors, including geological characteristics, hydrological conditions, vegetation coverage, etc. Geological disaster risk assessment needs to be based on the above factors, analyze and understand the mechanism and relationship between different factors, and predict the possibility and probability of geological disasters.

[0048] Machine learning methods are widely used in traditional geological disaster risk assessment. However, machine learning methods are relatively complex and often require sufficient professional experience and technical capabilities in model selection and hyperparameter adjustment, which constitutes a serious technical barrier for researchers and model application users who are not in the field of machine learning. In addition, under sudden scenario conditions, staff often need to spend a lot of energy on modeling and scenario analysis, which greatly reduces the efficiency of risk assessment.

[0049] Therefore, the present invention proposes a method for quickly assessing the geological hazard risks along the power grid by using the optimal performance model based on automated machine learning using the FLAML (Fast and Lightweight AutoML) framework. The method can improve the prediction accuracy of geological hazard risk assessment and significantly reduce the time and cost caused by manual experiments and adjustments during the risk assessment process.

[0050] The method for assessing geological disaster risks along a power grid provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the data collection device 102 communicates with the terminal 104 through the network. The data collection device 102 is used to collect geological disaster data and non-geological disaster data in the area along the power grid, and send it to the terminal 104. The terminal 104 builds a sample database based on the geological disaster data and non-geological disaster data, performs machine learning training, and executes the various steps of the method for assessing geological disaster risks along the power grid of this application. Among them, the terminal 104 can be but not limited to various personal computers, laptops, workstations, etc.

[0051] In an exemplary embodiment, Figure 2 As shown in the figure, a method for assessing geological hazards along the power grid is provided. Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0052] Step 202: construct a sample database based on historical geological disaster data in the target area along the power grid.

[0053] Optionally, historical geological disaster data and non-geological disaster data in the target area along the power grid are obtained, and then geological disaster samples and non-geological disaster samples are selected from the historical geological disaster data and non-geological disaster data, and a sample database is constructed based on the above samples.

[0054] Step 204, based on at least two environmental influencing factors and the sample database, a training sample database is constructed, and based on preset machine learning method parameters, the training sample database is trained to obtain at least two geological hazard risk assessment models.

[0055] Optionally, in the target area along the power grid, at least two environmental influencing factors that may induce geological disasters are selected; each environmental influencing factor is extracted into a sample database, and a training sample database is constructed based on the sample database; the training sample database is trained according to preset machine learning method parameters to obtain a geological disaster risk assessment model; the above steps are repeated for multiple trainings to obtain multiple geological disaster risk assessment models.

[0056] Step 206, comparing the geological disaster risk assessment model to obtain a target risk assessment model.

[0057] Optionally, a training sample database is constructed multiple times, and after all machine learning models are trained according to the machine learning method parameter settings, multiple geological hazard risk assessment models are compared to obtain a target risk assessment model with the best assessment effect.

[0058] Step 208: Perform a geological hazard assessment on the target area using a target risk assessment model.

[0059] Optionally, a target risk assessment model is used to obtain a geological disaster assessment prediction map of a target area along the power grid, and the result of the geological disaster risk assessment along the power grid is output in combination with the range of the carrier.

[0060] Exemplarily, the scope of the carrier may include power grid facilities, surrounding environment, areas affected by geological disasters, related infrastructure, etc.

[0061] In the above-mentioned method for assessing geological hazard risks along the power grid, training samples are constructed multiple times, machine learning method parameters are preset, and multiple geological hazard risk assessment models are trained. The optimal geological hazard risk assessment model is obtained by comparing multiple geological hazard risk assessment models, thereby improving the accuracy of geological hazard risk assessment along the power grid; and the automated machine learning method can quickly find suitable parameter settings and machine learning models to obtain the optimal geological hazard risk assessment model, significantly reducing personnel costs and time costs, and greatly improving risk assessment efficiency.

[0062] The following describes the method for constructing the sample database of this application through some embodiments.

[0063] In an exemplary embodiment, Figure 3 As shown in the figure, based on the historical geological disaster data in the target area along the power grid, the sample database is constructed including:

[0064] Step 302, based on the historical geological disaster data in the target area along the power grid, randomly select geological disaster data and non-geological disaster data.

[0065] Step 304: Mark the geological disaster data and non-geological disaster data as geological disaster samples and non-geological disaster samples, respectively.

[0066] Step 306: construct a sample database based on the geological disaster samples and non-geological disaster samples.

[0067] Exemplarily, historical geological disaster data are collected in the target area along the power grid. Based on the historical geological disaster data, geological disaster data and non-geological disaster data are randomly selected in the target area along the power grid and marked as geological disaster sample data and non-geological disaster sample data. The geological disaster sample data and non-geological disaster sample data are combined to construct a sample database.

[0068] The sample database in this embodiment includes geological disaster sample data and non-geological disaster sample data, and comprehensively covers the historical geological disaster data of the target area to ensure the comprehensiveness of the geological disaster risk assessment along the power grid.

[0069] In an exemplary embodiment, the method of the above embodiment further includes: adjusting the quantity ratio of geological disaster samples and non-geological disaster samples according to the evaluation results of the geological disaster risk evaluation model corresponding to the sample database.

[0070] For example, the ratio between geological disaster samples and non-geological disaster samples can be adjusted according to the assessment task requirements and risk assessment results, such as using a regression model, to obtain a more accurate risk prediction effect.

[0071] In an exemplary embodiment, Figure 4 As shown, based on at least two environmental influencing factors and a sample database, constructing a training sample database includes:

[0072] Step 402, performing correlation analysis on the environmental impact factors of at least two geological disasters to eliminate redundant features of the environmental impact factors; the environmental impact factors have the same resolution size.

[0073] Exemplarily, within the target area, environmental factors that may induce geological disasters are selected, including geological characteristics, hydrological conditions, vegetation coverage, etc., to construct an environmental factor database, and these factors are set to the same resolution size.

[0074] Step 404: construct an environmental influencing factor database based on the environmental influencing factors after eliminating redundant features.

[0075] Exemplarily, the variance inflation factor or automated feature screening is used to avoid redundant features, determine the close relationship between environmental influencing factors, eliminate the correlation between environmental influencing factors, and reduce the interdependence between factors.

[0076] Step 406: construct a training sample database based on the environmental influencing factor database and the sample database.

[0077] Exemplarily, environmental influencing factors such as geological characteristics, hydrological conditions, and vegetation coverage are extracted into the corresponding sample database, constructed into a training sample database, and redundant features are avoided through correlation analysis.

[0078] This embodiment selects multiple environmental influencing factors that may induce geological disasters and eliminates redundant features of environmental influencing factors through correlation analysis, thereby efficiently and accurately constructing a training sample database; at the same time, the comprehensiveness of the training sample database is ensured through a multi-source environmental influencing factor database and sample database.

[0079] The following is a detailed description of the method for implementing automated and rapid risk assessment in the present application in conjunction with some embodiments.

[0080] In an exemplary embodiment, Figure 5 As shown, the preset machine learning method parameters include training time, training task type, evaluation reference indicators and at least two machine learning models; based on the preset machine learning method parameters, the training sample database is trained to obtain at least two geological hazard risk assessment models including:

[0081] Step 502: Obtain the training task type according to the format of the training sample database.

[0082] Step 504: Obtain corresponding evaluation reference indicators according to the training task type.

[0083] Step 506, according to the training task type and the evaluation reference index, each machine learning model is iteratively trained until the training time is reached, and at least two geological hazard risk assessment models are obtained.

[0084] Optionally, the automated machine learning method is used to select the training time, training task type, evaluation reference index, machine learning model, etc., and the training sample database is trained and fitted by automated machine learning. The evaluation index of the previous automated machine learning model is compared, and the sample database is constructed multiple times to select the optimal risk assessment model.

[0085] Exemplarily, a training time is selected, such as a training time of 50s, 100s, 200s, or 300s. The training time can be shortened or extended according to the evaluation task objectives. For example, the training time can be shortened when a quick response is required.

[0086] The training task type can be selected as a classification task or a regression task according to the format of the geological disaster training samples; at the same time, various high-order machine learning models can be selected, such as LGBM (Light Gradient Boosting Machine), XGBoost (eXtreme Gradient Boosting), Catboost (Categorical Boosting), Random Forest, Extra Trees (Extremely Randomized Trees), Logistic Regression, and other models;

[0087] In addition, different evaluation reference indicators are selected according to the different types of geological disaster training tasks. For example, the evaluation reference indicators of regression tasks include MAE (Mean Absolute Error), MAPE (Mean Absolute Percentage Error), MSE (Mean Squared Error), RMSE (Root Mean Squared Error), etc., while the evaluation reference indicators of classification tasks include Accuracy, Precision, Recall, F1-Score, ROC-AUC (Receiver Operating Characteristic - Area Under Curve), etc.

[0088] The above embodiment gives the preset machine learning method parameters of the present application, gives corresponding parameter settings according to different training requirements, establishes regression tasks or classification tasks to cope with different geological disaster situations, and selects corresponding evaluation reference indicators according to the task type to ensure that the risk assessment model can achieve accurate prediction and build a comprehensive and diverse geological disaster risk assessment system along the power grid.

[0089] In an exemplary embodiment, Figure 6 As shown in the figure, the geological hazard assessment of the target area according to the target risk assessment model includes:

[0090] Step 602, determining the geological disaster risk probability value of the target area through the target risk assessment model.

[0091] Step 604, obtaining the geological disaster risk value along the power grid according to the geological disaster hazard probability value and the influence range of the power grid carrier.

[0092] Exemplarily, the risk assessment method is: D = P * A, where D is the geological risk value along the power grid, P is the probability value of geological disaster danger, and A is the impact range of the power grid carrier. The risk value is proportional to the possibility of geological disasters and the scope of the power grid facilities affected.

[0093] The risk assessment method provided in this embodiment can quantitatively assess the risk of geological disasters along the power grid, provide a scientific basis for power grid planning and design, and thus take corresponding prevention and control measures to reduce the impact of geological disasters on power grid facilities.

[0094] The following embodiments, combined with Figure 7 , showing the overall design process of the automatic and fast-response geological disaster risk assessment method along the power grid in this application. Among them, the VIF method is the Variance Inflation Factor (VIF) method.

[0095] In an exemplary embodiment, Figure 8 As shown, a method for assessing geological disaster risks along a power grid is provided, comprising the following steps:

[0096] Step 802: Collect historical geological disaster data in the target area. Based on the historical geological disaster data, randomly select geological disaster data samples and non-geological disaster data samples in the study area, and combine the two to build a sample database.

[0097] Step 804: Within the study area, select environmental factors that may induce geological disasters, including geological characteristics, hydrological conditions, vegetation coverage, etc., build an environmental factor database, and set these factors to the same resolution size.

[0098] Step 806: extract geological characteristics, hydrological conditions, vegetation coverage and other environmental influencing factors into the sample database corresponding to the environmental influencing factors to construct a training sample database; and eliminate redundant features through variance inflation factor or automated feature screening.

[0099] Step 808: Utilize the automated machine learning method to select the training time, training task type, evaluation reference indicators, high-order machine learning model, etc., and perform automated machine learning training fitting on the training sample database.

[0100] Step 810: After all machine learning models are trained, the optimal performance model is obtained, and used in the risk prediction of the target area to obtain a geological disaster risk assessment prediction map.

[0101] Step 812: The risk assessment method used is: D = P * A, and the result of the geological disaster risk assessment along the power grid is output in combination with the range of the carrier.

[0102] In this embodiment, the automated training of the risk assessment model and the rapid response of the assessment results reduce the time and cost of manual processing, improve the efficiency and performance of the risk assessment model, increase the effective time of geological hazard risk assessment professionals, and apply more energy to data processing. Automated machine learning can respond, build, train and deploy machine learning models with the best performance more quickly, accurately predict the possibility and probability of geological disasters, and finally automatically combine with the power grid carrier. Adapt to the needs of real-time updates and changes in geological hazard data, and adapt to changes in geological hazard data and model iteration processes by supplementing geological hazard data.

[0103] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.

[0104] Based on the same inventive concept, the embodiment of the present application also provides a device for assessing geological hazards along power grids for implementing the method for assessing geological hazards along power grids 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 embodiments of the device for assessing geological hazards along power grids provided below can refer to the limitations of the method for assessing geological hazards along power grids above, and will not be repeated here.

[0105] In an exemplary embodiment, Fig. 9 As shown, a device for assessing geological disaster risks along a power grid is provided, including: a data processing module 902, a sample training module 904, a model comparison module 906 and a risk assessment module 908, wherein:

[0106] The data processing module 902 is used to construct a sample database based on the historical geological disaster data in the target area along the power grid.

[0107] The sample training module 904 is used to construct a training sample database based on at least two environmental influencing factors and a sample database, and to train the training sample database based on preset machine learning method parameters to obtain at least two geological hazard risk assessment models.

[0108] The model comparison module 906 is used to compare the geological disaster risk assessment model to obtain a target risk assessment model.

[0109] The risk assessment module 908 is used to perform a geological hazard assessment on the target area through a target risk assessment model.

[0110] In an exemplary embodiment, the data processing module 902 further includes:

[0111] The sample construction module is used to randomly select geological disaster data and non-geological disaster data based on the historical geological disaster data in the target area along the power grid; mark the geological disaster data and non-geological disaster data as geological disaster samples and non-geological disaster samples respectively; and construct a sample database based on the geological disaster samples and non-geological disaster samples.

[0112] In an exemplary embodiment, the sample construction module is also used to adjust the quantity ratio of geological disaster samples and non-geological disaster samples according to the evaluation results of the geological disaster risk evaluation model corresponding to the sample database.

[0113] In an exemplary embodiment, the sample training module 904 further includes:

[0114] The influencing factor selection module is used to perform correlation analysis on the environmental influencing factors of at least two geological disasters and eliminate the redundant features of the environmental influencing factors; the environmental influencing factors have the same resolution size; an environmental influencing factor database is constructed based on the environmental influencing factors after eliminating the redundant features; a training sample database is constructed based on the environmental influencing factor database and the sample database.

[0115] In an exemplary embodiment, the preset machine learning method parameters include training time, training task type, evaluation reference indicators and at least two machine learning models; the sample training module 904 is also used to obtain the training task type according to the format of the training sample database; obtain the corresponding evaluation reference indicator according to the training task type; according to the training task type and the evaluation reference indicator, each machine learning model is iteratively trained until the training time is reached, and at least two geological hazard risk assessment models are obtained.

[0116] In an exemplary embodiment, the risk assessment module 908 is also used to determine the geological disaster risk probability value of the target area through a target risk assessment model; and obtain the geological disaster risk value along the power grid based on the geological disaster risk probability value and the influence range of the power grid carrier.

[0117] Each module in the above-mentioned geological disaster risk assessment device along the power grid can be implemented in whole or in part by software, hardware and their combination. 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 of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0118] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for assessing the risk of geological disasters along the power grid is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0119] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above method embodiment when executing the computer program.

[0121] 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 of the above method embodiment are implemented.

[0122] In one embodiment, a computer program product is provided, comprising a computer program, which performs the steps of the above method embodiment when executed by a processor.

[0123] 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 laws, regulations and standards of relevant countries and regions.

[0124] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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.

[0125] 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.

[0126] The above-described 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 assessing geological disaster risks along a power grid, characterized in that: The method comprises: Construct a sample database based on historical geological disaster data in the target area along the power grid; Based on at least two environmental influencing factors and the sample database, a training sample database is constructed, and based on preset machine learning method parameters, the training sample database is trained to obtain at least two geological hazard risk assessment models; Comparing the geological disaster risk assessment model, obtaining a target risk assessment model; The target risk assessment model is used to conduct a geological disaster assessment on the target area.

2. The method for assessing geological disaster risks along a power grid according to claim 1, characterized in that: The construction of a sample database based on historical geological disaster data in the target area along the power grid includes: Based on the historical geological disaster data in the target area along the power grid, the geological disaster data and non-geological disaster data are randomly selected; Marking the geological disaster data and the non-geological disaster data as geological disaster samples and non-geological disaster samples respectively; A sample database is constructed according to the geological disaster samples and the non-geological disaster samples.

3. The method for assessing geological disaster risks along the power grid according to claim 2, characterized in that: The method further comprises: According to the evaluation result of the geological disaster risk evaluation model corresponding to the sample database, the quantity ratio of the geological disaster samples and the non-geological disaster samples is adjusted.

4. The method for assessing geological disaster risks along a power grid according to claim 1, characterized in that: The constructing of a training sample database based on at least two environmental influencing factors and the sample database includes: Conducting correlation analysis on at least two environmental impact factors of geological disasters to eliminate redundant features of the environmental impact factors; the environmental impact factors have the same resolution size; Construct an environmental influencing factor database based on the environmental influencing factors after eliminating redundant features; The training sample database is constructed according to the environmental influencing factor database and the sample database.

5. The method for assessing geological disaster risks along a power grid according to claim 1, characterized in that: The preset machine learning method parameters include training time, training task type, evaluation reference index and at least two machine learning models; based on the preset machine learning method parameters, training the training sample database to obtain at least two geological hazard risk assessment models includes: Acquire the training task type according to the format of the training sample database; According to the training task type, obtaining the corresponding evaluation reference indicator; According to the training task type and the evaluation reference index, each machine learning model is iteratively trained until the training time is reached, so as to obtain at least two geological hazard risk assessment models.

6. The method for assessing geological disaster risks along a power grid according to claim 1, characterized in that: The performing of geological disaster assessment on the target area according to the target risk assessment model comprises: Determine the geological disaster risk probability value of the target area through the target risk assessment model; According to the geological disaster hazard probability value and the influence range of the power grid carrier, the geological disaster risk value along the power grid is obtained.

7. A device for assessing geological disaster risks along a power grid, characterized in that: The device comprises: A data processing module is used to construct a sample database based on historical geological disaster data in the target area along the power grid; A sample training module, used to construct a training sample database based on at least two environmental influencing factors and the sample database, and to train the training sample database to obtain at least two geological hazard risk assessment models based on preset machine learning method parameters; A model comparison module is used to compare the geological disaster risk assessment model to obtain a target risk assessment model; The risk assessment module is used to conduct a geological disaster assessment on the target area through the target risk assessment model.

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