Ultra-high voltage tower geological disaster insurance risk quantification and claim settlement decision method and device
By combining pre-set risk assessment models and insurance quantification models with trigger event data and the disaster-bearing capacity of power transmission facilities, the quantitative problem of geological disaster risk assessment for UHV towers has been solved, achieving precise risk assessment and insurance pricing and full-process management.
Patent Information
- Application Number
- CN202611332695.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-31
- Publication Date
- 2026-11-10
AI Technical Summary
Existing technologies lack the ability to quantify the risks of power transmission facilities in geological disaster risk assessment of UHV towers, which cannot effectively support insurance compensation pricing, and do not consider the probability of triggering by rainfall or earthquakes.
Based on a pre-set risk assessment model, and combined with sample data of triggered events to train the model, the disaster-bearing capacity and risk information of power transmission facilities are determined, and risk assessment and compensation are integrated through an insurance quantification model.
It has improved the accuracy and timeliness of risk assessment, enabled differentiated risk calculation for towers and precise insurance pricing, and supported the entire process management of pre-disaster loss prediction and post-disaster loss assessment.
Smart Images

Figure CN123069079A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of disaster assessment technology, specifically to methods, devices, and electronic equipment for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers. Background Technology
[0002] Currently, geological hazard risk assessments for power transmission facilities, such as ultra-high-voltage transmission line towers, typically rely on multi-source geological, meteorological, and disaster data to assess regional landslide susceptibility and identify potential landslide risk areas. However, this method focuses on regional-scale landslide risk assessment, lacking the ability to quantify the risk of critical disaster-bearing structures like power transmission facilities, and also lacks practical application in risk quantification for insurance payout assessments. Summary of the Invention
[0003] This invention provides a method and apparatus for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers, in order to solve the problems of only conducting regional landslide assessments, failing to quantify the vulnerability of exposed towers, not considering the probability of triggering by rainfall or earthquakes, and the inability of risk assessments to be aligned with insurance pricing and compensation.
[0004] In a first aspect, the present invention provides a method for risk quantification and compensation decision-making in geological disaster insurance for ultra-high voltage power transmission towers, the method comprising: Based on a pre-set risk assessment model, a risk assessment of the target geological hazard is conducted in the target assessment area to obtain the hazard risk information of the target assessment area. The pre-set risk assessment model is trained based on sample data of the triggering events corresponding to the target geological hazard. Based on the location and engineering information of each power transmission facility in the target assessment area, the disaster bearing capacity information of each power transmission facility is determined; Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, the disaster risk information of each power transmission facility is determined respectively; Based on the disaster risk information of each power transmission facility and the pre-set insurance quantification model, the insurance assessment information of each power transmission facility is determined.
[0005] This invention, based on a pre-set risk assessment model, conducts risk assessments of target geological hazards in the target assessment area, obtaining hazard risk information for the target assessment area. By using samples of triggering events to train the model, it can accurately obtain the landslide risk of the target area that closely matches sudden disasters, effectively improving the realism of the assessment. Furthermore, based on the location and engineering information of each power transmission facility in the target assessment area, it determines the disaster-bearing capacity information of each power transmission facility, which can better combine the disaster-bearing capacity of the tower location and tower engineering parameters to distinguish the disaster differences of different towers. Furthermore, based on the hazard risk information of each power transmission facility and a pre-set insurance quantification model, it determines the insurance assessment information of each power transmission facility, which can better integrate the regional landslide risk and the disaster-bearing capacity of the towers to obtain accurate comprehensive risk for each tower. Furthermore, based on the hazard risk information of each power transmission facility and the pre-set insurance quantification model, it can determine the insurance assessment information of each power transmission facility. By relying on tower risk data and a pre-set insurance model, it effectively realizes the integration of risk assessment and insurance pricing and compensation. Therefore, this method assesses regional landslide risk based on a trigger event model, obtains the risk of individual towers by quantifying their disaster-bearing capacity, and then outputs insurance assessment results, making the assessment more accurate and realizing differentiated risk calculation of towers and precise insurance pricing.
[0006] In one optional implementation, based on a preset risk assessment model, a risk assessment of the target geological hazard in the target assessment area is performed to obtain hazard risk information for the target assessment area, including: Acquire trigger event data for the target evaluation area; The trigger event data of the target assessment area is input into the preset risk assessment model to obtain the disaster risk information of the target assessment area.
[0007] This method uses data from triggering events such as rainfall and earthquakes to drive model calculations, making the assessment results closely match real disaster-induced scenarios, which can significantly improve the accuracy and timeliness of regional landslide risk prediction.
[0008] In one optional implementation, the preset risk assessment model is trained in the following manner: Based on a preset ratio, the sample data is divided into a training dataset and a test dataset; An initial risk assessment model is constructed based on the mapping relationship between the effective disaster impact factors of the target geological disaster and the disaster risk information of the target assessment area. Based on the training and test datasets, the initial risk assessment model is trained to obtain the preset risk assessment model.
[0009] This method trains the model by dividing it into training and testing sets, and selects effective factors to establish risk mapping, which improves the model's generalization ability and prediction accuracy, and effectively avoids the interference of invalid factors on the evaluation results.
[0010] In one alternative implementation, the method further includes: The triggering probability of a target geological disaster is determined based on the ratio of the area of the target geological disaster caused by the triggering event to the coverage area of the triggering event. Based on the triggering probability of the triggering event corresponding to the target geological disaster, sampling is carried out within the coverage area of the triggering event to obtain sample data.
[0011] This method samples and constructs samples based on the trigger probability, which can effectively fit the real spatial distribution of landslides, better eliminate the problem of sample ratio imbalance, and effectively improve the reliability of model training.
[0012] In one alternative implementation, the method further includes: The characteristics of multiple disaster impact factors corresponding to the target geological disaster are analyzed to obtain the effective disaster impact factors of the target geological disaster.
[0013] This method effectively reduces model interference and improves the accuracy and computational efficiency of risk prediction by performing feature analysis on multiple disaster impact factors corresponding to the target geological disaster and filtering out redundant and weakly collinear contributing factors.
[0014] In one optional implementation, feature analysis is performed on multiple disaster impact factors corresponding to the target geological hazard to obtain the effective disaster impact factors of the target geological hazard, including: The correlation between multiple disaster impact factors and other disaster impact factors was analyzed to obtain correlation information of multiple disaster impact factors; Disaster impact factors whose correlation information meets the preset correlation conditions are removed from multiple disaster impact factors to obtain multiple initial disaster impact factors. The preset correlation conditions are used to indicate that there is a strong correlation between disaster impact factors and other disaster impact factors. Multiple importance analysis sequences are constructed based on multiple initial disaster factors, and the importance of multiple initial disaster impact factors is analyzed based on multiple importance analysis sequences to obtain the importance information of multiple initial disaster impact factors. Among them, the sample arrangement order corresponding to at least one initial disaster factor in the multiple importance analysis sequences is different. Among multiple initial disaster impact factors, those whose importance information meets the preset importance condition are identified as effective disaster impact factors. The preset importance condition is used to indicate that the importance information of the initial disaster impact factor is greater than the preset importance.
[0015] This method first eliminates factors with multicollinearity through correlation testing, which can avoid distortion of model parameters. Furthermore, it uses multi-round permutation and ranking analysis to analyze the predictive contribution of each factor, and screens out variables with low importance, which can better simplify the model input, reduce the amount of computation, and effectively improve the stability and accuracy of landslide risk prediction.
[0016] In one optional implementation, the location information includes environmental sensitivity information of the power transmission facility, the engineering information includes importance information, structural type information, operating time information and historical damage information of the power transmission facility, and the disaster bearing capacity information includes exposure index and vulnerability index of the power transmission facility. Based on the location and engineering information of each power transmission facility in the target assessment area, the disaster-bearing capacity information of each power transmission facility is determined, including: The environmental sensitivity and importance information of each power transmission facility are weighted separately to obtain the exposure index of each power transmission facility; The vulnerability index of each power transmission facility is obtained by weighting the structural type information, operating time information and historical damage information of each facility.
[0017] This method uses multiple dimensions to break down indicators based on the environment of the power transmission facility and the engineering information of the facility. It then performs weighted quantification of the exposure index and vulnerability index, comprehensively and objectively reflecting the disaster conditions and structural vulnerability of the towers, and better realizing the standardized calculation of the towers' disaster-bearing capacity.
[0018] In one optional implementation, based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, the disaster risk information of each power transmission facility is determined, including: Based on the disaster risk information of the target assessment area, the disaster risk information of each power transmission facility location is determined; The disaster risk information of each power transmission facility is obtained by multiplying the disaster risk information of the location of each power transmission equipment, the exposure index and the vulnerability index of the power transmission facility.
[0019] This method calculates the comprehensive risk of a target tower by combining three indicators: landslide hazard, tower exposure, and vulnerability. It can fully cover three risk dimensions: the probability of disaster occurrence, the tower's exposure conditions, and the ease with which the tower structure is damaged. This method achieves intuitiveness and comparability of the quantitative results and more accurately reflects the true disaster risk level of a single tower.
[0020] In one optional implementation, based on the disaster risk information of each transmission facility and a pre-set insurance quantification model, insurance assessment information for each transmission facility is determined, including: The disaster risk information of each power transmission facility is input into the first insurance quantification model to obtain the insurance premium information of each power transmission facility; The disaster risk information of each power transmission facility is input into the second insurance quantification model to obtain the expected loss information of each power transmission facility; Based on the insurance premium rate information and expected loss information of each power transmission facility, the insurance liability limit is determined. The insurance liability limit is used to compare with the actual loss to determine the actual compensation information.
[0021] This method is based on the comprehensive risk of the target tower. By inputting it into a preset model, it can automatically generate differentiated premiums, effectively supporting the entire process of underwriting pricing, pre-disaster loss prediction, and post-disaster loss assessment. It solves the problems of the traditional power grid insurance rate being one-size-fits-all and the lack of quantitative standards for compensation.
[0022] Secondly, the present invention provides a device for risk quantification and compensation decision-making in geological disaster insurance for ultra-high voltage power transmission towers, the device comprising: The sampling module is used to randomly sample the target area based on the acquired disaster assessment data to obtain sample data of the target area; The filtering module is used to filter and eliminate disaster impact factors in the target area to obtain the effective disaster impact factors in the target area. The landslide probability prediction model calculation module is used to perform modeling calculations based on sample data and effective disaster impact factors of the target area to obtain the landslide probability prediction model; The pole exposure and vulnerability index calculation module is used to quantify the power disaster assessment data of the target area and obtain the pole exposure index and pole vulnerability index of the target area. The comprehensive risk index calculation module is used to perform coupled calculations based on the tower exposure index, tower vulnerability index and landslide probability of the target area to obtain the comprehensive risk index of the target area; The business quantitative decision-making model calculation module is used to perform coupled calculations based on the comprehensive risk index of the target area to obtain the business quantitative decision-making model.
[0023] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the above-described method for quantifying and deciding on the risk of geological disaster insurance for ultra-high voltage towers or any of its corresponding embodiments.
[0024] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the method for quantifying and making compensation decisions for geological disaster insurance of ultra-high voltage towers as described in the first aspect or any of its corresponding embodiments.
[0025] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the method for quantifying and making compensation decisions for geological disaster insurance of ultra-high voltage towers as described in the first aspect or any of its corresponding embodiments. Attached Figure Description
[0026] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0027] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating the process of training a preset risk assessment model in the method for quantifying and deciding on compensation for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention. Figure 4 This is a schematic diagram of the second process of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the third process of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage towers according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the fourth process of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage towers according to an embodiment of the present invention; Figure 7 This is the fifth flowchart of the method for risk quantification and compensation decision-making for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention. Figure 8 This is a structural block diagram of the ultra-high voltage power transmission tower geological disaster insurance risk quantification and compensation decision-making device according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0029] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0030] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0031] As an optional application scenario of this invention, such as Figure 1 As shown, the UHV tower geological disaster insurance risk quantification and compensation decision-making system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.
[0032] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.
[0033] According to an embodiment of the present invention, an embodiment of a method for risk quantification and compensation decision-making for geological disaster insurance of ultra-high voltage towers is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0034] This embodiment provides a method for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, which can be used in the aforementioned electronic equipment. Figure 2 This is a first flowchart of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention, as follows: Figure 2 As shown, the process includes the following steps: Step S201: Based on the preset risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area to obtain the hazard risk information of the target assessment area.
[0035] In this embodiment of the invention, the preset risk assessment model is a landslide probability calculation model that has been pre-trained and can be directly used. For example, it can be a model constructed using a random forest algorithm and trained based on landslide samples such as rainstorms and earthquakes to predict the probability of landslides. The disaster risk information is the standardized result output by this model, which may include the landslide occurrence probability and hazard zones for each grid cell in the target area.
[0036] In this embodiment of the invention, the target assessment area is the geographical scope of the landslide risk assessment being conducted. For example, the entire mountain corridor traversed by a certain ultra-high voltage transmission line. The transmission facilities are the planned disaster-bearing carriers of electricity, which can be ultra-high voltage transmission towers; for example, 1000kV angle steel transmission towers or steel pipe towers.
[0037] In this embodiment of the invention, a pre-trained preset risk assessment model is invoked to perform a full-area landslide hazard calculation on the designated target assessment area, and output unified regional landslide risk data. For example, a mountainous area along a certain ultra-high voltage line in a certain region can be selected as the target assessment area and landslide can be selected as the target geological hazard. First, the terrain and rainfall samples of rainstorm-triggered events in the region are retrieved to complete the training of the model. The terrain and rainfall data of the entire mountainous area are input into the preset model, and the probability of landslide occurrence of each grid in the entire region is output.
[0038] In one alternative implementation, Figure 3 This is a flowchart illustrating the process of training a preset risk assessment model in the method for quantifying and deciding on compensation for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention. Figure 3 As shown, the preset risk assessment model can be trained in the following way: Step S301: Based on a preset ratio, the sample data is divided into a training dataset and a test dataset.
[0039] In this embodiment of the invention, the sample data is divided into a training dataset and a test dataset according to a preset ratio. The preset ratio can be set to 7:3, 8:2, or 6:4, etc., and is not specifically limited here. For example, for landslide events triggered by heavy rainfall, the samples can be divided into a training dataset and a test dataset in a 7:3 ratio; for landslide events triggered by earthquakes, an 8:2 sample division ratio can be used.
[0040] In one optional implementation, sample data can be constructed using a conditional probability sample construction method based on Bayesian probability principles. The influence range of a triggering event is determined according to its type; for example, the influence range of a rainfall-triggered event is determined based on the rainfall coverage area or the range of rainfall isopleths, while the influence range of an earthquake-triggered event is determined based on the earthquake intensity influence range. Bayesian probability theory posits that, given a triggering event, the probability of an event occurring can be characterized by its prior probability. Under a triggering event, the prior probability of a landslide occurring can be estimated by the ratio of the total area of the landslide triggered by that triggering event to the influence range of that triggering event, thus achieving an objective quantification of the basic probability of landslide occurrence. For example, in a rainfall-triggered landslide scenario, the prior probability of a landslide occurring can be estimated by the ratio of the total area of the landslide triggered by that rainfall event to the area of the influence range of the rainfall event. The prior probability of a landslide occurring in a certain area under triggering conditions is shown in the following formula:
[0041] in, ∑Arls This indicates the total area of the landslide triggered by this event; A Indicates the area affected by the triggered event; Prls This represents the prior probability of a landslide occurring under the triggering condition, meaning its value ranges from 0 to 1. Correspondingly, this probability reflects the basic probability of a landslide occurring in any spatial unit under the triggering event constraint. Specifically, this prior probability is equivalent to the triggering probability in this invention.
[0042] In one optional implementation, random sampling is performed within the influence range of the triggering event, and the ratio of positive to negative samples is controlled according to prior probability to construct sample data that satisfies the conditional probability distribution constraints. Specifically, each triggering case has a corresponding preset ratio. Positive samples are point samples collected according to prior probability in the area where a landslide actually occurred, based on the influence range of this triggering event; negative samples are point samples collected according to prior probability in the area where no landslide occurred, based on the influence range of this triggering event.
[0043] For example, the prior probability of a landslide occurring in this triggering event is calculated to be 0.02. 200 landslide locations are collected as positive samples from the area within the influence range of the triggering event where landslides have actually occurred. Furthermore, 9800 locations where no landslides have occurred are collected as negative samples from the area within the influence range where no landslides have occurred, according to the proportion of the prior probability.
[0044] Specifically, the sampling scope is strictly limited to the geographical area actually affected by the triggering event. Random sampling is performed within this area, and the ratio of positive landslide samples to negative non-landslide samples is adjusted based on the prior probability of landslide occurrence in this scenario. This ensures that the probability distribution of the final sample set closely matches the statistical regularity of landslide occurrence in real triggering events, thereby generating a landslide modeling sample set for training the risk assessment model. The obtained sample data is then divided into training and testing datasets according to a preset ratio.
[0045] For example, if a severe rainstorm triggers a landslide, the mountainous area covered by the rainstorm is first identified as the affected area. Specifically, the historical landslide prior probability for this region is 0.05. Random sampling points are then taken within the affected mountainous area, and positive and negative samples are controlled according to the 0.05 prior probability, meaning approximately 5% are positive and 95% are negative. Furthermore, the rainfall, slope, soil type, and whether a landslide occurred at each sampling point are aggregated to obtain a landslide modeling sample set that satisfies the conditional probability distribution constraints.
[0046] Step S302: Based on the mapping relationship between the effective disaster impact factors of the target geological disaster and the disaster risk information of the target assessment area, an initial risk assessment model is constructed.
[0047] In this embodiment of the invention, based on the concept of conditional probability modeling of triggering events, a landslide probability prediction model is established using a logistic regression algorithm. Its linear regression expression is as follows:
[0048] Based on this, the linear combination result is mapped to the probability of landslide occurrence using the Sigmoid function, and its probability expression is as follows:
[0049] in, This is the first effective disaster impact factor. The regression coefficients corresponding to the effective disaster impact factors, For constant terms, This is the linear output value obtained by weighting and superimposing all effective disaster impact factors. This represents the probability of a landslide occurring under the triggering event conditions. Its value ranges from 0 to 1, with a higher probability value indicating a higher likelihood of a landslide occurring.
[0050] In this embodiment of the invention, the effective disaster impact factors are those factors that have been screened and are significantly correlated with the target geological disaster, and that truly influence the occurrence of the disaster. For example, after screening, slope, rainfall, and soil type are retained as effective disaster impact factors for landslides.
[0051] In one optional implementation, feature analysis can be performed on multiple disaster impact factors corresponding to the target geological hazard to obtain the effective disaster impact factors of the target geological hazard. Feature analysis can involve statistical, correlation, and significance analysis of numerous impact factors to determine the strength of the correlation between each factor and the geological hazard. For example, the correlation between each factor and landslide occurrence can be calculated, and factors with weak correlations can be eliminated.
[0052] In one alternative implementation, by conducting feature analysis on a batch of candidate disaster impact factors, identifying which factors are strongly correlated with the occurrence of geological disasters, and eliminating redundant, low-correlation, and interfering factors, while retaining the factors that truly affect the disaster, effective disaster impact factors are obtained.
[0053] In one optional implementation, feature analysis is performed on multiple hazard impact factors corresponding to the target geological hazard to obtain effective hazard impact factors for the target geological hazard. This includes: analyzing the correlation between the multiple hazard impact factors and other hazard impact factors to obtain correlation information of the multiple hazard impact factors; removing hazard impact factors whose correlation information meets preset correlation conditions from the multiple hazard impact factors to obtain multiple initial hazard impact factors. The preset correlation conditions are used to indicate that there is a strong correlation between the hazard impact factors and other hazard impact factors. For correlation analysis, commonly used test indicators include the variance inflation factor (VIF) and tolerance (TOL), which are reciprocals of each other, as shown in the following formula:
[0054] in: It is the i-th impact factor xi The coefficient of determination between the factor and the other influencing factors. i Influencing factors xi The higher the correlation with other influencing factors, A value close to 1 indicates a variance inflation coefficient. VIF The larger the value, the greater the possibility of collinearity among the influencing factors.
[0055] In one alternative implementation, when Tolerance < 0.1 or VIF > 10, a significant correlation is considered to exist, and the correlated factors need to be removed to ensure the stability and reliability of the model parameter estimation.
[0056] In one optional implementation, feature analysis is performed on multiple disaster impact factors corresponding to the target geological disaster to obtain effective disaster impact factors of the target geological disaster. The method further includes: constructing multiple importance analysis sequences based on multiple initial disaster factors, and analyzing the importance of multiple initial disaster impact factors based on multiple importance analysis sequences to obtain importance information of multiple initial disaster impact factors. In this method, the sample arrangement order corresponding to at least one initial disaster factor in the multiple importance analysis sequences is different.
[0057] Specifically, for the same batch of initial disaster factors, multiple importance analysis sequences are generated. Among them, at least one sequence has a different sample point arrangement order than the other sequences. Factor importance calculations are carried out separately for multiple sequences with different sample orders. Furthermore, the importance information of each initial disaster impact factor is obtained by combining the results of multiple analyses.
[0058] For example, the initial disaster factors are slope, rainfall, soil type, and vegetation cover. Based on these factors, two sets of importance analysis sequences are constructed. The first set of samples is arranged in the original geographical order, and the second set of samples is randomly shuffled and rearranged. The order of the samples in the two sets is different. Furthermore, the importance of each factor is calculated using the two sets of sequences respectively. Finally, the results of the two sets are combined to obtain the factor importance information of slope, rainfall, soil type, and vegetation cover.
[0059] In one alternative implementation, an importance analysis is performed by evaluating the contribution of features based on model predictions of performance changes. The basic idea is to randomly permutate a single feature variable while keeping other variables constant, disrupting the correspondence between that variable and the response variable, and then measuring the importance of the feature by comparing the degree of performance change predicted by the model. Here, a set of model input feature vectors corresponds to a set of importance analysis sequences. Each feature factor corresponds to an initial disaster impact factor. The model prediction output is... First, calculate the model's prediction performance metrics on the original test dataset. Sbase The feature vectors without feature permutation are input into the risk assessment model, and the baseline prediction performance of the risk assessment model on the training or test dataset is calculated. This can be obtained using metrics such as AUC, accuracy, or F1 score. Furthermore, for the... Features The sample order is randomly permuted to construct a new dataset. And recalculate the model's predictive performance metrics. The formula for calculating variable importance is shown below:
[0060] in, Indicates the first Importance score of each feature; Indicates the performance of the original model; Representation of features The performance of the model after the permutation. When The larger the value, the greater the contribution of the feature to the model's prediction.
[0061] In one alternative implementation, to reduce random error, each feature is... After several random permutations, the average importance is calculated as shown in the following formula:
[0062] in, Indicates the number of random permutations. Indicates the first Secondary features The model prediction performance index obtained after random permutation.
[0063] In one optional implementation, the initial disaster impact factors whose importance information meets a preset importance condition among multiple initial disaster impact factors are determined as effective disaster impact factors, wherein the preset importance condition is used to indicate that the importance information of the initial disaster impact factors is greater than a preset importance.
[0064] In one optional implementation, based on the importance information of each initial disaster impact factor, factors with importance information greater than a preset importance threshold are selected as effective disaster impact factors for subsequent modeling; correspondingly, factors with importance lower than the threshold are directly eliminated to reduce invalid features interfering with the model.
[0065] In one alternative implementation, the contribution of each influencing factor to the model prediction results is quantified by ranking the importance scores of all features and eliminating factors with lower importance, thereby obtaining a combination of key influencing factors for constructing a landslide probability prediction model.
[0066] Step S303: Based on the training dataset and the test dataset, train the initial risk assessment model to obtain the preset risk assessment model.
[0067] In this embodiment of the invention, the regression coefficients of the initial risk assessment model are automatically solved using the maximum likelihood estimation method based on the training samples. Specifically, landslide samples and non-landslide samples are used as training data, and the sample labels are set as y=1 and y=0. Furthermore, the model is continuously adjusted... and This minimizes the error between the predicted probability and the actual sample label, thus yielding the regression coefficients of each influencing factor. Specifically, The sign and magnitude of the value reflect the direction and intensity of the influence of the corresponding influencing factor on the probability of landslide occurrence.
[0068] In this embodiment of the invention, the model parameters are solved using the training samples through the maximum likelihood estimation method. Specifically, landslide samples are labeled as 1, and non-landslide samples are labeled as 0, and the influencing factors corresponding to each sample are input into the logistic regression model. For the ... j The model calculates the probability of landslide occurrence for each training sample based on the current parameters. Pj And based on the true labels of the samples yj A likelihood function is constructed to characterize the degree of matching between the model's predicted probabilities and the actual landslide and non-landslide labels. When yj When =1, the model hopes Pj As close to 1 as possible; when yj When =0, the model hopes Pj The likelihood function should be as close to 0 as possible. This is achieved by iteratively optimizing the likelihood function of all training samples, continuously adjusting the constant term. β0 Regression coefficients of each influencing factor βi This maximizes the overall likelihood function and ultimately yields the optimal combination of regression coefficients, thereby establishing a functional mapping relationship between the probability of a slide under triggering event conditions and the influencing factors.
[0069] For model validation and optimization, the model prediction results can be evaluated using test sets or cross-validation methods. Indicators such as accuracy, precision, recall, F1 score, and area under the ROC curve (AUC) can be calculated. Based on the evaluation results, the model parameters can be adjusted and optimized to obtain the preset risk assessment model.
[0070] In one optional implementation, the landslide impact factor data obtained after screening is processed for missing values and outliers are removed to ensure the integrity and consistency of the sample data.
[0071] In one alternative implementation, the landslide hazard zoning method can be a threshold classification method, with the classification thresholds determined according to the classification standards in the "Technical Specification for Thematic Map of Earthquake Landslide Probability Hazard Assessment", which includes extremely low hazard zone (<0.01%), low hazard zone (0.01%–0.1%), medium hazard zone (0.1%–1%), high hazard zone (1%–10%), and extremely high hazard zone (>10%).
[0072] Step S202: Based on the location and engineering information of each power transmission facility in the target assessment area, determine the disaster-bearing capacity information of each power transmission facility.
[0073] In this embodiment of the invention, the target assessment area is the geographical scope of the landslide risk assessment being conducted. For example, the entire mountain corridor traversed by a certain ultra-high voltage transmission line. The transmission facilities are the planned disaster-bearing carriers of electricity, which can be ultra-high voltage transmission towers; for example, 1000kV angle steel transmission towers or steel pipe towers.
[0074] In this embodiment of the invention, location information can be the spatial coordinates of the tower and geographical parameters of the surrounding environment. For example, it can be the GPS positioning coordinates of the tower, the tower slope, and the distance between the tower and a nearby river. Engineering information includes relevant attribute data such as the tower's construction, operation, and structure. For example, it can be the line voltage level, the type of tower structure, its service life, and historical damage records.
[0075] In one alternative implementation, the geographical location and environmental parameters of each power transmission facility, as well as the engineering parameters of the structure, construction, and operation of the power transmission facility itself, can be obtained first. Then, the obtained parameters can be normalized, weighted, and fused to directly output the disaster-bearing capacity information of each power transmission facility.
[0076] Step S203: Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, determine the disaster risk information of each power transmission facility.
[0077] In this embodiment of the invention, the disaster risk information of each power transmission facility is the final individual risk data obtained by combining the regional disaster risk and the disaster resistance level of the equipment. It is used to characterize the comprehensive risk level of the corresponding power transmission facility under the influence of the target geological disaster, which may result in damage or failure.
[0078] In this embodiment of the invention, firstly, for each power transmission facility, the regional disaster risk information corresponding to the location of the power transmission facility is obtained; then, the disaster bearing capacity information corresponding to the power transmission facility itself is obtained. Further, based on the regional disaster risk information of the location of the power transmission facility, and combined with the disaster bearing capacity of the power transmission facility, the disaster risk information corresponding to the power transmission facility is output. This processing procedure is repeated for all power transmission facilities within the assessment area to obtain the individual disaster risk information for each power transmission facility.
[0079] Step S204: Based on the disaster risk information of each power transmission facility and the preset insurance quantification model, determine the insurance assessment information of each power transmission facility.
[0080] In this embodiment of the invention, the preset insurance quantification model is a pre-built calculation model adapted to the power geological disaster scenario. The function of the preset insurance quantification model is to transform the equipment disaster risk into an assessment result related to insurance. For example, the preset insurance quantification model can be a standardized calculation model for the risk assessment and underwriting of geological disasters of power transmission facilities.
[0081] In this embodiment of the invention, by uniformly inputting the disaster risk data corresponding to each power transmission facility into a pre-built insurance quantification model, and based on the quantitative assessment logic built into the model, differentiated assessments are performed on power transmission facilities with different risks, and insurance assessment information corresponding to each power transmission facility is automatically generated, thus realizing the complete transformation of power transmission facilities from disaster risk judgment to insurance risk evaluation.
[0082] For example, in the same area, there are two types of power transmission facilities: underground cables and overhead conductors. The geological disaster risks of the two types of equipment are input into an insurance quantification model. The insurance quantification model automatically makes targeted assessments based on the risk differences and outputs insurance assessment information for cables and conductors respectively, thus achieving a refined assessment of power transmission facility insurance.
[0083] The method for quantifying geological disaster insurance risks and making compensation decisions for UHV transmission towers provided in this embodiment can obtain differentiated and individualized disaster risks of transmission facilities, realize the quantitative linkage between geological disaster risks and insurance assessments, effectively improve the precision and scientific nature of disaster risk assessment and insurance business judgment for transmission facilities, and provide quantitative support for power grid disaster prevention and control and power insurance management.
[0084] This embodiment provides a method for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, which can be used in electronic equipment. Figure 4 This is a second flowchart of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention, as follows: Figure 4 As shown, the process includes the following steps: Step S401: Based on the preset risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area to obtain the hazard risk information of the target assessment area.
[0085] Specifically, step S401 includes: S4011, Obtain trigger event data for the target evaluation area.
[0086] In this embodiment of the invention, the triggering event data is data related to the external driving conditions that can induce the target geological disaster, and is used to reflect the actual situation of the triggering event.
[0087] In this embodiment of the invention, raw data on triggering events that could cause geological disasters within the target assessment area are collected to obtain the raw data on triggering events in the corresponding area. For example, when conducting a landslide risk assessment on a mountainous power transmission corridor, recent heavy rainfall data for the area is retrieved from a meteorological data source; this data constitutes the obtained triggering event data and is used for subsequent risk assessment.
[0088] S4012, input the trigger event data of the target assessment area into the preset risk assessment model to obtain the disaster risk information of the target assessment area.
[0089] In this embodiment of the invention, the collected data on triggered events in the target assessment area are fed into a pre-trained risk assessment model. The model then uses the learned disaster occurrence patterns to perform calculations and outputs disaster risk information for the entire target assessment area.
[0090] For example, for a power transmission corridor in a mountainous area, the rainfall distribution data of the area is input into a pre-trained landslide risk assessment model. Furthermore, the model combines the learned rainfall-landslide correspondence to calculate and output the probability of landslide occurrence at each geographical location in the assessment area, which is the disaster risk information of the target assessment area.
[0091] In this embodiment of the invention, a landslide event database is constructed. Based on remote sensing images before and after triggering events, such as rainfall or earthquakes, and combined with historical disaster survey data and information on triggering events like rainfall and earthquakes, the database acquires attribute information such as the spatial location, area, and occurrence time of landslides within the study area. The selection criteria for remote sensing images can be set as follows: the image resolution should be no less than 6 meters, and the cloud cover should be less than 10% to ensure image clarity and boundary recognition accuracy. The landslide database mainly includes information characterizing the specific situation of landslides, such as spatial location, boundaries, area, occurrence time, triggering type, and morphological characteristics. It also integrates historical geological disaster survey data and field investigation data. The attribute information of each landslide event is uniformly formatted and organized in vector or raster data formats, such as .shp, .kml, or .tif formats, to construct a landslide event database that can be used for triggering event conditional probability modeling and subsequent landslide probability prediction model training.
[0092] In this embodiment of the invention, a landslide influencing factor dataset is constructed. Specifically, landslide influencing factors such as geology, topography, meteorology, hydrology, and human engineering activities are selected. Spatial registration and normalization are performed on each influencing factor to establish a landslide influencing factor dataset with a unified resolution. The influencing factors may include: topographic factors, such as elevation, slope, aspect, curvature, and other topographic relief; geological factors, such as soil type, rock structure, or distance from faults; hydrological and meteorological factors, such as distance from rivers or topographic humidity index; triggering factors, such as rainfall or seismic parameters; and other factors that can be further explained, such as vegetation cover or land use type. Spatial registration, rasterization, and normalization or encoding are performed on the various factor data to unify them to a 30-meter spatial resolution, constructing a multi-factor raster dataset that can be used for landslide probability modeling.
[0093] In this embodiment of the invention, a disaster-bearing body database for ultra-high voltage (UHV) transmission line towers is constructed. Specifically, spatial location data and engineering attribute data of UHV transmission line towers within the study area are collected, including tower coordinates, associated line, voltage level, construction year, operational year, design bearing capacity, and historical damage records. The tower data undergoes spatial verification and attribute organization to establish a complete UHV transmission line tower disaster-bearing body database. This disaster-bearing body database includes collecting attribute information such as spatial coordinates, associated line, voltage level, tower type, foundation type, construction and operational year, design bearing capacity, and historical damage records for all towers within the study area. Spatial data undergoes GIS verification to ensure location accuracy, and attribute data is formatted in a unified way and missing values are supplemented, forming a database that can be used for disaster-bearing body vulnerability analysis.
[0094] Step S402: Based on the location and engineering information of each power transmission facility in the target assessment area, determine the disaster-bearing capacity information of each power transmission facility.
[0095] Please see details Figure 2 Step S202 of the illustrated embodiment will not be described again here.
[0096] Step S403: Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, determine the disaster risk information of each power transmission facility.
[0097] Please see details Figure 2 Step S203 of the illustrated embodiment will not be described again here.
[0098] Step S404: Based on the disaster risk information of each power transmission facility and the preset insurance quantification model, determine the insurance assessment information of each power transmission facility.
[0099] Please see details Figure 2Step S204 of the illustrated embodiment will not be described again here.
[0100] The method for quantifying geological disaster insurance risks and making compensation decisions for UHV transmission towers provided in this embodiment can assess geological disaster risks based on trigger event data, effectively distinguish individual disaster resistance differences of transmission facilities, avoid the result deviation caused by static assessment, and complete the full-link quantitative calculation from triggering conditions to insurance assessment, effectively improving the real-time performance and accuracy of risk assessment.
[0101] This embodiment provides a method for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, which can be used in electronic equipment. Figure 5 This is a third flowchart of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention, as follows: Figure 5 As shown, the process includes the following steps: Step S501: Based on the preset risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area to obtain the hazard risk information of the target assessment area.
[0102] Please see details Figure 2 Step S201 of the illustrated embodiment will not be described again here.
[0103] Step S502: Based on the location and engineering information of each power transmission facility in the target assessment area, determine the disaster-bearing capacity information of each power transmission facility.
[0104] Specifically, step S502 above includes: S5021, the environmental sensitivity information and importance information of each power transmission facility are weighted respectively to obtain the exposure index of each power transmission facility.
[0105] In this embodiment of the invention, the exposure index is used to characterize the degree of exposure of power transmission facilities to geological hazards. Specifically, a higher value indicates that the facility is more easily exposed to the effects of the hazard.
[0106] In one alternative implementation, the tower exposure index model can be constructed using exposure... This represents the degree to which the i-th tower is exposed to the landslide hazard environment under the triggering event conditions. Influencing factors include, but are not limited to, the importance of the transmission line, the sensitivity of the surrounding environment, and other factors that may affect the degree of damage to the tower, as shown in the following formula:
[0107] in, The importance coefficient of the transmission line to which the tower belongs is used to characterize the importance of the transmission line in the power grid system. This coefficient is obtained by classifying and standardizing the transmission line according to the line voltage level, transmission capacity or importance of the power grid node. This is a sensitivity index for the environment surrounding power poles, used to characterize the sensitivity of the natural environment around power poles to landslide disasters. The index is calculated by weighting environmental factors such as slope, distance from river, topographic humidity index, and land use type after normalization. , For the corresponding weight coefficients, and satisfying + =1. This weighting coefficient is determined using the analytic hierarchy process or based on historical disaster statistical data analysis, and is used to reflect the degree of influence of different factors on tower exposure.
[0108] S5022 calculates the vulnerability index of each power transmission facility by weighting its structural type, operating time, and historical damage information.
[0109] In this embodiment of the invention, the vulnerability index is used to characterize the ease with which power transmission facilities are damaged after being subjected to geological disasters. Specifically, the higher the value, the more easily the facility is damaged.
[0110] In one alternative implementation, the tower vulnerability index model can be constructed using vulnerability... Indicates the first The vulnerability of a tower to damage under landslide action is influenced by factors including, but not limited to, tower structure type, service life, historical damage, and other engineering factors that may affect structural stability, as shown in the following formula:
[0111] in, For tower structure type coefficient, This is a standardized value for the service life of the tower. Indicators for historical damage records of power poles, , , For the corresponding weight coefficients, and satisfying The weighting coefficients are determined using the analytic hierarchy process (AHP) or based on historical disaster loss statistics, and are used to characterize the degree of influence of different factors on the vulnerability of the tower structure.
[0112] In this embodiment of the invention, the above-mentioned indicators are normalized to make... and All in Within the interval, to ensure the stability of subsequent risk coupling calculations.
[0113] Step S503: Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, determine the disaster risk information of each power transmission facility.
[0114] Please see details Figure 2 Step S203 of the illustrated embodiment will not be described again here.
[0115] Step S504: Based on the disaster risk information of each power transmission facility and the preset insurance quantification model, determine the insurance assessment information of each power transmission facility.
[0116] Please see details Figure 2 Step S204 of the illustrated embodiment will not be described again here.
[0117] This embodiment provides a method for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, which can be used in electronic equipment. Figure 6 This is a fourth flowchart of the method for quantifying and deciding on the risk of geological disaster insurance for ultra-high voltage power transmission towers according to an embodiment of the present invention, as follows: Figure 6 As shown, the process includes the following steps: Step S601: Based on the preset risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area to obtain the hazard risk information of the target assessment area.
[0118] Please see details Figure 2 Step S201 of the illustrated embodiment will not be described again here.
[0119] Step S602: Based on the location and engineering information of each power transmission facility in the target assessment area, determine the disaster-bearing capacity information of each power transmission facility.
[0120] Please see details Figure 2 Step S202 of the illustrated embodiment will not be described again here.
[0121] Step S603: Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, determine the disaster risk information of each power transmission facility.
[0122] Specifically, step S603 above includes: Step S6031: Based on the disaster risk information of the target assessment area, determine the disaster risk information of each power transmission facility's location.
[0123] In this embodiment of the invention, the disaster risk information of the location of the power transmission facility is a risk value extracted from the risk of the entire region and corresponding one-to-one with the geographical location of the individual power transmission facility, which is used to indicate the degree of danger of geological disasters occurring at the location of the equipment.
[0124] Step S6032: Multiply the disaster risk information of each power transmission equipment location, the exposure index and vulnerability index of the power transmission facility, respectively, to obtain the disaster risk information of each power transmission facility.
[0125] In this embodiment of the invention, the disaster risk information of the power transmission facility is used to characterize the comprehensive risk of damage and failure of the facility under geological disasters.
[0126] In this embodiment of the invention, for each power transmission facility, the corresponding exposure index, vulnerability index, and disaster risk information of the power transmission facility are multiplied together to couple the probability of disaster occurrence at the location, the facility exposure level, and the facility vulnerability degree to calculate the comprehensive disaster risk information of the power transmission facility.
[0127] For example, the landslide disaster risk of a certain tower location is 0.7, the exposure index is 0.8, and the vulnerability index is 0.7; multiplying these three values together gives 0.392. This 0.392 is the disaster risk information of the tower, representing the comprehensive risk level of the tower being damaged and failing after being subjected to a landslide.
[0128] In one optional implementation, the formula for calculating the disaster risk information of each transmission facility is as follows:
[0129] in, Indicates the first i Disaster risk information for individual ultra-high voltage power transmission towers. Indicates the first i The probability of a landslide occurring at the location of each tower. Indicates the first i Exposure index of each tower, Indicates the first i Vulnerability index of individual towers.
[0130] Step S604: Based on the disaster risk information of each power transmission facility and the preset insurance quantification model, determine the insurance assessment information of each power transmission facility.
[0131] Please see details Figure 2 Step S204 of the illustrated embodiment will not be described again here.
[0132] The method for quantifying and deciding on compensation for geological disaster insurance of UHV transmission towers provided in this embodiment can integrate the probability of disasters occurring in transmission facilities, the exposure level of facilities, and the vulnerability of facilities. It can accurately quantify the comprehensive risk of tower damage and failure, reduce the assessment bias caused by the overall risk of the directly used area, realize the quantitative calculation of tower disaster risk, and effectively improve the quantitative level and accuracy of tower landslide insurance assessment.
[0133] This embodiment provides a method for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, which can be used in electronic equipment. Figure 7 This is the fifth flowchart of the method for quantifying risks and making compensation decisions for geological disaster insurance of ultra-high voltage power transmission towers according to an embodiment of the present invention, as follows: Figure 7 As shown, the process includes the following steps: Step S701: Based on the preset risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area to obtain the hazard risk information of the target assessment area.
[0134] Please see details Figure 2 Step S201 of the illustrated embodiment will not be described again here.
[0135] Step S702: Based on the location and engineering information of each power transmission facility in the target assessment area, determine the disaster-bearing capacity information of each power transmission facility.
[0136] Please see details Figure 2 Step S202 of the illustrated embodiment will not be described again here.
[0137] Step S703: Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility, determine the disaster risk information of each power transmission facility.
[0138] Please see details Figure 2 Step S203 of the illustrated embodiment will not be described again here.
[0139] Step S704: Based on the disaster risk information of each power transmission facility and the preset insurance quantification model, determine the insurance assessment information of each power transmission facility.
[0140] Specifically, step S704 above includes: Step S7041: Input the disaster risk information of each power transmission facility into the first insurance quantification model to obtain the insurance premium information of each power transmission facility.
[0141] In this embodiment of the invention, the first insurance quantification model is a preset calculation model used to convert insurance rates based on the disaster risks of power transmission facilities. By taking the pre-calculated disaster risks of each power transmission facility as input, and feeding them one by one into the first insurance quantification model, the model performs the conversion according to the level of risk and outputs insurance rate information specific to each power transmission facility, thereby realizing the quantitative conversion of disaster risks into insurance rates.
[0142] In one optional implementation, the insurance premium calculation model has the following calculation formula:
[0143] in: For the first i Insurance rates for individual towers; The basic insurance premium is determined based on the statistical results of historical landslide disaster loss rates in the study area or the benchmark premium rate of the insurance industry, and is used to represent the basic premium rate under the average risk level. The comprehensive risk index for poles and towers; The risk adjustment coefficient is determined through statistical regression analysis or least squares fitting between the historical disaster risk index and the actual loss rate, and is used to adjust the degree of influence of the risk index on the insurance premium rate.
[0144] The historical disaster risk index is calculated based on the hazard, exposure, and vulnerability data corresponding to the periods when historical landslide disasters occurred. Specifically, existing recorded historical landslide disaster events are selected, and the landslide hazard index, tower exposure index, and tower vulnerability index at the time of the disaster are spatially matched. The corresponding historical disaster risk index for the tower or line section is then obtained according to a comprehensive risk calculation model. The actual loss rate is calculated based on data such as direct economic losses, repair and emergency repair costs, equipment replacement costs, downtime losses, or insurance claims caused by historical disasters. It can be expressed as the ratio between the actual loss amount and the insured value of the tower, the asset value of the equipment, or the insured amount. Furthermore, the historical disaster risk index and the actual loss rate are subjected to statistical regression or least squares fitting to determine the risk adjustment coefficient.
[0145] In step S7042, the disaster risk information of each power transmission facility is input into the second insurance quantification model to obtain the expected loss information of each power transmission facility.
[0146] In this embodiment of the invention, the second insurance quantification model is a pre-configured calculation model used to calculate expected losses based on the disaster risks of power transmission facilities. Specifically, by taking the individual disaster risks of each power transmission facility as input, the second insurance quantification model is fed into it. This model combines the risk level to perform loss extrapolation and outputs the expected loss information corresponding to each power transmission facility, thus completing the quantitative conversion of disaster risks into estimated insurance losses.
[0147] In one alternative implementation, the calculation formula for the expected insurance loss is as follows:
[0148] in: Indicates the first i The expected loss of each tower; This indicates the comprehensive risk index of the pole / tower. This indicates the insured value or reconstruction cost of the pole.
[0149] Step S7043: Determine the insurance liability limit based on the insurance premium rate information and expected loss information of each power transmission facility.
[0150] In this embodiment of the invention, the insurance liability limit is the maximum compensation amount agreed upon in the insurance for the power transmission facility, and is a key parameter for insurance underwriting. Specifically, by utilizing the insurance premium rate information and expected loss information of each power transmission facility, and combining the numerical relationship between the two, an insurance liability limit suitable for the facility is obtained, so that the compensation limit matches the facility's risk, loss, and premium level.
[0151] In one alternative implementation, after a landslide occurs, the compensation amount for the tower is calculated based on the on-site loss assessment results and the insurance contract stipulations, as shown in the following formula:
[0152] in: For the first The final compensation amount for each pole; The actual amount of loss caused by the disaster; This is the maximum liability limit stipulated in the insurance contract.
[0153] In this embodiment of the invention, after the insurance claim is completed, the relevant parameters in the tower risk index model are updated and corrected based on the actual disaster loss data, the amount of compensation, and the frequency of disaster occurrence. This enables closed-loop decision support for the landslide disaster risk quantification results on insurance rates, compensation amounts, and insurance management strategies, thereby continuously optimizing landslide disaster insurance pricing and compensation decisions and improving the accuracy and reliability of insurance risk management.
[0154] This embodiment also provides a device for risk quantification and compensation decision-making for geological disaster insurance of ultra-high voltage power transmission towers. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0155] This embodiment provides a device for quantifying risks and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, such as... Figure 8 As shown, it includes: The assessment module 801 is used to preset a risk assessment model, conduct risk assessment of the target geological hazards in the target assessment area, and obtain the disaster risk information of the target assessment area. The disaster bearing capacity information determination module 802 is used to determine the disaster bearing capacity information of each power transmission facility based on the location information and engineering information of each power transmission facility in the target assessment area. The disaster risk information determination module 803 is used to determine the disaster risk information of each power transmission facility based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each power transmission facility. The insurance assessment information determination module 804 is used to determine the insurance assessment information of each power transmission facility based on the disaster risk information of each power transmission facility and the preset insurance quantification model.
[0156] In some alternative implementations, the evaluation module 801 includes: The acquisition unit is used to acquire trigger event data of the target evaluation area.
[0157] The input unit is used to input the trigger event data of the target assessment area into the preset risk assessment model to obtain the disaster risk information of the target assessment area.
[0158] In some optional implementations, the evaluation module 801 further includes: The determining unit is used to determine the triggering probability of a target geological disaster based on the ratio of the range of the target geological disaster caused by the triggering event to the coverage range of the triggering event.
[0159] The sampling unit is used to sample within the coverage area of the triggering event based on the triggering probability of the triggering event corresponding to the target geological disaster, and obtain sample data.
[0160] In some optional implementations, the disaster risk information determination module 803 includes: The disaster risk information determination unit is used to determine the disaster risk information of each power transmission facility based on the disaster risk information of the target assessment area.
[0161] The multiplication unit is used to multiply the disaster risk information of each power transmission equipment location, the exposure index and vulnerability index of the power transmission facility, respectively, to obtain the disaster risk information of each power transmission facility.
[0162] In some optional implementations, the insurance assessment information determination module 804 further includes: The first input unit inputs the disaster risk information of each power transmission facility into the first insurance quantification model to obtain the insurance premium information of each power transmission facility.
[0163] The second input unit inputs the disaster risk information of each power transmission facility into the second insurance quantification model to obtain the expected loss information of each power transmission facility.
[0164] The insurance liability limit is determined based on the insurance premium rate information and expected loss information of each transmission facility.
[0165] The UHV tower geological disaster insurance risk quantification and compensation decision-making device provided in this embodiment of the invention can execute the UHV tower geological disaster insurance risk quantification and compensation decision-making method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.
[0166] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0167] The following is a detailed reference. Figure 9 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in ROM 902 or a program loaded from memory 908 into RAM 903. RAM 903 also stores various programs and data required for the operation of the electronic device. The processor 901, ROM 902, and RAM 903 are interconnected via bus 904. An input / output (I / O) interface 905 is also connected to bus 904; wherein, ROM is a read-only memory and RAM is a random access memory.
[0168] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 9 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0169] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the method for risk quantification and compensation decision-making for geological disaster insurance of ultra-high voltage power transmission towers according to embodiments of the present invention.
[0170] Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0171] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the risk quantification and compensation decision-making method for geological disaster insurance of ultra-high voltage power transmission towers shown in the above embodiments is implemented.
[0172] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0173] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for quantifying risks and making compensation decisions in geological disaster insurance for ultra-high voltage power transmission towers, characterized in that, The method includes: Based on a preset risk assessment model, a risk assessment of the target geological hazard is conducted on the target assessment area to obtain the hazard risk information of the target assessment area. The preset risk assessment model is trained based on sample data of the triggering events corresponding to the target geological hazard. Based on the location and engineering information of each power transmission facility in the target assessment area, the disaster bearing capacity information of each power transmission facility is determined; Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each of the power transmission facilities, the disaster risk information of each of the power transmission facilities is determined respectively; Based on the disaster risk information of each of the aforementioned power transmission facilities and the preset insurance quantification model, the insurance assessment information of each of the aforementioned power transmission facilities is determined.
2. The method according to claim 1, characterized in that, The process involves conducting a risk assessment of the target geological hazards in the target assessment area based on a preset risk assessment model, thereby obtaining hazard risk information for the target assessment area, including: Acquire the trigger event data of the target evaluation area; The trigger event data of the target assessment area is input into the preset risk assessment model to obtain the disaster risk information of the target assessment area.
3. The method according to claim 1 or 2, characterized in that, The preset risk assessment model is trained in the following way: Based on a preset ratio, the sample data is divided into a training dataset and a test dataset; Based on the mapping relationship between the effective disaster impact factors of the target geological disaster and the disaster risk information of the target assessment area, an initial risk assessment model is constructed. The initial risk assessment model is trained based on the training dataset and the test dataset to obtain the preset risk assessment model.
4. The method according to claim 3, characterized in that, The method further includes: Based on the ratio of the range of the target geological disaster caused by the triggering event to the coverage area of the triggering event, the triggering probability of the triggering event corresponding to the target geological disaster is determined. Based on the triggering probability of the triggering event corresponding to the target geological disaster, sampling is performed within the coverage area of the triggering event to obtain the sample data.
5. The method according to claim 3, characterized in that, The method further includes: The characteristics of multiple disaster impact factors corresponding to the target geological disaster are analyzed to obtain the effective disaster impact factors of the target geological disaster.
6. The method according to claim 5, characterized in that, The method involves performing feature analysis on multiple disaster impact factors corresponding to the target geological disaster to obtain the effective disaster impact factors of the target geological disaster, including: The correlation between multiple disaster impact factors and other disaster impact factors is analyzed to obtain correlation information of multiple disaster impact factors; Disaster impact factors whose correlation information satisfies a preset correlation condition are removed from the multiple disaster impact factors to obtain multiple initial disaster impact factors. The preset correlation condition is used to indicate that the disaster impact factor has a strong correlation with other disaster impact factors. Multiple importance analysis sequences are constructed based on multiple initial disaster factors, and the importance of the multiple initial disaster impact factors is analyzed based on the multiple importance analysis sequences to obtain the importance information of the multiple initial disaster impact factors. Among the multiple importance analysis sequences, the sample arrangement order corresponding to at least one of the initial disaster factors is different. The initial disaster impact factors whose importance information meets the preset importance condition among the multiple initial disaster impact factors are determined as the effective disaster impact factors, wherein the preset importance condition is used to indicate that the importance information of the initial disaster impact factors is greater than the preset importance.
7. The method according to claim 1, characterized in that, The location information includes environmental sensitivity information of the power transmission facility; the engineering information includes importance information, structural type information, operating time information, and historical damage information of the power transmission facility; and the disaster bearing capacity information includes the exposure index and vulnerability index of the power transmission facility. The process of determining the disaster-bearing capacity information of each power transmission facility based on its location and engineering information within the target assessment area includes: The environmental sensitivity information and importance information of each of the power transmission facilities are weighted separately to obtain the exposure index of each of the power transmission facilities; The vulnerability index of each power transmission facility is obtained by weighting the structural type information, operating time information and historical damage information of each facility.
8. The method according to claim 1, characterized in that, Based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each of the power transmission facilities, the disaster risk information of each of the power transmission facilities is determined, including: Based on the disaster risk information of the target assessment area, the disaster risk information of each of the power transmission facilities is determined. The disaster risk information of each power transmission facility is obtained by multiplying the disaster risk information of the location of each power transmission facility, the exposure index of the power transmission facility, and the vulnerability index of the power transmission facility.
9. The method according to claim 1, characterized in that, The process of determining insurance assessment information for each of the aforementioned power transmission facilities based on disaster risk information and a pre-defined insurance quantification model includes: The disaster risk information of each of the aforementioned power transmission facilities is input into the first insurance quantification model to obtain the insurance premium information of each of the aforementioned power transmission facilities; The disaster risk information of each of the aforementioned power transmission facilities is input into the second insurance quantification model to obtain the expected loss information of each of the aforementioned power transmission facilities; Based on the insurance premium information and expected loss information of each of the aforementioned power transmission facilities, an insurance liability limit is determined. This insurance liability limit is used to compare with the actual loss to determine the actual compensation information.
10. A device for quantifying risk and making compensation decisions for geological disaster insurance on ultra-high voltage power transmission towers, characterized in that, The device includes: The assessment module is used to preset a risk assessment model, conduct a risk assessment of the target geological hazards in the target assessment area, and obtain the hazard risk information of the target assessment area; The disaster bearing capacity information determination module is used to determine the disaster bearing capacity information of each power transmission facility based on the location information and engineering information of each power transmission facility in the target assessment area. The disaster risk information determination module is used to determine the disaster risk information of each of the power transmission facilities based on the disaster risk information of the target assessment area and the disaster bearing capacity information of each of the power transmission facilities. The insurance assessment information determination module is used to determine the insurance assessment information of each of the power transmission facilities based on the disaster risk information of each of the power transmission facilities and the preset insurance quantification model.
