Debris flow prevention and control comprehensive evaluation method and system based on ductile disaster reduction

Abstract

The invention belongs to the field of ductile disaster reduction, and discloses a debris flow prevention and control comprehensive evaluation method, system and equipment based on ductile disaster reduction and a medium. The assessment method comprises the following steps: obtaining historical core element data, determining the weight of each element by using an entropy evaluation method, calculating the contribution degrees of the elements under different dimensions to ductile disaster reduction, and carrying out weighted average to obtain disaster reduction toughness; distinguishing first element data directly related to disaster reduction toughness and second element data indirectly related to disaster reduction toughness according to the contribution degree, and associating the first element data in pairs to generate third element data; and finally, constructing a structural equation model, and generating a prevention and control comprehensive evaluation model by utilizing the data and disaster reduction toughness training for preset region evaluation. Weights are distributed objectively through an entropy method, and subjective deviation is avoided; multi-dimensional elements and association thereof are comprehensively considered, and disaster reduction toughness is accurately quantified; the constructed model can systematically evaluate the prevention and control condition of the preset area, provides a scientific basis for debris flow prevention and control, and improves the rationality and effectiveness of prevention and control decisions.

Description

Technical Field

[0001] This application belongs to the field of resilience disaster reduction, and specifically relates to a comprehensive assessment method, system, equipment and medium for debris flow prevention and control based on resilience disaster reduction. Background Technology

[0002] Current research on debris flow prevention and control has formed a technical system based on "engineering measures as the main approach and monitoring and early warning as the supplementary approach," focusing on single elements such as topographic and geomorphological transformation, interception and drainage projects, and rainfall monitoring and early warning.

[0003] Current research approaches still suffer from insufficient analysis of factor correlations. Most studies focus only on the impact of a single factor on disasters, neglecting the interactions between natural, engineering, and social factors, leading to one-sided assessment results. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a comprehensive assessment method, system, equipment, and medium for debris flow prevention and control based on resilience mitigation. This solution comprehensively considers multiple dimensions and their interrelationships, accurately quantifying disaster mitigation resilience.

[0005] To address the aforementioned technical problems, the first aspect of this disclosure proposes a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, the assessment method comprising: Obtain core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data. The contribution of each core element data under different dimensions to the resilience and disaster reduction is calculated, and the disaster reduction resilience is obtained by weighted averaging of each contribution and its corresponding weight value. Based on the contribution, determine the first element data that is directly related to the disaster reduction resilience and the second element data that is indirectly related to the core element data, and then associate the first element data in pairs to generate the third element data. A structural equation model is constructed, and a comprehensive prevention and control assessment model is generated by training the structural equation model with the first element data, the second element data, the third element data, and the disaster reduction resilience. The comprehensive prevention and control assessment model is then used to conduct a comprehensive prevention and control assessment of the preset area.

[0006] According to a preferred embodiment of this disclosure, the construction of a structural equation model, which involves training the structural equation model using the first element data, the second element data, and the third element data to generate a comprehensive prevention and control assessment model, includes: Construct a structural equation model that includes the path mapping relationships between the first element data, the second element data, and the third element data and the disaster reduction resilience, respectively; The structural equation model is fitted using the first element data, the second element data, the third element data, and the disaster mitigation resilience; and the model fit of the fitted structural equation model is calculated. When the model fit meets the preset requirements, the trained comprehensive evaluation model for prevention and control is obtained; When the model fit does not meet the preset requirements, the path coefficients of the path mapping relationship of the structural equation model are adjusted, and the model fit is recalculated until the model fit meets the preset requirements, thus obtaining the trained comprehensive evaluation model for prevention and control.

[0007] According to a preferred embodiment of this disclosure, the evaluation method further includes: Adjust the values ​​of the first element data, the second element data, or the third element data multiple times according to the preset value interval, and determine the model fit after each value adjustment through the trained comprehensive prevention and control evaluation model. When the fluctuation range of the model fit is less than the preset fluctuation range, the data quality of the first element data, second element data, or third element data of the adjusted values ​​is verified or removed, and the prevention and control comprehensive evaluation model is refitted.

[0008] According to a preferred embodiment of this disclosure, the acquisition of core element data related to debris flow resilience and disaster reduction from historical data includes: Obtain multi-source raw data from historical data, including geological data, topographic data, meteorological data, engineering measures data, and historical disaster data; Based on the grey relational analysis method, the correlation between multi-source raw data and debris flow disasters is analyzed and calculated; Multi-source raw data whose correlation degree meets the preset correlation degree requirements are used as disaster reduction correlation data; The continuous disaster reduction correlation data is standardized to generate the first correlation data; One-hot encoding is performed on the categorized disaster mitigation correlation data to generate second correlation data; Then, the various disaster reduction-related data are combined into a third related data through weighted summation; The first associated data, the second associated data, and the third associated data are used as the core element data.

[0009] According to a preferred embodiment of this disclosure, the calculation of the contribution of each of the core element data in different dimensions to the resilience and disaster reduction includes: Based on the PSR model algorithm, the core element data is divided into stress dimension, state dimension and response dimension; The analysis of core element data reveals the first influence trend of the stress dimension data on the state dimension data, the second influence trend of the stress dimension data on the response dimension data, and the third influence trend of the response dimension data on the state dimension data. Based on the first influence trend, the second influence trend, and the third influence trend, the contribution of each core element data to the resilience and disaster reduction is calculated.

[0010] According to a preferred embodiment of this disclosure, the evaluation method further includes: Multiple sets of disaster data are selected from the historical data, and the historical core element data and corresponding disaster data in each set of disaster data are determined. By processing the historical core element data through the aforementioned comprehensive prevention and control assessment model, the predicted historical disaster reduction resilience is obtained. The predicted historical disaster resilience is compared with the disaster data to determine the relative deviation of the prediction, and the comprehensive relative deviation of multiple sets of disaster data is calculated. When the overall relative deviation is greater than the preset deviation, the overall prevention and control assessment model is corrected.

[0011] According to a preferred embodiment of this disclosure, the step of conducting a comprehensive prevention and control assessment of a preset area using the comprehensive prevention and control assessment model includes: Obtain data on the core elements to be evaluated in the preset area; The data of the core elements to be evaluated are processed by the comprehensive prevention and control assessment model to determine the disaster reduction resilience of the preset area to be evaluated. The resilience level is determined by assessing the disaster reduction resilience, and prevention and control recommendations are sent according to the handling methods corresponding to the resilience level in the preset resilience level table.

[0012] To address the aforementioned technical problems, a second aspect of this disclosure proposes a comprehensive assessment system for debris flow prevention and control based on resilience mitigation, the assessment system comprising: The data processing module is used to acquire core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data. The disaster resilience determination module is used to calculate the contribution of each core element data under different dimensions to the resilience disaster reduction, and to obtain the disaster resilience by weighted averaging of each contribution and its corresponding weight value. The data classification module is used to determine, based on the contribution, the first element data directly related to the disaster reduction resilience and the second element data indirectly related to the core element data, and to generate the third element data by associating the first element data in pairs. The assessment model construction module is used to construct a structural equation model, and to train the structural equation model using the first element data, the second element data, the third element data, and the disaster reduction resilience to generate a comprehensive prevention and control assessment model. The comprehensive assessment module is used to conduct a comprehensive assessment of the prevention and control of a preset area using the comprehensive prevention and control assessment model.

[0013] To address the aforementioned technical problems, a third aspect of this disclosure provides an electronic device, comprising: Processor; and A memory storing computer-executable instructions, which, when executed, cause the processor to perform the method described in any of the above embodiments.

[0014] To address the aforementioned technical problems, a fourth aspect of this disclosure provides a computer storage medium that stores one or more programs, which, when executed by a processor, implement the method described in any of the above embodiments.

[0015] Compared with existing technologies, this application has the following advantages: By acquiring historical core element data, the weight of each element is determined using the entropy method, and the contribution of elements to resilience and disaster reduction under different dimensions is calculated and weighted averaged to obtain disaster reduction resilience; based on the contribution, the first element data directly related to disaster reduction resilience and the second element data indirectly related are distinguished, and the first element data are correlated pairwise to generate third element data; finally, a structural equation model is constructed, and a comprehensive prevention and control assessment model is generated using the above data and disaster reduction resilience for assessment of the preset area. The entropy method objectively allocates weights, avoiding subjective bias; it comprehensively considers multi-dimensional elements and their correlations, accurately quantifying disaster reduction resilience; the constructed model can systematically assess the prevention and control situation of the preset area, providing a scientific basis for debris flow prevention and control, and improving the rationality and effectiveness of prevention and control decisions.

[0016] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1A schematic diagram of one of the flowcharts of a comprehensive assessment method for debris flow prevention and control based on resilience mitigation according to an embodiment of the present disclosure is shown. Figure 2 A second schematic diagram of a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, according to an embodiment of this disclosure, is shown. Figure 3 A flowchart of a method for verifying the quality of element data according to an embodiment of the present disclosure is shown; Figure 4 A schematic diagram of a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, according to an embodiment of this disclosure, is shown in part three. Figure 5 A schematic diagram of the process for a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, according to an embodiment of this disclosure, is shown in Part IV. Figure 6 A schematic diagram of a comprehensive assessment system for debris flow prevention and control based on resilience mitigation, according to an embodiment of the present disclosure, is shown. Figure 7 A schematic diagram of an electronic device structure according to an embodiment of the present disclosure is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The same reference numerals in the accompanying drawings denote the same or similar elements, components, or parts, and therefore repeated descriptions of the same or similar elements, components, or parts may be omitted below. It should also be understood that although qualifiers such as first, second, third, etc., indicating numbers may be used herein to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these qualifiers. That is, these qualifiers are only used to distinguish one from another. For example, a first device may also be referred to as a second device, without departing from the essence of the technical solution of this disclosure. Furthermore, the terms "and / or" and "and / or" refer to all combinations including the first or more of the listed items.

[0021] Please see Figure 1 , Figure 1 This is one of the flowcharts of a comprehensive assessment method for debris flow prevention and control based on resilience mitigation provided in this disclosure, such as... Figure 1 As shown, the evaluation methods include: S11. Obtain core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data.

[0022] In this embodiment, core data closely related to debris flow resilience and mitigation are precisely selected from historical data, covering multiple dimensions such as natural (e.g., topography, rainfall), engineering (e.g., the condition of retaining structures), and social (e.g., emergency response capabilities). Then, the entropy method is used to objectively determine the weight of each core data element in the resilience and mitigation assessment system based on its information entropy. On the one hand, the entropy method determines weights based on the characteristics of the data itself, avoiding the arbitrariness of subjective weighting and making the weight allocation more scientific and reasonable. On the other hand, it can fully explore the value of historical data and comprehensively consider the impact of each core element on debris flow resilience and mitigation, laying a solid foundation for subsequent accurate assessment of mitigation effects and the formulation of prevention and control strategies.

[0023] In this embodiment, multi-source raw data is obtained from historical data, including geological data, topographic data, meteorological data, engineering measures data, and historical disaster data. Based on the grey relational analysis method, the correlation between the multi-source raw data and debris flow disasters is analyzed and calculated. Multi-source raw data whose correlation meets the preset correlation requirements are used as disaster reduction correlation data. Continuous disaster reduction correlation data is standardized to generate first correlation data. Disaster reduction correlation data of different types is uniquely encoded to generate second correlation data. The first and second correlation data are used as core element data.

[0024] In this embodiment, data collection involves integrating remote sensing imagery (e.g., vegetation cover), geological survey data (e.g., lithological distribution), meteorological data (e.g., rainfall intensity), and engineering data (e.g., location of silt-trapping dams). Correlation analysis is performed using Pearson / Spearman correlation coefficients or grey relational analysis to screen for elements significantly correlated with the resilience index (e.g., vegetation cover, slope, silt-trapping dam density). Principal component analysis (PCA) is used to reduce the dimensionality of high-dimensional data and extract the principal components with the largest explained variance as key elements. Standardization is used to generate correlated data: Min-Max or Z-score standardization is applied to indicators of different dimensions to eliminate scale differences. Examples: Vegetation cover (0-100%) → standardized to 0-1; Rainfall intensity (mm / h) → standardized to 0-1. Classification and coding are performed: Qualitative indicators (e.g., lithological type) are numerically coded (e.g., sandstone = 1, mudstone = 2). Index synthesis: A comprehensive index is synthesized by weighted summation or entropy weighting (e.g., erosion modulus = vegetation coverage × 0.3 + slope × 0.5 + rainfall intensity × 0.2).

[0025] In this embodiment, the data source is determined by the following requirements: 1. Representativeness: covering the entire chain of debris flow formation, movement, and disaster; 2. Measurability: the data is available and the quantification method is clear; 3. Dynamism: able to reflect spatiotemporal changes (such as seasonal vegetation cover and engineering aging).

[0026] In this embodiment, literature review and expert consultation can be conducted to review the current status of debris flow resilience research at home and abroad, and combine disaster prevention and mitigation theories to screen key elements (such as topography, vegetation cover, engineering measures, monitoring and early warning, emergency response, etc.).

[0027] In this embodiment, the index weights can also be determined by following the principles of scientific rigor, operability, and representativeness, and by using the Analytic Hierarchy Process (AHP) or the entropy weight method.

[0028] The indicator system framework includes: natural elements such as slope, valley morphology, rainfall intensity, and vegetation coverage; engineering elements such as silt traps, drainage channels, and slope protection projects; management elements such as monitoring and early warning system coverage, emergency response plan completeness, and community disaster prevention awareness; and social elements such as population density, economic resilience, and post-disaster recovery capacity.

[0029] The final list of core elements is shown in the table below:

[0030] S12. Calculate the contribution of each core element data in different dimensions to resilience and disaster reduction, and calculate the disaster reduction resilience by weighting the contribution and the corresponding weight value.

[0031] In this embodiment, based on the identified core element data, the contribution of each core element to debris flow resilience and mitigation is quantified from different dimensions such as natural, engineering, and social aspects. Then, according to the pre-determined weight values ​​of each core element, the contribution of each element is multiplied by its corresponding weight, and all products are summed to obtain a comprehensive disaster reduction resilience value. Dimensional calculation of contribution allows for a detailed analysis of the differences in the role of each element in disaster reduction under different dimensions, accurately identifying key influencing factors. The weighted average comprehensively considers the importance of each element, making the obtained disaster reduction resilience value more scientific and comprehensive, and objectively reflecting the overall resilience status of the regional debris flow prevention and control system.

[0032] In a specific embodiment, in addition to directly calculating the disaster mitigation resilience using a weighted average, disaster mitigation resilience can also be calculated using the following nonlinear formula, based on nonlinear coupling theory and system dynamics model, combined with the multi-dimensional interactive characteristics of disaster mitigation resilience: ; in, For disaster resilience, NT represents the score of the core element data corresponding to natural resilience; ET represents the score of the core element data corresponding to engineering resilience; ST represents the score of the core element data corresponding to social resilience. NT, ET, and ST represent the contribution of the corresponding core element data to resilience disaster reduction; w1, w2, and w3 are the corresponding weights (determined by SEM path coefficients or entropy weight method), and the sum of w1, w2, and w3 is 1; nonlinear coupling term. : This is the coupling correction factor (k is the coupling coefficient, a value of 0.5-1.2 is recommended). Geometric mean kernel This method replaces linear weighting and strengthens the multiplicative effect between dimensions. Standardization (such as Z-score) can also be used to ensure uniformity of dimensions.

[0033] Both of the above methods can calculate disaster resilience. Compared to the coarse calculation using weighted average, nonlinear enhancement is achieved through exponential weights and geometric averages to avoid the sensitivity of linear models to extreme values. A coupling degree correction factor quantifies the synergistic effect of natural, engineering, and social resilience, retaining the weights determined by the SEM / entropy weight method to ensure compatibility with existing assessment systems. The coupling coefficient k can be adjusted according to regional characteristics to adapt to different disaster scenarios. For rapid model building, weighted average calculation can be used to obtain disaster resilience. In scenarios requiring higher accuracy, nonlinear coupling of each contribution level and its corresponding weight value can be used to obtain disaster resilience.

[0034] S13. Based on the contribution, determine the first element data directly related to disaster reduction resilience and the second element data indirectly related to it in the core element data, and generate the third element data by linking the first element data in pairs.

[0035] In this embodiment, based on the calculated contribution of core element data to resilience and disaster reduction, the system distinguishes between first-element data that is directly and closely related to disaster reduction and resilience, and second-element data that is indirectly related, according to the magnitude of their contribution. Then, the first-element data are paired and combined to generate new third-element data. By distinguishing between directly and indirectly related elements, the core factors that play a crucial role in disaster reduction and resilience can be more clearly identified. Generating third-element data uncovers the potential connections between directly related elements, enriches the data dimensions, and helps to analyze the comprehensive impact of each element on disaster reduction and resilience more comprehensively and deeply.

[0036] S14. Construct a structural equation model. Train the structural equation model using the first element data, the second element data, the third element data, and disaster reduction resilience to generate a comprehensive prevention and control assessment model. Use the comprehensive prevention and control assessment model to conduct a comprehensive prevention and control assessment of the preset area.

[0037] In this embodiment, a structural equation model is established as the theoretical framework. The first, second, and third element data, along with disaster reduction resilience, acquired in the early stages, are used as input variables to train the model. By continuously adjusting the model parameters, the model is brought to its optimal fit, thereby generating a comprehensive assessment model for debris flow prevention and control. Finally, this model is used to conduct a comprehensive assessment of prevention and control in a predetermined area. The structural equation model can effectively integrate multi-source data, clarify the complex relationships between various elements, and the trained assessment model can comprehensively and accurately reflect the region's debris flow prevention and control capabilities. The assessment of the predetermined area can scientifically identify shortcomings in prevention and control, providing strong support for formulating reasonable and effective prevention and control measures and optimizing resource allocation.

[0038] In this embodiment, core element data of a preset area to be assessed is acquired; the core element data is processed using a comprehensive prevention and control assessment model to determine the disaster resilience of the preset area; the resilience level is determined based on the disaster resilience, and prevention and control recommendations are sent according to the processing method corresponding to the resilience level in a preset resilience level table. By acquiring the core element data of the preset area to be assessed, inputting it into the generated comprehensive prevention and control assessment model for processing, the disaster resilience value of the preset area is obtained. Based on the preset resilience level table, the resilience level corresponding to this value is determined. Finally, targeted prevention and control recommendations are sent to relevant departments according to the processing method corresponding to the level in the level table. This method can quickly and accurately assess the debris flow disaster resilience of a preset area, intuitively presenting the regional prevention and control capacity level by clearly defining the resilience level. The prevention and control recommendations sent based on the level are highly targeted and operable, helping to improve the regional debris flow prevention and control capacity in a timely and effective manner, and reducing disaster risks and losses.

[0039] DRI2 = w1 × NT + w2 × ET + w3 × ST; Wherein, DRI2 represents the disaster mitigation resilience to be assessed; NT: the score of the core element data corresponding to natural resilience; ET: the score of the core element data corresponding to engineering resilience; ST: the score of the core element data corresponding to social resilience; w1, w2, and w3 are the corresponding weights (determined by SEM path coefficients or entropy weight method).

[0040] In this embodiment, the resilience level is determined by the DRI value, and corresponding prevention and control suggestions are proposed. For example, 0.8-1.0 is high resilience, maintaining the status quo and optimizing monitoring and early warning; 0.5-0.8 is medium resilience, carrying out local reinforcement projects and improving community capabilities; less than 0.5 is low resilience, carrying out comprehensive upgrade engineering measures and conducting disaster prevention education.

[0041] In this embodiment, DRI2 can be calculated with reference to the above nonlinear formula.

[0042] In this embodiment, historical core element data is acquired, and the weight of each element is determined using the entropy method. The contribution of each element to resilience and disaster reduction under different dimensions is calculated, and a weighted average is used to obtain disaster reduction resilience. Based on the contribution, the first element data directly related to disaster reduction resilience and the second element data indirectly related are distinguished. The first element data are then correlated pairwise to generate third element data. Finally, a structural equation model is constructed, and a comprehensive prevention and control assessment model is generated using the above data and disaster reduction resilience for assessment of the preset area. The entropy method objectively allocates weights to avoid subjective bias; it comprehensively considers multi-dimensional elements and their correlations to accurately quantify disaster reduction resilience; the constructed model can systematically assess the prevention and control situation of the preset area, providing a scientific basis for debris flow prevention and control, and improving the rationality and effectiveness of prevention and control decisions.

[0043] Please see Figure 2 , Figure 2 This is the second part of a flowchart illustrating a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, as disclosed in this publication. Figure 2 As shown, the evaluation methods include: S21. Construct a structural equation model that includes the path mapping relationship between the first element data, the second element data, and the third element data and disaster reduction resilience, respectively.

[0044] In this embodiment, based on clearly defined first, second, and third element data, the inherent logical connections between these element data and disaster reduction resilience are explored in depth. The specific paths from each element data to disaster reduction resilience are identified, and a structural equation model incorporating these path mapping relationships is constructed to present the complex mechanism by which multiple elements affect disaster reduction resilience. This model can comprehensively and systematically reveal the correlation between each element and disaster reduction resilience, accurately quantify their degree of influence, and help to accurately identify key factors affecting disaster reduction resilience.

[0045] S22. Fit the structural equation model using the first element data, the second element data, the third element data, and disaster reduction resilience; and calculate the model fit of the fitted structural equation model.

[0046] In this embodiment, the determined data of the first, second, and third elements, along with the disaster reduction resilience values, are substituted into a pre-constructed structural equation model. Specific algorithms and statistical methods are used to continuously adjust the model parameters, making the model output as close as possible to the actual data, thus completing the model fitting process. Subsequently, a series of standard indicators, such as the chi-square degree of freedom ratio and the root mean square of the approximation error, are used to calculate the goodness of fit of the fitted model, thereby evaluating the degree of fit between the model and the actual data. Through the fitting operation, the structural equation model can better reflect the true relationship between multiple elements and disaster reduction resilience, improving the model's accuracy and reliability. Calculating the model fit can scientifically determine the model quality; if the fit is good, the model can be used for subsequent analysis and prediction.

[0047] In this embodiment, the model is assumed to include first element data X1, second element data X2, and third element data X3 as exogenous variables, and the disaster mitigation resilience value R as an endogenous variable. The model fit is calculated using the following core indicators: Calculate the chi-square value of the model: ; in, Here, N is the chi-square value, and N is the sample size. The minimum value of the maximum likelihood function reflects the degree of difference between the model's predicted covariance matrix and the sample covariance matrix; Calculate the degrees of freedom of the model: ; in, For the model's degrees of freedom, The number of exogenous variables is 3 in this scheme. The number of endogenous variables is 1 in this scheme. This refers to the number of parameters in the model, such as path coefficients and residual variance.

[0048] Approximate calculation of root mean square error: ; Wherein, RMSEA is the root mean square error approximation. An absolute measure of the degree of model misfit. This indicates standardization, eliminating the influence of sample size and degrees of freedom. RMSEA < 0.05 indicates an excellent fit, and 0.05-0.08 indicates a good fit.

[0049] Calculate the comparison fit index: ; CFI is the comparison fit index. The closer the CFI is to 1, the better the model fit (≥0.90 is excellent). It is the chi-square value of the baseline model. These are the degrees of freedom of the baseline model. The baseline model is a benchmark model used for comparative evaluation in structural equation modeling (SEM). Its core function is to quantify the degree of improvement of the theoretical model by comparing it with the theoretical model (i.e., the model you proposed that includes the first element, the second element, the third element, and disaster mitigation resilience).

[0050] In this embodiment, RMSEA and CFI are used to jointly determine the following: Excellent fit: RMSEA < 0.05 and CFI ≥ 0.90; Good fit: RMSEA < 0.08 and CFI ≥ 0.85; Needs correction: If the above criteria are not met, the model settings or data quality need to be checked.

[0051] S23. When the model fit meets the preset requirements, the trained comprehensive evaluation model for prevention and control is obtained.

[0052] S24. When the model fit does not meet the preset requirements, adjust the path coefficients of the path mapping relationship of the structural equation model and recalculate the model fit until the model fit meets the preset requirements, and obtain the trained comprehensive evaluation model for prevention and control.

[0053] In this embodiment, the trained comprehensive assessment model for epidemic prevention and control is trained. If the goodness of fit does not meet the preset standard, the path coefficients of the path mapping relationship between each element in the model and disaster reduction resilience are adjusted and optimized. Then, the model goodness of fit is recalculated. This adjustment and calculation process is continuously iterated until the model goodness of fit meets the preset requirements, and finally, a trained comprehensive assessment model for epidemic prevention and control is obtained. This scheme ensures that the generated comprehensive assessment model for epidemic prevention and control can accurately reflect the complex relationship between multiple elements and disaster reduction resilience by strictly controlling the model goodness of fit, thereby improving the accuracy and reliability of the model. The process of continuously adjusting the path coefficients optimizes the model structure, making the model more scientific and practical.

[0054] In this embodiment, a threshold can be set for the number of times the model parameters can be adjusted. When the number of adjustments reaches the threshold, the fitting process stops, and the data can be readjusted to refit the model. Alternatively, the model with the best fit during the fitting process can be used as the comprehensive evaluation model for prevention and control.

[0055] like Figure 3 As shown, this solution provides a method for verifying the quality of feature data, including the following steps: S31. Adjust the values ​​of the first element data, the second element data, or the third element data multiple times according to the preset value and determine the model fit after each adjustment through the trained comprehensive evaluation model for prevention and control.

[0056] In this embodiment, the values ​​of the first, second, or third element data are systematically adjusted multiple times according to pre-set numerical intervals. The complete set of element data after each adjustment is then input into a well-trained comprehensive prevention and control assessment model. The model's calculations yield the model fit value corresponding to each adjustment. This method allows for in-depth exploration of the impact of different element data value changes on model fit, accurately identifying the key elements and numerical ranges affecting model fit, and providing detailed and reliable data support for further model optimization and improved model evaluation accuracy.

[0057] S32. When the fluctuation range of the model fit is less than the preset fluctuation range, the data quality of the first element data, second element data or third element data of the adjusted values ​​is verified or removed, and the prevention and control comprehensive evaluation model is refitted.

[0058] In this embodiment, the fluctuation range of the model fit is used as the criterion. When it is less than a preset fluctuation range, it is determined that the first, second, and third element data corresponding to the adjusted values ​​may have problems. Therefore, quality verification is performed on these element data, identifying and removing poor-quality data. Then, the remaining high-quality data is used to refit the comprehensive prevention and control assessment model. This approach effectively ensures the quality of the model input data, avoiding model evaluation bias due to data problems. By removing poor data and refitting, the accuracy, stability, and reliability of the comprehensive prevention and control assessment model can be improved, making it more accurately reflect the actual situation.

[0059] Please see Figure 4 , Figure 4 This is the third part of a flowchart illustrating a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, as provided in this publication. Figure 4 As shown, the evaluation methods include: S41. Based on the PSR model algorithm, the core element data is divided into stress dimension, state dimension and response dimension.

[0060] In this embodiment, leveraging the mature framework of the PSR (Stress-State-Response) model algorithm, the acquired core element data is systematically sorted and categorized according to its inherent logic and classification criteria. Element data related to external stress sources are assigned to the stress dimension, element data reflecting the current actual situation are assigned to the state dimension, and element data regarding countermeasures taken in response to the current situation are assigned to the response dimension. This categorization method clearly presents the hierarchical structure and logical relationships among the core element data, making the complex data system more organized and facilitating in-depth analysis of problems from different dimensions. It enables a comprehensive and accurate understanding of the region's stress, current state, and response actions in relevant fields.

[0061] In this embodiment, Pressure refers to external shock factors (such as rainfall intensity and human activity intensity). Examples of indicators include: annual maximum rainfall and land use change rate. State refers to the current state of the system (such as terrain stability and vegetation cover). Examples of indicators include: slope variability and mean NDVI. Response refers to the system's coping capabilities (such as monitoring and early warning, and emergency response). Examples of indicators include: monitoring station density and emergency plan completeness score.

[0062] S42. Analyze the first influence trend of the pressure dimension data on the state dimension data, the second influence trend of the pressure dimension data on the response dimension data, and the third influence trend of the response dimension data on the state dimension data through core element data analysis.

[0063] In this embodiment, based on the core element data that has been divided into pressure, state, and response dimensions, statistical analysis and data modeling are used to explore the intrinsic relationship between pressure dimension data and state dimension data, and to identify the first influence trend of pressure dimension data on the state dimension. Simultaneously, the same analytical methods are used to explore the correlation between response dimension data and state dimension data, clarifying the second influence trend of the response dimension on the state dimension. This approach clearly presents the dynamic influence relationships between different dimensions, accurately identifies the key factors affecting the state dimension and their direction of influence, and contributes to a deeper understanding of the system's operating mechanism.

[0064] In this embodiment, time-series data of core element data are introduced to analyze how pressure affects the state (such as long-term rainfall leading to soil erosion) and how the response regulates the state (such as using a dam to reduce the risk of debris flow).

[0065] Example: Construct a structural equation model (SEM) to verify the path of "vegetation cover → reduced runoff → reduced erosion → improved resilience".

[0066] S43. Based on the first, second, and third impact trends, calculate the contribution of each core element data to resilience and disaster reduction.

[0067] In this embodiment, based on clarifying the first influence trend of the stress dimension on the state dimension and the second influence trend of the response dimension on the state dimension, the specific performance and action path of each core element data in the stress and response dimensions are comprehensively considered. Quantitative analysis methods such as mathematical modeling and weight allocation are used to calculate the magnitude of the effect of each core element data on resilience and disaster reduction under the first and second influence trends, thereby deriving the contribution of each core element data to resilience and disaster reduction. By accurately calculating the contribution of each core element data, key elements with significant impact on resilience and disaster reduction can be clearly identified.

[0068] In this embodiment, based on the SEM model, the total effect of each factor on system resilience (direct effect + indirect effect) is calculated. Example: Total effect of rainfall intensity = β1 (rainfall → natural resilience) × β2 (natural resilience → system resilience) + β3 (rainfall → system resilience), where β1 represents the impact of rainfall on natural resilience, β2 represents the impact of natural resilience on system resilience, and β3 represents the trend of rainfall's impact on system resilience. Local sensitivity analysis: While keeping other factors fixed, a single factor is varied (e.g., the density of silt-trapping dams changes from 0.1 dams / km²). 2 Increased to 0.5 seats / km 2 ), observe the rate of change of the total effect; calculate the contribution = (Δtotal effect / baseline value of total effect) × 100%, where Δtotal effect is the rate of change of the total effect, and the baseline value of the total effect is the total effect of the system resilience under the baseline data of each element.

[0069] In this embodiment, the explanatory power of each dimension on resilience can also be calculated by using a geographic detector or grey relational analysis (e.g., the stress dimension contributes 30% and the state dimension contributes 50%).

[0070] Specifically, the first influence trend is denoted as T1, which reflects the overall influence of the pressure dimension element on the state dimension element. The second influence trend is denoted as T2, which reflects the overall influence of the pressure dimension element on the response dimension element. The third influence trend is denoted as T3, which reflects the overall influence of the response dimension element on the state dimension element.

[0071] The contribution of each core element to resilience and disaster mitigation is calculated using the following formula: ; in, This represents the contribution of the i-th core element data to resilience and disaster reduction. This represents the weight of the contribution of the i-th core element data to the first influencing trend. This represents the contribution weight of the i-th core element data to the second influencing trend. This represents the contribution weight of the i-th core element data to the third influence trend. The contribution weight can be obtained through data analysis. It is the weight that first influences the trend. It is the second most influential factor in the trend. It is the weight of the third influencing trend, and ; It is a preset comprehensive adjustment coefficient used to adjust the scale and direction of the entire contribution calculation (this coefficient can be obtained through data fitting or expert judgment). It is the value of disaster mitigation resilience.

[0072] Please see Figure 5 , Figure 5 This is the fourth part of a flowchart illustrating a comprehensive assessment method for debris flow prevention and control based on resilience mitigation, as provided in this publication. Figure 5 As shown, the evaluation methods include: S51. Select multiple sets of disaster data from historical data, and determine the historical core element data and corresponding disaster data in each set of disaster data.

[0073] In this embodiment, existing historical data serves as the data source. Based on certain screening criteria, such as disaster type, time span, and impact range, multiple sets of representative and valuable disaster data are selected. For each selected set, data extraction and identification techniques are used to accurately determine the core historical data elements contained within, while also clarifying the corresponding disaster data itself (such as specific indicators like disaster intensity and damage level). By carefully selecting multiple sets of disaster data, a rich variety of disaster scenarios and situations can be covered, ensuring the comprehensiveness and diversity of the research sample. Accurately determining the core historical data elements and corresponding disaster data provides a solid and accurate data foundation for subsequent in-depth analysis of disaster formation mechanisms and the correlation between core elements and disasters, contributing to improved reliability and practicality of the research conclusions.

[0074] S52. By processing historical core element data through a comprehensive prevention and control assessment model, the predicted historical disaster reduction resilience is obtained.

[0075] In this embodiment, historical core element data identified from historical data is used as input and substituted into a pre-constructed comprehensive disaster prevention and control assessment model. Utilizing the model's pre-set algorithms, parameters, and operational logic, a series of complex processing and analysis operations are performed on this historical core element data, ultimately outputting predicted historical disaster resilience-related results. By processing historical core element data using the comprehensive disaster prevention and control assessment model, hidden disaster resilience information within historical data can be extracted, presenting the region's disaster resilience level under different past conditions in a quantitative form. This provides a basis for comparing and analyzing disaster reduction effects under different periods and conditions, and also helps verify the model's accuracy.

[0076] S53. Compare the predicted historical disaster resilience with disaster data to determine the relative deviation of the prediction, and calculate the comprehensive relative deviation of multiple sets of disaster data.

[0077] In this embodiment, the predicted historical disaster resilience obtained by processing historical core element data through the comprehensive disaster prevention and control assessment model is compared one by one with the corresponding historical disaster data (such as actual disaster losses, impact range, and other indicator data that can reflect the true disaster reduction situation). The relative deviation between the predicted value and the actual value under each set of disaster data is calculated. Then, using appropriate statistical methods, the relative deviations of multiple sets of disaster data are combined to calculate the comprehensive relative deviation. By comparing, the accuracy of the model's prediction can be intuitively understood, and determining the prediction relative deviation can accurately locate the differences between the model's prediction and the actual situation. Calculating the comprehensive relative deviation can comprehensively evaluate the model's predictive performance for multiple sets of disaster data.

[0078] S54. When the overall relative deviation is greater than the preset deviation, the comprehensive assessment model for prevention and control shall be corrected.

[0079] In this embodiment, a pre-set deviation value is used as a benchmark. The calculated relative deviation of multiple sets of disaster data is compared with this benchmark. If the overall relative deviation exceeds the preset deviation range, it is determined that the current comprehensive prevention and control assessment model has an inaccurate prediction problem. Then, based on the deviation situation, methods such as adjusting model parameters, optimizing algorithm structure, and supplementing key variables are used to correct and improve the comprehensive prevention and control assessment model. This solution can promptly detect the deviation between the model prediction and the actual situation. By correcting the model, its prediction accuracy and reliability can be improved, making the comprehensive prevention and control assessment model more in line with reality.

[0080] Please see Figure 6 , Figure 6 This disclosure provides a comprehensive assessment system for debris flow prevention and control based on resilience disaster reduction. The assessment system includes: a data processing module 11, a disaster reduction resilience determination module 12, a data classification module 13, an assessment model construction module 14, and a comprehensive assessment module 15.

[0081] In this embodiment, the data processing module 11 is used to acquire core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data.

[0082] In this embodiment, the disaster resilience determination module 12 is used to calculate the contribution of each core element data in different dimensions to resilience disaster reduction, and to obtain disaster resilience by weighted averaging of each contribution and its corresponding weight value.

[0083] In this embodiment, the data classification module 13 is used to determine the first element data directly related to disaster reduction resilience and the second element data indirectly related to it in the core element data according to the contribution, and to generate the third element data by associating the first element data in pairs.

[0084] In this embodiment, the evaluation model construction module 14 is used to construct a structural equation model and train the structural equation model using the first element data, the second element data, the third element data, and disaster reduction resilience to generate a comprehensive prevention and control evaluation model. In this embodiment, the comprehensive evaluation module 15 is used to conduct a comprehensive evaluation of the prevention and control of a preset area through a comprehensive prevention and control evaluation model.

[0085] In this embodiment, the evaluation model construction module 14 is specifically used to construct a structural equation model that includes path mapping relationships between first element data, second element data, and third element data and disaster reduction resilience, respectively; fit the structural equation model using the first element data, second element data, third element data, and disaster reduction resilience; and calculate the model fit of the fitted structural equation model; when the model fit meets the preset requirements, a trained comprehensive prevention and control evaluation model is obtained; when the model fit does not meet the preset requirements, the path coefficients of the path mapping relationships of the structural equation model are adjusted, and the model fit is recalculated until the model fit meets the preset requirements, thus obtaining a trained comprehensive prevention and control evaluation model.

[0086] In this embodiment, the evaluation model construction module 14 is specifically used to adjust the values ​​of the first element data, the second element data, or the third element data multiple times according to the preset value adjustment interval, and determine the model fit after each adjustment through the trained comprehensive evaluation model for prevention and control; when the fluctuation range of the model fit is less than the preset fluctuation range, the data quality of the first element data, the second element data, or the third element data of the adjusted values ​​is verified or removed, and the comprehensive evaluation model for prevention and control is refitted.

[0087] In this embodiment, the data processing module 11 is specifically used to acquire multi-source raw data from historical data, including geological data, topographic data, meteorological data, engineering measures data, and historical disaster data; based on the grey relational analysis method, analyze and calculate the correlation between the multi-source raw data and debris flow disasters; use the multi-source raw data whose correlation meets the preset correlation requirements as disaster reduction correlation data; perform standardization processing on continuous disaster reduction correlation data to generate first correlation data; perform one-hot encoding on the categorized disaster reduction correlation data to generate second correlation data; and synthesize third correlation data by weighted summation of each disaster reduction correlation data; and use the first correlation data, second correlation data, and third correlation data as core element data.

[0088] In this embodiment, the disaster resilience determination module 12 is specifically used to divide the core element data into a stress dimension, a state dimension, and a response dimension based on the PSR model algorithm; analyze the first influence trend of the stress dimension data on the state dimension data, the second influence trend of the stress dimension data on the response dimension data, and the third influence trend of the response dimension data on the state dimension data through the core element data; and calculate the contribution of each core element data to the resilience disaster reduction based on the first influence trend, the second influence trend, and the third influence trend.

[0089] In this embodiment, the assessment model construction module 14 is specifically used to select multiple sets of disaster data from historical data, and determine the historical core element data and corresponding disaster data in each set of disaster data; process the historical core element data through the prevention and control comprehensive assessment model to obtain the predicted historical disaster reduction resilience; compare the predicted historical disaster reduction resilience with the disaster data to determine the prediction relative deviation, and calculate the comprehensive relative deviation of multiple sets of disaster data; when the comprehensive relative deviation is greater than the preset deviation, the prevention and control comprehensive assessment model is corrected.

[0090] In this embodiment, the comprehensive assessment module 15 is specifically used to acquire the core element data to be assessed in the preset area; process the core element data to be assessed through the comprehensive assessment model for prevention and control to determine the disaster reduction resilience of the preset area; determine the resilience level through the disaster reduction resilience to be assessed, and send prevention and control suggestions according to the processing method corresponding to the resilience level in the preset resilience level table.

[0091] like Figure 7 As shown, this embodiment of the present disclosure provides an electronic device, including a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140. Memory 1130 is used to store computer programs; When the processor 1110 executes the program stored in the memory 1130, it implements any of the above methods.

[0092] The electronic device provided in this embodiment of the present disclosure includes a processor 1110 that executes a program stored in a memory 1130 to obtain core element data related to debris flow resilience and disaster reduction from historical data, determines corresponding weight values ​​based on the entropy values ​​of each core element data, calculates the contribution of each core element data to resilience and disaster reduction in different dimensions, and calculates a weighted average of each contribution and its corresponding weight value to obtain disaster reduction resilience. Based on the contribution, it determines the first element data directly related to disaster reduction resilience and the second element data indirectly related to it from the core element data, and generates third element data by pairwise association of the first element data. It constructs a structural equation model, trains the structural equation model using the first element data, the second element data, the third element data, and disaster reduction resilience to generate a comprehensive prevention and control assessment model, and conducts a comprehensive prevention and control assessment of a preset area using the comprehensive prevention and control assessment model.

[0093] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, and a component bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus.

[0094] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0095] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0096] The processor 1110 mentioned above can be a general-purpose processor 1110, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0097] This disclosure provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors 1110 to implement the methods of any of the above embodiments.

[0098] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this disclosure is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0099] Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A comprehensive assessment method for debris flow prevention and control based on resilience mitigation, characterized in that, The evaluation method includes: Obtain core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data. The contribution of each core element data under different dimensions to the resilience and disaster reduction is calculated, and the disaster reduction resilience is obtained by weighted averaging of each contribution and its corresponding weight value. Based on the contribution, determine the first element data that is directly related to the disaster reduction resilience and the second element data that is indirectly related to the core element data, and then associate the first element data in pairs to generate the third element data. A structural equation model is constructed, and a comprehensive prevention and control assessment model is generated by training the structural equation model with the first element data, the second element data, the third element data, and the disaster reduction resilience. The comprehensive prevention and control assessment model is then used to conduct a comprehensive prevention and control assessment of the preset area.

2. The evaluation method according to claim 1, characterized in that, The construction of the structural equation model involves training the structural equation model using the first element data, the second element data, and the third element data to generate a comprehensive prevention and control assessment model, including: Construct a structural equation model that includes the path mapping relationships between the first element data, the second element data, and the third element data and the disaster reduction resilience, respectively; The structural equation model is fitted using the first element data, the second element data, the third element data, and the disaster mitigation resilience; and the model fit of the fitted structural equation model is calculated. When the model fit meets the preset requirements, the trained comprehensive evaluation model for prevention and control is obtained; When the model fit does not meet the preset requirements, the path coefficients of the path mapping relationship of the structural equation model are adjusted, and the model fit is recalculated until the model fit meets the preset requirements, thus obtaining the trained comprehensive evaluation model for prevention and control.

3. The evaluation method according to claim 2, characterized in that, The evaluation method also includes: Adjust the values ​​of the first element data, the second element data, or the third element data multiple times according to the preset value interval, and determine the model fit after each value adjustment through the trained comprehensive prevention and control evaluation model. When the fluctuation range of the model fit is less than the preset fluctuation range, the data quality of the first element data, second element data, or third element data of the adjusted values ​​is verified or removed, and the prevention and control comprehensive evaluation model is refitted.

4. The evaluation method according to claim 1, characterized in that, The core data elements related to debris flow resilience and disaster reduction obtained from historical data include: Obtain multi-source raw data from historical data, including geological data, topographic data, meteorological data, engineering measures data, and historical disaster data; Based on the grey relational analysis method, the correlation between multi-source raw data and debris flow disasters is analyzed and calculated; Multi-source raw data whose correlation degree meets the preset correlation degree requirements are used as disaster reduction correlation data; The continuous disaster reduction correlation data is standardized to generate the first correlation data; One-hot encoding is performed on the categorized disaster mitigation correlation data to generate second correlation data; Then, the various disaster reduction-related data are combined into a third related data through weighted summation; The first associated data, the second associated data, and the third associated data are used as the core element data.

5. The evaluation method according to claim 1, characterized in that, The calculation of the contribution of each of the core element data in different dimensions to the resilience and disaster reduction includes: Based on the PSR model algorithm, the core element data is divided into stress dimension, state dimension and response dimension; The analysis of core element data reveals the first influence trend of the stress dimension data on the state dimension data, the second influence trend of the stress dimension data on the response dimension data, and the third influence trend of the response dimension data on the state dimension data. Based on the first influence trend, the second influence trend, and the third influence trend, the contribution of each core element data to the resilience and disaster reduction is calculated.

6. The evaluation method according to claim 1, characterized in that, The evaluation method also includes: Multiple sets of disaster data are selected from the historical data, and the historical core element data and corresponding disaster data in each set of disaster data are determined. By processing the historical core element data through the aforementioned comprehensive prevention and control assessment model, the predicted historical disaster reduction resilience is obtained. The predicted historical disaster resilience is compared with the disaster data to determine the relative deviation of the prediction, and the comprehensive relative deviation of multiple sets of disaster data is calculated. When the overall relative deviation is greater than the preset deviation, the overall prevention and control assessment model is corrected.

7. The evaluation method according to any one of claims 1 to 6, characterized in that, The step of conducting a comprehensive prevention and control assessment of the preset area using the comprehensive prevention and control assessment model includes: Obtain data on the core elements to be evaluated in the preset area; The data of the core elements to be evaluated are processed by the comprehensive prevention and control assessment model to determine the disaster reduction resilience of the preset area to be evaluated. The resilience level is determined by assessing the disaster reduction resilience, and prevention and control recommendations are sent according to the handling methods corresponding to the resilience level in the preset resilience level table.

8. A comprehensive assessment system for debris flow prevention and control based on resilience mitigation, characterized in that, The evaluation system includes: The data processing module is used to acquire core element data related to debris flow resilience and disaster reduction from historical data, and determine the corresponding weight value based on the entropy value of each core element data. The disaster resilience determination module is used to calculate the contribution of each core element data under different dimensions to the resilience disaster reduction, and to obtain the disaster resilience by weighted averaging of each contribution and its corresponding weight value. The data classification module is used to determine, based on the contribution, the first element data directly related to the disaster reduction resilience and the second element data indirectly related to the core element data, and to generate the third element data by associating the first element data in pairs. The assessment model construction module is used to construct a structural equation model, and to train the structural equation model using the first element data, the second element data, the third element data, and the disaster reduction resilience to generate a comprehensive prevention and control assessment model. The comprehensive assessment module is used to conduct a comprehensive assessment of the prevention and control of a preset area using the comprehensive prevention and control assessment model.

9. An electronic device, characterized in that, include: processor; as well as A memory storing computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1-7.

10. A computer storage medium, characterized in that, in, The computer storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-7.

Images