Natural disaster landslide early warning risk assessment method and system based on model workflow

Abstract

The invention provides a model workflow-based natural disaster landslide early warning risk assessment method and system. The method comprises the following steps: sorting index factors and algorithm models according to different scales; constructing a tool set and issuing the tool set; according to risk assessment requirements, calling the index factor tool set and the model tool set, and constructing a natural disaster landslide early warning risk assessment workflow; calling the natural disaster landslide early warning risk assessment workflow to carry out risk assessment to obtain a model result data set; and based on the model result data set, in combination with different matching colors corresponding to different risk values, issuing wms map service. According to the invention, different landslide disaster models can be flexibly constructed, and the protection work of natural disaster landslide can be well done.

Description

Technical Field

[0001] The present invention belongs to the technical field of natural disaster risk assessment, and in particular relates to a natural disaster landslide early warning risk assessment method and system based on a model workflow. Background Art

[0002] Landslides are a common geological disaster, characterized by suddenness, destructive power, and wide-ranging impacts. In recent years, landslide disasters have become frequent, causing significant casualties and property losses. Current research on landslide assessment models remains limited to the study of hazard factors and model algorithms. Early information systems were primarily based on client-server architectures and GIS component technology, resulting in the following shortcomings: 1. File-based storage is often used for data storage; 2. The model has insufficient flexibility in constructing different models for disaster-causing factors; 3. The system is mostly built for the assessment of a certain type of natural disaster model and lacks universality; 4. Model evaluation requires frequent manual intervention and lacks automation; 5. The technology is relatively backward and the maintenance cost is high. Summary of the Invention

[0003] The present invention proposes a natural disaster landslide early warning risk assessment method and system based on model workflow, which can flexibly construct different landslide disaster models and better carry out natural disaster landslide protection work.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows: A natural disaster landslide early warning risk assessment method based on model workflow includes: S1. Sorting out the indicator factors involved in the algorithm for the hazard of hazard factors, sensitivity of the disaster-prone environment, vulnerability of the landslide itself, and comprehensive landslide risk at different scales; based on the different types of indicator factor data, storing them in PostGIS according to naming rules, and accessing real-time data through API; S2. Sorting out the hazards of hazard factors, sensitivity of disaster-prone environments, vulnerability of landslide entities, and algorithmic models for comprehensive landslide risk according to different scales; S3. Build and publish a tool set, which includes an indicator factor tool set and a model tool set; the indicator factor tool set is a data preprocessing tool set for the indicator factors, and the model tool set is a tool set for algorithmic models of the hazard of hazard factors, sensitivity of the disaster-prone environment, vulnerability of the landslide itself, and comprehensive landslide risk; S4. According to the risk assessment requirements, call the indicator factor toolset and model toolset, and construct a natural disaster landslide early warning risk assessment workflow in the order that the indicator factor toolset outputs to three model toolsets, including the hazard factor hazard model toolset, the disaster-prone environment sensitivity model toolset, and the landslide vulnerability model toolset, and the three model toolsets output to the landslide comprehensive risk model toolset; S5, calling the natural disaster landslide early warning risk assessment workflow to perform risk assessment and obtain a model result data set; S6. Based on the model result dataset, combined with different color schemes corresponding to different risk values, it is published as a wms map service.

[0005] Furthermore, in step S1, the indicator factors include: Disaster factors: indicators of the risk of disasters, including rainfall, earthquake intensity, geological conditions, slope, and slope direction; Disaster-prone factors: indicators of disaster-prone environmental sensitivity, including geological structure, groundwater level changes, and vegetation coverage; Ontological vulnerability factor: an indicator factor of landslide ontological vulnerability, including building density, population density, and infrastructure distribution; Comprehensive landslide risk: The comprehensive landslide risk is obtained by conducting a comprehensive assessment based on the hazard of hazard factors, the sensitivity of the disaster-prone environment and the vulnerability of the landslide itself.

[0006] Furthermore, in step S2, the algorithm model includes: Hazard factor risk model: Based on the hazard factors, the random forest or support vector machine algorithm is used for evaluation; Disaster-prone environmental sensitivity model: Based on disaster-prone factors, the model uses logistic regression or Bayesian network algorithms for evaluation; Landslide vulnerability model: Based on the vulnerability factors of building density and population density, the model is evaluated using multi-criteria decision analysis, comprehensive index method, or fuzzy matter-element evaluation method. Comprehensive landslide risk model: Combined with the hazard factor hazard model, the disaster-prone environment sensitivity model and the landslide vulnerability model, a comprehensive assessment is conducted using the weighted superposition method or the hierarchical analysis method.

[0007] Furthermore, the tool set construction method in step S3 includes: Set the tool base class as the abstract base class, provide internationalization support through i18nFunction(), and define a unified interface Execute(), requiring the tool implementation class as a subclass to implement the core logic; set the tool implementation class to inherit from the tool base class, override the Execute() method to operate the vector dataset class DatasetVector to implement calculations; set the factory base class to dynamically bind the relationship between the tool implementation class and the base class through the SPI registration mechanism. The factory base class instantiates the tool implementation class according to the registration information and calls its Execute() method to execute the task, while the tool base class provides public logic.

[0008] On the other hand, the present invention also proposes a natural disaster landslide early warning risk assessment system based on a model workflow, comprising: Factor module: This module sorts out the indicator factors involved in the algorithm of disaster-causing factor hazard, disaster-pregnant environmental sensitivity, landslide vulnerability, and comprehensive landslide risk at different scales. Based on the different types of indicator factor data, the module is stored in PostGIS according to naming rules, and real-time data is accessed through the API. Model module: sort out the hazard of disaster-causing factors, sensitivity of disaster-prone environments, vulnerability of landslides, and algorithmic models of comprehensive landslide risks according to different scales; Toolset module: Build and publish a toolset, which includes an indicator factor toolset and a model toolset. The indicator factor toolset is a data preprocessing toolset for the indicator factors, and the model toolset is a toolset for algorithmic models of hazard factors, sensitivity of the disaster-prone environment, vulnerability of the landslide itself, and comprehensive landslide risk. Workflow module: According to the risk assessment requirements, the indicator factor toolset and model toolset are called. The indicator factor toolset is output to three model toolsets, including the hazard factor hazard model toolset, the disaster-prone environment sensitivity model toolset, and the landslide vulnerability model toolset. The three model toolsets are then output to the landslide comprehensive risk model toolset in this order to construct a natural disaster landslide early warning risk assessment workflow. Calling module: calling the natural disaster landslide early warning risk assessment workflow to perform risk assessment and obtain a model result data set; Service publishing module: Based on the model result dataset, combined with different color schemes corresponding to different risk values, it is published as a wms map service.

[0009] Furthermore, in the factor module, the indicator factors include: Disaster factors: indicators of the risk of disasters, including rainfall, earthquake intensity, geological conditions, slope, and slope direction; Disaster-prone factors: indicators of disaster-prone environmental sensitivity, including geological structure, groundwater level changes, and vegetation coverage; Ontological vulnerability factor: an indicator factor of landslide ontological vulnerability, including building density, population density, and infrastructure distribution; Comprehensive landslide risk: The comprehensive landslide risk is obtained by conducting a comprehensive assessment based on the hazard of hazard factors, the sensitivity of the disaster-prone environment and the vulnerability of the landslide itself.

[0010] Furthermore, in the model module, the algorithm model includes: Hazard factor risk model: Based on the hazard factors, the random forest or support vector machine algorithm is used for evaluation; Disaster-prone environmental sensitivity model: Based on disaster-prone factors, the model uses logistic regression or Bayesian network algorithms for evaluation; Landslide vulnerability model: Based on the vulnerability factors of building density and population density, the model is evaluated using multi-criteria decision analysis, comprehensive index method, or fuzzy matter-element evaluation method. Comprehensive landslide risk model: Combined with the hazard factor hazard model, the disaster-prone environment sensitivity model and the landslide vulnerability model, a comprehensive assessment is conducted using the weighted superposition method or the hierarchical analysis method.

[0011] Furthermore, in the toolset module, building a toolset includes setting the tool base class as the abstract base class, providing internationalization support through i18nFunction(), and defining a unified interface Execute(), requiring the tool implementation class as a subclass to implement the core logic; setting the tool implementation class to inherit from the tool base class, overriding the Execute() method to operate the vector dataset class DatasetVector to implement calculations; setting the factory base class to dynamically bind the relationship between the tool implementation class and the base class through the SPI registration mechanism. The factory base class instantiates the tool implementation class according to the registration information and calls its Execute() method to execute the task, while the tool base class provides public logic.

[0012] Compared with the existing technology, the natural disaster landslide early warning risk assessment method and system proposed in the present invention based on model workflow has the following beneficial effects: 1. Improve assessment accuracy: Through real-time access to meteorological and geological data, the accuracy and effectiveness of landslide risk assessment are improved; 2. Enhanced system flexibility: Users can customize the parameters involved in the calculation and flexibly build different landslide disaster models to adapt to different application scenarios; 3. Reduce maintenance costs: Based on the SuperMap iDesktopX extended development API interface, the system architecture is simple and the maintenance cost is low; 4. Improve early warning capabilities: The system automatically monitors data changes and updates risk assessment results in real time, providing strong support for landslide disaster early warning and effectively protecting people’s lives and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of a flow chart of an embodiment of the present invention; Figure 2 This is a schematic diagram of the data flow of a toolset according to an embodiment of the present invention; Figure 3 It is a UML diagram for constructing a PGA indicator factor tool set according to an embodiment of the present invention; Figure 4 It is a schematic diagram of the model workflow construction process of an embodiment of the present invention. DETAILED DESCRIPTION

[0014] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0015] In order to make the purpose and features of the present invention more obvious and easy to understand, the present invention is further described below with reference to the accompanying drawings and specific embodiments.

[0016] This embodiment is based on the SuperMap GIS platform framework and uses iDesktopXJava as the API interface to build a landslide disaster risk assessment model workflow covering different scales. SuperMap iserver publishes the model workflow service; the browser calls the published model service, automatically calculates the risk value, and automatically publishes the risk map service with different color symbols according to different risk values.

[0017] The method proposed in this embodiment is as follows Figure 1 Shown, including: Step 1: Sort out the data and indicator factors involved in the algorithm of disaster-causing factor hazard, disaster-prone environmental sensitivity, landslide vulnerability, and landslide comprehensive model risk according to different scales; the different scales mainly refer to different administrative spatial scales, such as the data and indicator factors of landslide points in all spatial locations within the province, district, county, and township areas.

[0018] Based on the different types of data, PostGIS uses certain naming rules for storage. In one embodiment, the naming rule is as follows: dataset abbreviation (such as PGA for earthquake intensity) + year, month, day, hour, minute, second + administrative division code. The naming rules for indicator factors and models are the same.

[0019] Real-time data is accessed through an API to ensure real-time and accuracy. For example, meteorological data, which primarily includes rainfall, wind speed, and temperature, is sourced from an API provided by the National Meteorological Science Data Center.

[0020] Disaster factors: indicators of the risk of disasters, including rainfall, earthquake intensity, geological conditions, slope, and slope direction; Disaster-prone factors: indicators of disaster-prone environmental sensitivity, including geological structure, groundwater level changes, and vegetation coverage; Ontological vulnerability factor: an indicator factor of landslide ontological vulnerability, including building density, population density, and infrastructure distribution; Comprehensive landslide risk results: Combined with the hazard model results of hazard factors, the sensitivity results of the disaster-prone environment and the vulnerability results of the landslide itself, the comprehensive landslide risk is obtained by comprehensive assessment using the hazard model results of hazard factors, the sensitivity results of the disaster-prone environment and the vulnerability results of the landslide itself as factors.

[0021] Step 2: Sort out the hazards of hazard factors, sensitivity of the disaster-prone environment, vulnerability of landslides, and algorithms for comprehensive landslide risk models at different scales; Disaster risk factor model: Based on disaster factors such as rainfall and earthquake intensity, machine learning algorithms such as random forest and support vector machine are used for evaluation.

[0022] Disaster-prone environmental sensitivity model: Based on disaster-prone factors such as geological structure and groundwater level changes, algorithms such as logistic regression and Bayesian networks are used for evaluation.

[0023] Landslide vulnerability model: Based on factors such as building density and population density, multi-criteria decision analysis (MCDA) and other methods are used for assessment.

[0024] Comprehensive landslide risk model: combining the disaster-causing model, disaster-pregnancy model and ontological vulnerability model, using weighted superposition method, analytic hierarchy process (AHP) and other methods for comprehensive assessment.

[0025] Step 3: Based on the desktop GIS software SuperMap iDesktopX extension development, construct tool sets according to the different indicator factors, disaster factor hazard model, disaster-prone environment sensitivity model, landslide vulnerability model, and landslide comprehensive risk model sorted out above, and set up a "toolbox". The constructed tool sets are placed in the toolbox according to the directory for management.

[0026] Each indicator factor / model tool set must meet data input and data output requirements, such as Figure 2The data flow diagram of the toolset shown in the figure shows that each toolset is configured based on the functionality it aims to achieve. The indicator factor toolset inputs the raw data corresponding to the indicator factor, encapsulates the preprocessing algorithm logic for this raw data, and outputs the preprocessed data results based on the output of the algorithm logic. Taking the PGA (seismic intensity) indicator factor toolset as an example, the input is the raw data acquired for PGA. This raw data is fed into the PGA indicator factor toolset and then passes through the encapsulated preprocessing algorithm logic for PGA data (which may include detrending and demeaning, filtering, resampling, Fourier transform, vector conversion, and other preprocessing algorithm logic). The application of these preprocessing algorithms yields preprocessed PGA data, which effectively improves the quality of PGA data and converts data unsuitable for model analysis into vectors, facilitating the accuracy of the next step of model analysis.

[0027] The input of the model toolset is the output of multiple indicator factor toolsets. The model toolset encapsulates the model algorithm logic for this model toolset, and the output is the model analysis results based on the output of the model algorithm logic. Figure 4 Taking the disaster-prone environmental sensitivity model toolset as an example, the input data includes the output results of the landform type indicator factor toolset, the output results of the vegetation coverage indicator factor, and the output results of other related indicator factor toolsets (such as groundwater level changes). The disaster-prone environmental sensitivity model algorithm logic encapsulated in it (optional logistic regression, Bayesian network, etc.) is used for classification and probability prediction to output disaster probability data.

[0028] The process of building a toolset is as follows Figure 3 As shown, Figure 3 Taking the PGA indicator factor toolset as an example, the construction process includes: BaseProcess (the tool base class) is set as the abstract base class, providing internationalization support through i18nFunction() and defining unified interfaces (such as Execute()). Subclasses (tool implementation classes) are required to implement core logic. PGAProcessFactor (the tool implementation class) is set to inherit from BaseProcess, overriding the Execute() method to operate on the vector dataset class DatasetVector to implement the preprocessing calculation of specific PGA indicator factors. The PGAFactory (the factory base class) dynamically binds the tool implementation class to the base class through the SPI registration mechanism. AbstractAnnotatedProcessFactory and its annotations (such as AnnotatedProcessBean) are used to manage PGA indicator factor tool set metadata, achieving decoupling and object creation. The specific process is as follows: the factory base class instantiates PGAProcessFactor based on the registration information and calls its Execute() method to execute the task. The tool base class BaseProcess provides common logic (such as input validation). This design, through SPI extensions and the factory pattern, enables efficient registration, flexible expansion, and unified call of processing tools.

[0029] The construction process of the model toolset is the same as that of the indicator factor toolset above and will not be repeated here.

[0030] After completing the construction of the indicator factor toolset and the model toolset, publish all the toolsets as jar packages and place them in the lib path of SuperMap iDesktopX. Restart SuperMap iDesktopX to display the developed toolsets in the toolbox.

[0031] Step 4: Based on the indicator and model toolsets constructed in Step 3, in the processing automation module of the desktop GIS software SuperMap iDesktopX, drag the corresponding indicator and model toolsets into the current window according to the desired model results. A workflow is constructed, with the indicator toolsets outputting to the three model toolsets (hazard factor hazard model toolset, hazard-prone environmental sensitivity model toolset, and landslide vulnerability model toolset), and then the three model toolsets outputting to the comprehensive landslide risk model toolset. After completion, run the model in SuperMap iDesktopX to test the feasibility of the model and verify the accuracy of the results. If all steps are correct, enter the SuperMap iServer connection information on the SuperMap iDesktopX publishing page and click Publish to publish the model as a RestFul protocol service. Compared to previous technologies, model calculations were typically performed manually and distributed, and the final results were then calculated, without publishing the model as a service for invocation. This model workflow and publishing it as a callable service will significantly shorten model execution time, reduce manual intervention, and facilitate invocation of the model service on other platforms. The model workflow construction process is shown in Figure 4 It can be seen that administrative divisions are used as an input for each indicator factor tool set, which means that different administrative divisions have different scales, and indicator factor data of the corresponding scale needs to be selected for input.

[0032] Step 5: The model service published in Step 4 is called from the web system frontend to generate a model dataset in the database. Previously, when calling a model service, the entire process from inputting the model's raw data to outputting the model results was completed in one step, focusing on the model's results data without storing or recording the process data. However, during this model service call, process data, including indicator factors, models, and other process datasets, are also generated in the database during the model generation process, allowing for later analysis and traceability of the model results.

[0033] Step 6: Combine different color schemes corresponding to different risk values and publish them as a WMS map service.

[0034] Based on the model result dataset generated in Step 5, a column of attribute values represents the risk value of the current model at the current administrative scale (province, district, county, township). Based on different risk values (7-10 for red, 4-7 for yellow, 6-3 for blue, and 0-3 for transparent), representing high risk, medium risk, low risk, and no risk, respectively, an SLD style file is generated in QGIS for GeoServer to publish WMS services. Add the GeoServer-Manager development dependency to the Java backend program, configure the workspace, database connection information, and the generated SLD file, and automatically publish it as a WMS service. Compared to previous technologies, this method uses different styles to more intuitively display risk levels. It is also automatically published as a WMS service, eliminating the tedious manual publishing process and allowing for sharing as a service.

[0035] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A natural disaster landslide early warning risk assessment method based on model workflow, characterized in that: include: S1. Sorting out the indicator factors involved in the algorithm of hazard factor hazard, hazard-prone environmental sensitivity, landslide vulnerability, and comprehensive landslide risk at different scales; Considering the different types of indicator factor data, they are stored in PostGIS according to naming rules, and real-time data is accessed through API. S2. Sorting out the hazards of hazard factors, sensitivity of disaster-prone environments, vulnerability of landslide entities, and algorithmic models for comprehensive landslide risk according to different scales; S3. Build and publish a tool set, which includes an indicator factor tool set and a model tool set; the indicator factor tool set is a data preprocessing tool set for the indicator factors, and the model tool set is a tool set for algorithmic models of the hazard of hazard factors, sensitivity of the disaster-prone environment, vulnerability of the landslide itself, and comprehensive landslide risk; S4. According to the risk assessment requirements, call the indicator factor toolset and model toolset, and construct a natural disaster landslide early warning risk assessment workflow in the order that the indicator factor toolset outputs to three model toolsets, including the hazard factor hazard model toolset, the disaster-prone environment sensitivity model toolset, and the landslide vulnerability model toolset, and the three model toolsets output to the landslide comprehensive risk model toolset; S5, calling the natural disaster landslide early warning risk assessment workflow to perform risk assessment and obtain a model result data set; S6. Based on the model result dataset, combined with different color schemes corresponding to different risk values, it is published as a wms map service.

2. The natural disaster landslide early warning risk assessment method based on model workflow according to claim 1 is characterized in that: In step S1, the index factors include: Disaster factors: indicators of the risk of disasters, including rainfall, earthquake intensity, geological conditions, slope, and slope direction; Disaster-prone factors: indicators of disaster-prone environmental sensitivity, including geological structure, groundwater level changes, and vegetation coverage; Ontological vulnerability factor: an indicator factor of landslide ontological vulnerability, including building density, population density, and infrastructure distribution; Comprehensive landslide risk: The comprehensive landslide risk is obtained by conducting a comprehensive assessment based on the hazard of hazard factors, the sensitivity of the disaster-prone environment and the vulnerability of the landslide itself.

3. The natural disaster landslide early warning risk assessment method based on model workflow according to claim 1 is characterized in that: In step S2, the algorithm model includes: Hazard factor risk model: Based on the hazard factors, the random forest or support vector machine algorithm is used for evaluation; Disaster-prone environmental sensitivity model: Based on disaster-prone factors, the model uses logistic regression or Bayesian network algorithms for evaluation; Landslide vulnerability model: Based on the vulnerability factors of building density and population density, the model is evaluated using multi-criteria decision analysis, comprehensive index method, or fuzzy matter-element evaluation method. Comprehensive landslide risk model: Combined with the hazard factor hazard model, the disaster-prone environment sensitivity model and the landslide vulnerability model, a comprehensive assessment is conducted using the weighted superposition method or the hierarchical analysis method.

4. The natural disaster landslide early warning risk assessment method based on model workflow according to claim 1 is characterized in that: The toolset construction method in step S3 includes: Set the tool base class as the abstract base class, provide internationalization support through i18nFunction(), and define a unified interface Execute(), requiring the tool implementation class as a subclass to implement the core logic; set the tool implementation class to inherit from the tool base class, override the Execute() method to operate the vector dataset class DatasetVector to implement calculations; set the factory base class to dynamically bind the relationship between the tool implementation class and the base class through the SPI registration mechanism. The factory base class instantiates the tool implementation class according to the registration information and calls its Execute() method to execute the task, while the tool base class provides public logic.

5. A natural disaster landslide early warning risk assessment system based on model workflow, characterized in that: include: Factor module: This module sorts out the indicator factors involved in the algorithm of disaster-causing factor hazard, disaster-pregnant environmental sensitivity, landslide vulnerability, and comprehensive landslide risk at different scales. Based on the different types of indicator factor data, the module is stored in PostGIS according to naming rules, and real-time data is accessed through the API. Model module: sort out the hazard of disaster-causing factors, sensitivity of disaster-prone environments, vulnerability of landslide entities, and algorithmic models of comprehensive landslide risk according to different scales; Toolset module: Build and publish a toolset, which includes an indicator factor toolset and a model toolset. The indicator factor toolset is a data preprocessing toolset for the indicator factors, and the model toolset is a toolset for algorithmic models of hazard factors, sensitivity of the disaster-prone environment, vulnerability of the landslide itself, and comprehensive landslide risk. Workflow module: According to the risk assessment requirements, the indicator factor toolset and model toolset are called. The indicator factor toolset is output to three model toolsets, including the hazard factor hazard model toolset, the disaster-prone environment sensitivity model toolset, and the landslide vulnerability model toolset. The three model toolsets are then output to the landslide comprehensive risk model toolset in this order to construct a natural disaster landslide early warning risk assessment workflow. Calling module: calling the natural disaster landslide early warning risk assessment workflow to perform risk assessment and obtain a model result data set; Service publishing module: Based on the model result dataset, combined with different color schemes corresponding to different risk values, it is published as a wms map service.

6. The natural disaster landslide early warning risk assessment system based on model workflow according to claim 5 is characterized in that: In the factor module, the indicator factors include: Disaster factors: indicators of the risk of disasters, including rainfall, earthquake intensity, geological conditions, slope, and slope direction; Disaster-prone factors: indicators of disaster-prone environmental sensitivity, including geological structure, groundwater level changes, and vegetation coverage; Ontological vulnerability factor: an indicator factor of landslide ontological vulnerability, including building density, population density, and infrastructure distribution; Comprehensive landslide risk: The comprehensive landslide risk is obtained by conducting a comprehensive assessment based on the hazard of hazard factors, the sensitivity of the disaster-prone environment and the vulnerability of the landslide itself.

7. The natural disaster landslide early warning risk assessment system based on model workflow according to claim 5 is characterized in that: In the model module, the algorithm model includes: Hazard factor risk model: Based on the hazard factors, the random forest or support vector machine algorithm is used for evaluation; Disaster-prone environmental sensitivity model: Based on disaster-prone factors, the model uses logistic regression or Bayesian network algorithms for evaluation; Landslide vulnerability model: Based on the vulnerability factors of building density and population density, the model is evaluated using multi-criteria decision analysis, comprehensive index method, or fuzzy matter-element evaluation method. Comprehensive landslide risk model: Combined with the hazard factor hazard model, the disaster-prone environment sensitivity model and the landslide vulnerability model, a comprehensive assessment is conducted using the weighted superposition method or the hierarchical analysis method.

8. The natural disaster landslide early warning risk assessment system based on model workflow according to claim 5 is characterized in that: In the toolset module, building a toolset includes setting the tool base class as the abstract base class, providing internationalization support through i18nFunction(), and defining a unified interface Execute(), requiring the tool implementation class as a subclass to implement the core logic; setting the tool implementation class to inherit from the tool base class, overriding the Execute() method to operate the vector dataset class DatasetVector to implement calculations; setting the factory base class to dynamically bind the relationship between the tool implementation class and the base class through the SPI registration mechanism. The factory base class instantiates the tool implementation class according to the registration information and calls its Execute() method to execute the task, while the tool base class provides public logic.

Images