A natural disaster analysis system with multiple detection terminals based on a large model

Abstract

The present invention provides a natural disaster analysis system with multiple detection terminals based on a large model, including a data acquisition module, a scene judgment module, a scene environment simulation module, a scene noise module, a denoising module, a standard disaster module, and a scene impact analysis module. The data acquisition module collects disaster data, the scene environment simulation module establishes a scene simulation environment, the scene judgment module is used to determine the application scenario to which the current input data belongs, the scene noise module is used to determine the impact of basic environmental noise on the data, the denoising module is used to denoise the disaster data results, the standard disaster module establishes a disaster model without scene factors, and the scene impact analysis module is used to establish a database of the characteristic impacts of different scenes on disaster detection data. The present invention fully considers the mutual influence between the two dimensions of environment and disaster type, and is more scene-specific and has more accurate data than existing technical means. It provides a data basis for the mutual synthesis of multiple disasters and the classification of disasters with similar impacts.

Description

Technical Field

[0001] The present invention relates to the field of information and communication technology specifically suitable for administrative, commercial, financial, management or supervisory purposes, and in particular to a natural disaster analysis system with multiple detection terminals based on a large model. Background Art

[0002] Natural disasters are characterized by a wide variety of types, wide geographical distribution, high frequency, heavy losses, and high risk. To prevent and mitigate major natural disaster risks, conducting multi-hazard natural disaster risk assessments is crucial for strengthening natural disaster prevention and control capabilities.

[0003] Current natural disaster risk assessments are often based on surveys and assessments of risk factors for a single natural disaster, considering only the impact of a single disaster. These results are not applicable to regions affected by multiple natural disasters, nor do they consider the impact of the environment on disaster data. This makes it difficult to establish similar relationships between disasters with similar impacts, hindering the guidance and tracking of disaster response measures. This makes it difficult to provide scientific and comprehensive support for comprehensive local disaster risk assessments, disaster prevention and control, and emergency rescue efforts.

[0004] Therefore, it is necessary to provide a natural disaster analysis system with multiple detection ends based on a large model to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to solve the problem that the current natural disaster risk assessment in the existing technology is mostly based on the investigation and assessment of the risk factors of a single natural disaster, and only considers the impact of a single natural disaster for assessment and analysis. The assessment results are not applicable to areas affected by multiple natural disasters, and do not consider the impact of the environment on disaster data. It is difficult to establish similar relationships between disasters with similar impacts, which makes it difficult to guide the tracking of disaster emergency measures. A natural disaster analysis system with multiple detection terminals based on a large model is provided, which obtains environmental impact parameters through the two dimensions of environment and disaster type, and then obtains the physical parameter characteristics of the actual scene and disaster, thereby solving the above problems.

[0006] The present invention provides a large-scale model-based multi-detection terminal natural disaster analysis system, which includes a data acquisition module, a scene judgment module, a scene environment simulation module, a scene noise module, a denoising module, a standard disaster module, and a scene impact analysis module.

[0007] The data acquisition module collects disaster data from different actual scenarios;

[0008] The scene environment simulation module establishes the scene simulation environment by inputting data;

[0009] The scene judgment module is used to judge the application scene to which the current input data belongs based on the data characteristics under the normal state of the scene;

[0010] The scene noise module is used to determine the impact of basic environmental noise on data under normal conditions of each scene based on the scene simulation environment;

[0011] The denoising module is used to denoise the disaster data collected by the data acquisition module based on the results of the scene noise module;

[0012] The standard disaster module establishes a disaster model without scenario factors based on theoretical data, and obtains theoretical physical detection data based on the disaster model;

[0013] The scenario impact analysis module is used to establish a database of the characteristic impacts of different scenarios on disaster detection data based on the standard disaster model data and the results processed by the denoising module.

[0014] The present invention describes a large-scale model-based multi-detection terminal natural disaster analysis system, in which, as a preferred embodiment, the data acquisition module collects data including electrical data, optical data, mechanical data, thermal data, fluid data, chemical data, acoustic data and geophysical data.

[0015] The natural disaster analysis system with multiple detection terminals based on a large model described in the present invention, as a preferred embodiment, also includes a disaster similarity module. The disaster similarity module extracts the analysis results of the scenario impact analysis module, and generates a disaster feature table according to the data characteristics of the disaster type, scenario type and each physical quantity based on the analysis results. According to the disaster feature table, the similarity of physical quantities under different combinations of disaster types and scenario types is obtained.

[0016] In the large-scale model-based multi-detection terminal natural disaster analysis system described in the present invention, as a preferred embodiment, the similarity degree is obtained by calculating the standard deviation of the Canberra distance of each data.

[0017] In the large-scale model-based multi-detection terminal natural disaster analysis system described in the present invention, as a preferred embodiment, the similarity calculation method is:

[0018] Calculate the deviation coefficient K:

[0019] ;

[0020] Among them, SDq i is the standard deviation of the data corresponding to the ith physical attribute under all scenarios and disaster types, q i represents the quantity corresponding to the i-th physical property;

[0021] Calculate the physical quantity correlation L:

[0022] ;

[0023] Among them, b is the frequency coefficient, the default value is 0.75, is the number of effective physical quantities of the combination of disaster type and occurrence scenario whose similarity is calculated, avg is the mean of the number of physical quantities of the combination of disaster type and occurrence scenario, k1 is the frequency normalization parameter of the nonlinear term, and the default value is 1.2;

[0024] Calculate the correlation function :

[0025] ;

[0026] Where D represents the combination of disaster type and occurrence scenario whose similarity is calculated;

[0027] Calculate the identification parameter F(q i ):

[0028] ;

[0029] N is the total number of combinations of disaster types and occurrence scenarios, n(q i ) indicates a i The number of attribute physical quantities;

[0030] Calculate the similarity Sim:

[0031] ;

[0032] The combinations of disaster types and occurrence scenarios are arranged according to the similarity Sim. The larger the value, the higher the correlation with the current disaster type and occurrence scenario combination.

[0033] The beneficial effects of the present invention are as follows:

[0034] This technical solution fully considers the interplay between the environment and disaster type, generating non-theoretical, real-world impact data characteristics by synthesizing environmental and disaster impact parameters, thereby capturing the physical parameters characteristic of both the actual scenario and the disaster. Compared to existing technologies, this approach offers greater scene specificity and more accurate data. It also facilitates the synthesis of multiple disasters and provides a basis for classifying disasters with similar impacts. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Schematic diagram of a natural disaster analysis system with multiple detection terminals based on a large model.

[0036] Reference numerals:

[0037] 1. Data acquisition module; 2. Scene judgment module; 3. Scene environment simulation module; 4. Scene noise module; 5. Denoising module; 6. Standard disaster module; 7. Scene impact analysis module. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Example 1

[0039] like Figure 1 As shown, a large-scale model-based multi-detection terminal natural disaster analysis system includes a data acquisition module 1, a scene judgment module 2, a scene environment simulation module 3, a scene noise module 4, a denoising module 5, a standard disaster module 6, and a scene impact analysis module 7;

[0040] The data collection module 1 collects disaster data of different actual scenarios;

[0041] The scene environment simulation module 3 establishes a scene simulation environment by inputting data;

[0042] The scene judgment module 2 is used to judge the application scene to which the current input data belongs based on the data characteristics under the normal state of the scene;

[0043] The scene noise module 4 is used to determine the impact of basic environmental noise on data under normal conditions of each scene based on the scene simulation environment;

[0044] The denoising module 5 is used to denoise the disaster data collected by the data collection module 1 based on the results of the scene noise module 4;

[0045] Standard Disaster Module 6 establishes a disaster model without scenario factors based on theoretical data, and obtains theoretical physical detection data based on the disaster model;

[0046] The scenario impact analysis module 7 is used to establish a database of the characteristic impacts of different scenarios on disaster detection data based on the standard disaster model data and the results processed by the denoising module 5.

[0047] The data acquisition module 1 acquires data including electrical data, optical data, mechanical data, thermal data, fluid data, chemical data, acoustic data and geophysical data. Example 2

[0048] This embodiment is different from Embodiment 1 and further includes a disaster similarity module. The disaster similarity module extracts the analysis results of the scenario impact analysis module 7, generates a disaster feature table based on the analysis results according to the disaster type, scenario type and data characteristics of each physical quantity, and obtains the similarity of physical quantities under different combinations of disaster types and scenario types based on the disaster feature table.

[0049] The degree of similarity was obtained by calculating the standard deviation of the Canberra distance of each data. Example 3

[0050] Different from Example 2, the similarity in this embodiment is obtained by the following method:

[0051] Calculate the deviation coefficient K:

[0052] ;

[0053] Among them, SDq i is the standard deviation of the data corresponding to the ith physical attribute under all scenarios and disaster types, q i represents the quantity corresponding to the i-th physical property;

[0054] Calculate the physical quantity correlation L:

[0055] ;

[0056] Among them, b is the frequency coefficient, the default value is 0.75, is the number of effective physical quantities of the combination of disaster type and occurrence scenario whose similarity is calculated, avg is the mean of the number of physical quantities of the combination of disaster type and occurrence scenario, k1 is the frequency normalization parameter of the nonlinear term, and the default value is 1.2;

[0057] Calculate the correlation function :

[0058] ;

[0059] Where D represents the combination of disaster type and occurrence scenario whose similarity is calculated;

[0060] Calculate the identification parameter F qi :

[0061] ;

[0062] N is the total number of combinations of disaster types and occurrence scenarios, n qi Indicates the number of physical quantities with qi attributes;

[0063] Calculate the similarity Sim:

[0064] ;

[0065] The combinations of disaster types and occurrence scenarios are arranged according to the similarity Sim. The larger the value, the higher the correlation with the current disaster type and occurrence scenario combination.

[0066] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A large-scale model-based multi-detection terminal natural disaster analysis system, characterized by: It includes a data acquisition module (1), a scene judgment module (2), a scene environment simulation module (3), a scene noise module (4), a denoising module (5), a standard disaster module (6), a disaster similarity module and a scene impact analysis module (7); The data acquisition module (1) collects disaster data of different actual scenarios; The scene environment simulation module (3) establishes a scene simulation environment by inputting data; The scene judgment module (2) is used to judge the application scene to which the current input data belongs based on the data characteristics under the normal state of the scene; The scene noise module (4) is used to determine the influence of basic environmental noise on data in a normal state of each scene based on the scene simulation environment; The denoising module (5) is used to denoise the disaster data collected by the data collection module (1) based on the result of the scene noise module (4); The standard disaster module (6) establishes a disaster model without scenario factors based on theoretical data, and obtains theoretical physical detection data based on the disaster model; The scenario impact analysis module (7) is used to establish a database of characteristic impacts of different scenarios on disaster detection data based on the standard disaster model data and the results processed by the denoising module (5); The disaster similarity module extracts the analysis results of the scenario impact analysis module (7), generates a disaster feature table based on the analysis results according to the disaster type, scenario type and data characteristics of each physical quantity, and obtains the similarity of physical quantities under different combinations of disaster types and scenario types according to the disaster feature table; The similarity calculation method is: Calculate the deviation coefficient K: ； Among them, SDq i is the standard deviation of the data corresponding to the ith physical attribute under all scenarios and disaster types, q i represents the quantity corresponding to the i-th physical property; Calculate the physical quantity correlation L: ； Among them, b is the frequency coefficient, the default value is 0.75, is the number of effective physical quantities of the combination of disaster type and occurrence scenario whose similarity is calculated, avg is the mean of the number of physical quantities of the combination of disaster type and occurrence scenario, k1 is the frequency normalization parameter of the nonlinear term, and the default value is 1.2; Calculate the correlation function : ； Where D represents the combination of disaster type and occurrence scenario whose similarity is calculated; Calculate the identification parameter F(q i ): ； N is the total number of combinations of disaster types and occurrence scenarios, n(q i ) indicates a i The number of attribute physical quantities; Calculate the similarity Sim: ； The combinations of disaster types and occurrence scenarios are arranged according to the similarity Sim. The larger the value, the higher the correlation with the current disaster type and occurrence scenario combination.

2. The large-scale model-based multi-detection terminal natural disaster analysis system according to claim 1, characterized in that: The data acquisition module (1) acquires data including electrical data, optical data, mechanical data, thermal data, fluid data, chemical data, acoustic data and geophysical data.

3. The large-scale model-based multi-detection terminal natural disaster analysis system according to claim 1, characterized in that: The similarity is obtained by calculating the standard deviation of the Canberra distance of each data.

Images