Multi-detection-end natural disaster analysis system based on large model

Abstract

The invention provides a multi-detection-end natural disaster analysis system based on a large model, and the system comprises a data collection 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 scene environment simulation module establishes a scene simulation environment, the scene judgment module is used for judging an application scene to which current input data belongs, the scene noise module is used for determining the influence of basic environment noise on data, the denoising module is used for denoising disaster data results, and the standard disaster module establishes a disaster model without scene factors. The scene influence analysis module is used for establishing a feature influence database of different scenes on disaster detection data. The method fully considers the mutual influence between the two dimensions of the environment and the disaster type, and is higher in scene pertinence and more accurate in data compared with the prior art. And a data basis is provided for mutual synthesis of multiple disasters and classification of disasters with similar influence.

Description

Technical Field

[0001] The present invention relates to the field of information and communication technologies specifically applicable to administrative, commercial, financial, management, or supervision purposes, and particularly to a multi-detection-end natural disaster analysis system based on a large model. Background Art

[0002] Natural disasters are characterized by a wide variety of disaster types, wide geographical distribution, high occurrence frequency, heavy losses, and high disaster risks. To prevent and mitigate major natural disaster risks and conduct multi-hazard natural disaster risk assessments is of great significance for strengthening the ability to prevent and control natural disasters.

[0003] Currently, most natural disaster risk assessments are based on the investigation and assessment of single-hazard risk elements of natural disasters, and only consider the impact of a single natural disaster for assessment and analysis. The assessment results are not applicable to areas affected by multiple natural disasters, nor do they consider the impact of the environment on disaster data. It is difficult to establish the similarity relationship between disasters with similar impacts, resulting in difficulty in guiding the tracking of disaster emergency measures. It is difficult to provide scientific and comprehensive support for local disaster comprehensive risk assessment, disaster prevention and control, and emergency rescue work.

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

[0005] The present invention is to solve the problem that currently, most natural disaster risk assessments are based on the investigation and assessment of single-hazard risk elements of natural disasters, and only consider the impact of a single natural disaster for assessment and analysis. The assessment results are not applicable to areas affected by multiple natural disasters, nor do they consider the impact of the environment on disaster data. It is difficult to establish the similarity relationship between disasters with similar impacts, resulting in difficulty in guiding the tracking of disaster emergency measures. A multi-detection-end natural disaster analysis system based on a large model is provided. By obtaining environmental impact parameters from two dimensions of the environment and disaster type, and then obtaining the physical parameter characteristics of the actual scenario and the disaster, the above problems are solved.

[0006] The present invention provides a multi-detection-end natural disaster analysis system based on a large model, including a data acquisition module, a scenario judgment module, a scenario environment simulation module, a scenario noise module, a denoising module, a standard disaster module, and a scenario impact analysis module; The data acquisition module acquires disaster data of different actual scenarios; The scenario environment simulation module establishes a scenario simulation environment by inputting data; The scenario judgment module is used to judge the application scenario to which the currently input data belongs based on the data characteristics under the normal state of the scenario; The scene noise module is used to determine the impact of the basic environmental noise on data under normal conditions of each scene based on the scene simulation environment; The denoising module is used to denoise the disaster data collected by the data acquisition module based on the result of the scene noise module; The standard disaster module establishes a disaster model without scene factors based on theoretical data, and obtains theoretical physical detection data based on the disaster model; The scene impact analysis module is used to establish a characteristic impact database of different scenes on disaster detection data based on the standard disaster model data and the result processed by the denoising module.

[0007] In a preferred embodiment of the multi-detection-end natural disaster analysis system based on a large model of the present invention, the data collected by the data acquisition module includes electrical data, optical data, mechanical data, thermal data, fluid data, chemical data, acoustic data, and geophysical data.

[0008] In a preferred embodiment of the multi-detection-end natural disaster analysis system based on a large model of the present invention, the multi-detection-end natural disaster analysis system based on a large model further includes a disaster similarity module. The disaster similarity module extracts the analysis result of the scene impact analysis module, generates a disaster feature table according to the disaster type, scene type, and data characteristics of each physical quantity, and obtains the similarity degree of physical quantities under different combinations of disaster types and scene types according to the disaster feature table.

[0009] In a preferred embodiment of the multi-detection-end natural disaster analysis system based on a large model of the present invention, the similarity degree is obtained by the standard deviation after calculating the Canberra distance of each data.

[0010] In a preferred embodiment of the multi-detection-end natural disaster analysis system based on a large model of the present invention, the similarity calculation method is as follows: Calculate the deviation coefficient K: ; where SDq i is the standard deviation of the data corresponding to the i-th physical attribute under all scenarios and disaster types, and q i represents the quantity corresponding to the i-th physical attribute; Calculate the physical quantity correlation L: ; where b is the frequency coefficient, defaulting to 0.75, is the number of effective physical quantities in the combination of the disaster type and occurrence scenario for which the similarity is calculated, avg is the mean of the number of physical quantities in the combination of the disaster type and occurrence scenario, and k 1 is the non-linear term frequency normalization parameter, defaulting to 1.2; Calculate the correlation function : ; where D represents the combination of disaster types and occurrence scenarios for which the similarity is calculated; Calculate the recognition parameter F(q i ): ; N is the total number of combinations of disaster types and occurrence scenarios, and n(q i ) represents the number of physical quantities with the q i attribute; Calculate the similarity Sim: ; Arrange the combinations of disaster types and occurrence scenarios according to the similarity Sim. The larger the value, the higher the correlation with the current combination of disaster type and occurrence scenario.

[0011] The beneficial effects of the present invention are as follows: This technical solution fully considers the mutual influence between the two dimensions of the environment and disaster types, obtains the non-theoretical actual influence data characteristics synthesized from the environmental influence parameters and disaster influence parameters, and acquires the physical parameter characteristics of the actual scenario and the disaster. It is more targeted at the scenario and more accurate in data compared with the existing technical means. It is also convenient to provide a basis for the mutual synthesis of multiple disasters. At the same time, it provides a basis for the classification of disasters with similar influences. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of a natural disaster analysis system with multiple detection terminals based on a large model.

[0013] Reference Signs: 1. Data acquisition module; 2. Scenario judgment module; 3. Scenario environment simulation module; 4. Scenario noise module; 5. Denoising module; 6. Standard disaster module; 7. Scenario impact analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Embodiment 1

[0015] As Figure 1 shown, a natural disaster analysis system with multiple detection terminals based on a large model includes a data acquisition module 1, a scenario judgment module 2, a scenario environment simulation module 3, a scenario noise module 4, a denoising module 5, a standard disaster module 6, and a scenario impact analysis module 7; The data acquisition module 1 acquires disaster data of different actual scenarios; The scenario environment simulation module 3 establishes a scenario simulation environment through input data; The scenario judgment module 2 is used to judge the application scenario to which the current input data belongs based on the data characteristics in the normal state of the scenario; The scenario noise module 4 is used to determine the influence of the basic environmental noise on the data in the normal state of each scenario based on the scenario 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 scenario 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 influence analysis module 7 is used to establish a characteristic influence database of different scenarios on disaster detection data based on the standard disaster model data and the result processed by the denoising module 5.

[0016] The data collected by the data collection module 1 includes electrical data, optical data, mechanical data, thermal data, fluid data, chemical data, acoustic data, and geophysical data. Embodiment 2

[0017] In this embodiment, different from Embodiment 1, it further includes a disaster similarity module. The disaster similarity module extracts the analysis result of the scenario influence analysis module 7, generates a disaster characteristic table according to the analysis result according to the disaster type, scenario type, and data characteristics of each physical quantity, and obtains the similarity degree of the physical quantity in different combinations of disaster types and scenario types according to the disaster characteristic table.

[0018] The similarity degree is obtained through the standard deviation after calculating the Canberra distance of each data. Embodiment 3

[0019] Different from Embodiment 2, in this embodiment, the similarity degree is obtained through the following method: Calculate the deviation coefficient K: ; where SDq i is the standard deviation of the data corresponding to the i-th physical attribute in all scenarios and disaster types, and q i represents the quantity corresponding to the i-th physical attribute; Calculate the physical quantity correlation L: ; where b is the frequency coefficient, defaulting to 0.75, is the number of effective physical quantities in the combination of the disaster type and occurrence scenario for which the similarity degree is calculated, avg is the mean value of the number of physical quantities in the combination of the disaster type and occurrence scenario, and k 1is the frequency normalization parameter of the non - linear term, with a default value of 1.2; Calculate the correlation function : ; Among them, D represents the combination of disaster types and occurrence scenarios for which similarity is calculated; Calculate the recognition parameter F qi : ; N is the total number of combinations of disaster types and occurrence scenarios, and n qi represents the number of physical quantities with the qi attribute; Calculate the similarity Sim: ; Arrange each combination of disaster types and occurrence scenarios according to the similarity Sim. The larger the value, the higher the correlation with the current combination of disaster types and occurrence scenarios.

[0020] As described above, only the preferred specific implementation manners of the present invention are provided, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and all should be covered by the protection scope of the present invention.

Claims

1. A natural disaster analysis system with multiple detection terminals based on a large model, 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) and a scene impact analysis module (7); The data collection 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 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).

2. The natural disaster analysis system with multiple detection terminals based on a large model 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 natural disaster analysis system with multiple detection terminals based on a large model according to claim 1, characterized in that: The large model-based multi-detection terminal natural disaster analysis system also includes a disaster similarity module, which 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.

4. The natural disaster analysis system with multiple detection terminals based on a large model according to claim 3 is characterized by: The similarity is obtained by calculating the standard deviation of the Canberra distance of each data.

5. The natural disaster analysis system with multiple detection terminals based on a large model according to claim 3 is characterized by: 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 in all scenarios and disaster types, q i Represents the quantity corresponding to the i-th physical attribute; Calculate the correlation L of physical quantities: ； Where b is the frequency coefficient, the default value is 0.75, is the number of effective physical quantities of the disaster type and occurrence scenario combination whose similarity is calculated, avg is the mean of the number of physical quantities of the disaster type and occurrence scenario combination, 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 disaster type and occurrence scenario combinations are arranged according to the similarity Sim. The larger the value, the higher the correlation with the current disaster type and occurrence scenario combination.

Images