Geological disaster intelligent safety early warning system based on internet of things

Abstract

The application discloses a geological disaster intelligent safety early warning system based on Internet of Things and relates to the technical field of geological disaster monitoring and early warning.The system comprises an edge network construction module, an Internet of Things sensing module, a multi-source data fusion module, a disaster risk assessment module and a hierarchical early warning response module.The edge network construction module deploys sensing terminals and establishes a multi-hop transmission link, collects geological environment multi-parameter monitoring data through the sensing terminals, generates fusion data streams with space-time correlation attributes through multi-source data fusion processing, calls a geological disaster evolution model to perform dynamic analysis to obtain a comprehensive disaster risk index and an influence area, and pushes early warning information and evacuation schemes according to the risk index ladder matching.The application realizes multi-source data fusion and dynamic risk assessment, can adaptively adjust early warning thresholds and hierarchically push early warning information according to real-time data change rates, and effectively improves the accuracy and response efficiency of geological disaster early warning.

Description

Technical Field

[0001] This invention relates to the field of geological disaster monitoring and early warning technology, specifically to an intelligent safety early warning system for geological disasters based on the Internet of Things. Background Technology

[0002] Intelligent early warning of geological disasters is of great significance for protecting people's lives and property and for disaster prevention and mitigation. In recent years, extreme weather has occurred frequently around the world, and geological disasters such as landslides and debris flows have become more frequent, which has placed higher demands on the monitoring and early warning capabilities of disaster-prone areas. Currently, IoT technology has been widely applied in the field of geological disaster monitoring. By deploying various sensing terminals in disaster-prone areas, remote collection and real-time transmission of geological environmental data can be achieved. However, existing geological disaster monitoring and early warning systems still have many shortcomings: First, monitoring methods mostly use single-type sensors for data collection, lacking the fusion and comprehensive analysis of multi-source heterogeneous data, making it difficult to comprehensively and accurately assess the evolution of geological disasters; second, the early warning thresholds of existing systems are mostly based on fixed empirical values ​​and cannot be adaptively adjusted according to the rate of change of real-time data, leading to early warning delays in extreme weather or sudden situations; in addition, data from different monitoring stations are often independent of each other, lacking an effective collaborative processing mechanism, and the early warning information push is also relatively simple, failing to achieve graded push to different responsible parties according to risk level.

[0003] How to achieve deep integration and dynamic risk assessment of multi-source monitoring data, and adaptively adjust the early warning threshold according to real-time data changes, so as to achieve accurate hierarchical early warning and efficient response, is the problem we need to solve. To this end, we now provide an intelligent safety early warning system for geological disasters based on the Internet of Things. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent safety early warning system for geological disasters based on the Internet of Things.

[0005] The objective of this invention can be achieved through the following technical solution: an intelligent safety early warning system for geological disasters based on the Internet of Things, comprising: The edge network construction module deploys sensing terminals, establishes a network and interconnects between sensing terminals based on a preset local communication protocol, establishes multi-hop data transmission links, and verifies the node status of sensing terminals through an edge computing gateway. The Internet of Things (IoT) sensing module is used to collect multi-parameter monitoring data of the geological environment within the target monitoring area and obtain the geospatial reference information corresponding to the target monitoring area. The multi-source data fusion module preprocesses the acquired geological environment multi-parameter monitoring data based on the geospatial reference information of the target monitoring area, generating a fused data stream with spatiotemporal correlation attributes. The disaster risk assessment module calls the constructed geological disaster evolution model to perform dynamic evolution analysis on the fused data stream, obtain the comprehensive disaster risk index and affected area of ​​the current geological disaster, and dynamically adjust the early warning threshold according to the rate of change of the fused data stream, and output the risk assessment results and hazard level. The tiered early warning and response module matches the corresponding response terminal according to the level of danger, executes the tiered push of early warning information and evacuation plans, and outputs a visual early warning report.

[0006] Preferably, in the edge network construction module, the process of deploying and interconnecting the sensing terminals includes: Several sensing terminals are deployed within the target monitoring area. A preset local communication protocol is used to assign a node ID to each sensing terminal. The path with the best signal quality is selected as the relay node according to the network topology algorithm to network and interconnect the sensing terminals and establish a multi-hop data transmission link. The edge computing gateway sends a heartbeat polling command to the sensing terminals at a preset period. When a real-time heartbeat response is not received from a terminal node for a preset number of consecutive times, the terminal node is marked as abnormal and the adjacent node interpolation filling operation is triggered. Then, the link status and real-time connectivity status of each node are summarized and uploaded.

[0007] Preferably, in the IoT sensing module, the process of collecting multi-parameter monitoring data of the geological environment and obtaining geospatial reference information includes: Through sensing terminals, data on slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level are collected according to preset sampling frequencies and reported in real time through multi-hop data transmission links. By calling the geospatial information database corresponding to the target monitoring area, high-precision digital elevation model and geospatial coordinate system data of the area are obtained as a geographical reference benchmark for multi-source data fusion processing.

[0008] Preferably, in the multi-source data fusion module, the process of preprocessing the acquired multi-parameter monitoring data includes: The system acquires the deployment three-dimensional spatial coordinates of each sensing terminal and associates the multi-parameter monitoring data reported by each terminal with the corresponding deployment coordinates. To address the differences in preset sampling frequencies, the acquired multi-parameter monitoring data is aligned to the same time reference axis and then denoised and normalized to eliminate dimensional differences between different physical quantities. The normalized multi-parameter monitoring data is then associated and aggregated according to the three-dimensional spatial coordinates of the sensing terminals to generate a fused data stream with spatiotemporal correlation attributes.

[0009] Preferably, in the disaster risk assessment module, the process of calling the geological disaster evolution model to perform dynamic evolution analysis on the fused data stream includes: Extract slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level data at the current monitoring moment from the fused data stream, and simultaneously calculate the real-time change rate and acceleration of each indicator; call the constructed geological disaster evolution model, and calculate the comprehensive disaster risk index at the current moment based on the extracted current values ​​and change rates, according to the contribution weight of each triggering factor to the disaster level; based on the value of the comprehensive disaster risk index and the spatial coordinate data of the current monitoring point, obtain the influence area of ​​the current potential landslide.

[0010] Preferably, in the disaster risk assessment module, the process of dynamically adjusting the early warning threshold based on the rate of change of the fused data stream includes: When calculating the comprehensive disaster risk index, the rate of change of each indicator in the fused data stream is tracked simultaneously. If the rate of change of a certain indicator shows a sharp increase in the short term and exceeds the preset rate warning value, the early warning response threshold corresponding to the comprehensive disaster risk index is lowered. If the rate of change continues to be flat, it is restored to the normal threshold. Based on the dynamically adjusted judgment conditions, the final risk assessment result and hazard level are output.

[0011] Preferably, in the graded early warning response module, the process of matching and pushing early warnings according to the level of danger includes: Obtain the comprehensive disaster risk index and the spatial range of the affected area; based on the comprehensive disaster risk index, conduct tiered decision matching, and push early warning information, on-site verification tasks or evacuation plans corresponding to the risk level to the terminals of responsible departments, on-site personnel, and mobile terminals of affected people within the spatial range of the affected area. While pushing the information, the system performs early warning rendering based on the GIS map engine, marks the scope of the affected area, and generates a visual early warning report to push to terminals at all levels.

[0012] Compared with existing technologies, the beneficial effects of this invention are as follows: by generating a fused data stream with spatiotemporal correlation attributes through multi-source data fusion processing, the fusion and accurate assessment of multi-parameter monitoring data of the geological environment are realized; at the same time, the geological disaster evolution model can adaptively adjust the early warning threshold according to the rate of change of the fused data stream, effectively improving the response sensitivity and reliability to sudden geological disasters; in addition, the system performs tiered decision matching based on the comprehensive disaster risk index, realizing graded push to various terminals under different risk levels, significantly improving the accuracy of geological disaster early warning and the overall efficiency of emergency response. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0015] like Figure 1 As shown, an IoT-based intelligent safety early warning system for geological disasters includes: The edge network construction module deploys sensing terminals, establishes a network and interconnects between sensing terminals based on a preset local communication protocol, establishes multi-hop data transmission links, and verifies the node status of sensing terminals through an edge computing gateway. The Internet of Things (IoT) sensing module is used to collect multi-parameter monitoring data of the geological environment within the target monitoring area and obtain the geospatial reference information corresponding to the target monitoring area. The multi-source data fusion module preprocesses the acquired geological environment multi-parameter monitoring data based on the geospatial reference information of the target monitoring area, generating a fused data stream with spatiotemporal correlation attributes. The disaster risk assessment module calls the constructed geological disaster evolution model to perform dynamic evolution analysis on the fused data stream, obtain the comprehensive disaster risk index and affected area of ​​the current geological disaster, and dynamically adjust the early warning threshold according to the rate of change of the fused data stream, and output the risk assessment results and hazard level. The tiered early warning and response module matches the corresponding response terminal according to the level of danger, executes the tiered push of early warning information and evacuation plans, and outputs a visual early warning report.

[0016] Furthermore, in the edge network construction module, the process of deploying and interconnecting sensing terminals includes: Based on the on-site terrain and spatial range of the target monitoring area, several distributed sensing terminals are deployed within the target monitoring area. After deployment, a local communication protocol is constructed based on LoRa spread spectrum modulation technology. A unique node ID is assigned to each sensing terminal. According to the preset networking topology algorithm, the real-time signal strength of each terminal is used as the path weight. The path with the best signal quality is selected as the relay node to perform networking and interconnection between sensing terminals and establish a multi-hop data transmission link. It should be further explained that during the networking process, multiple possible relay transmission paths between various sensing terminals are considered as candidate paths. A comprehensive score is applied to each candidate path. The preset network topology algorithm uses a weighted path scoring criterion, and its scoring formula is as follows: , in, Let J be the real-time signal-to-noise ratio of the j-th alternative path. This is the communication stability coefficient for this path. This represents the historical packet loss rate for this path. , , These are the corresponding preset weighting coefficients; The scoring formula calculates the comprehensive score of each alternative path and selects the one with the highest score as the optimal communication link at the current moment. In actual operation scenarios, the specific operation logic of the multi-hop data transmission link is as follows: when the straight-line distance between terminal A located at the bottom of the valley and the edge computing gateway is too far or there is a mountain in between, making it impossible for terminal A to communicate directly with the gateway point-to-point, terminal A will send the collected geological monitoring data to terminal B on the mountainside with better signal, and terminal B will act as a relay node to forward it to the edge computing gateway, thereby realizing multi-hop data transmission in complex mountainous terrain. Furthermore, in the edge network construction module, the process of verifying the node status of the sensing terminal through the edge computing gateway includes: The edge computing gateway sends heartbeat polling commands to all sensing terminals within its jurisdiction at a preset fixed period. When the gateway fails to receive a real-time heartbeat response from a terminal node three times in a row, it marks the terminal node as "abnormal" in the node status table and triggers the neighboring node interpolation filling operation. Subsequently, it summarizes and uploads the link status and real-time connectivity status of each node.

[0017] Furthermore, in the IoT sensing module, the process of collecting multi-parameter monitoring data of the geological environment within the target monitoring area includes: The sensing terminals deployed in the target monitoring area collect data on slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level elevation at a preset sampling frequency, and report the collected raw measurement data in real time through a multi-hop data transmission link; the sensing terminals include GNSS displacement monitoring nodes, tipping bucket rain gauges, FDR soil moisture sensors and water pressure level gauges; Furthermore, in the IoT sensing module, the process of acquiring the geospatial reference information corresponding to the target monitoring area includes: By calling the geospatial information database corresponding to the target monitoring area, the high-precision digital elevation model and geospatial coordinate system data of the area are obtained as a geographic reference benchmark for subsequent multi-source data fusion processing; It should be further explained that the geospatial information database is pre-loaded into the backend database before operation, and is used to provide a unified geographic coordinate system mapping reference for discrete data collected by various types of sensors.

[0018] Furthermore, in the multi-source data fusion module, the process of preprocessing the acquired multi-parameter monitoring data includes: It receives and collects data on slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content, and groundwater level elevation; it uses the acquired high-precision digital elevation model and geospatial coordinate system data of the target monitoring area as a reference for spatial projection; and it acquires the deployment three-dimensional spatial coordinates of each sensing terminal. The multi-parameter monitoring data reported by each terminal is uniformly associated with its corresponding deployment coordinates, so that the originally discrete sensor readings have a clear spatial attribute. After completing the spatial correlation, based on the differences in the preset sampling frequencies of different sensors, piecewise linear interpolation is used to align all sensor data to the same time reference axis; In the denoising stage, Kalman filtering or low-pass filtering algorithms are used to filter out abnormal spike noise caused by electromagnetic interference in the field environment; in the normalization stage, the Min-Max normalization method is used to uniformly map the measured values ​​of various physical quantities to... The normalization formula for the interval is: , in, These are the original measured values. This is the minimum range of the sensor. This is the maximum range of the sensor; After completing the above processing, the data is processed according to the three-dimensional spatial coordinates of the monitoring points. The normalized multi-parameter monitoring data of each point are correlated and aggregated to generate a multi-dimensional data vector containing the characteristics of slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric water content and groundwater level elevation, forming a fused data stream with spatiotemporal correlation attributes; It should be further explained that the fused data stream generated after preprocessing is essentially a set of six-dimensional spatial point cloud data structures arranged in a time series based on a geospatial benchmark: Where t is a unified timestamp. For spatial point coordinates, These are the normalized slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level data corresponding to this location.

[0019] Furthermore, in the disaster risk assessment module, the process of calling the geological disaster evolution model to perform dynamic evolution analysis on the fused data stream includes: Extract the slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level data at the current monitoring moment from the fused data stream, and simultaneously calculate the real-time change rate and acceleration of each indicator; The constructed geological hazard evolution model is invoked, and the comprehensive hazard risk index for the current moment is calculated based on the extracted current value and rate of change. Its calculation expression is: , in, The acceleration representing the change in displacement of the current slope surface. This represents the region's historical maximum displacement acceleration. This represents the cumulative rainfall over the previous 24 hours. This is the critical rainfall level for disaster prevention; This represents the current soil volumetric moisture content. This refers to the soil saturation water content. , , The dynamic trigger weight coefficients are obtained by training and extracting from historical disaster data; Based on the comprehensive disaster risk index Based on the numerical values ​​and the spatial coordinate data of the current monitoring points, the potential impact area of ​​the landslide is estimated, and a preliminary risk assessment result is output. Further explanation is needed regarding the construction process of the geological disaster evolution model: A sample set is constructed by collecting historical landslide disaster records and corresponding data on slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content, and groundwater level elevation in the target monitoring area. The abrupt changes of each disaster triggering factor in this sample set before the landslide occur are used as features. The occurrence and severity of the landslide are used as the judgment criteria, and a classification algorithm is used to train the model. After training, the contribution weights of each triggering factor to the landslide occurrence are extracted from the model and used as weight coefficients in the subsequent dynamic weighted scoring formula. , , Meanwhile, based on the median mutation rate of each triggering factor before the occurrence of historical landslides, dynamic adjustment coefficients and rate warning values ​​are set to form an evolutionary model that can automatically adjust weights when real-time data changes. When invoked, the model performs dynamic evolution calculations based on the slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric water content and groundwater level data uploaded in real time by the sensing terminal. Furthermore, in the disaster risk assessment module, the process of dynamically adjusting the early warning threshold based on the rate of change of the fused data stream includes: When calculating the comprehensive disaster risk index, the rate of change of slope surface displacement, rainfall intensity, soil volumetric moisture content, and groundwater level in the fused data stream is tracked simultaneously; and a rate warning value is preset for each indicator. Real-time calculation of the instantaneous rate of change of the current indicator. And calculate the proportion exceeding the threshold. ; When the rate of change of any indicator shows a sharp increase in the short term and At that time, the dynamic risk downgrade coefficient K is automatically calculated, and its calculation formula is as follows: , in, The preset adaptive adjustment coefficient K is used to adjust the comprehensive disaster risk index in real time. Corresponding early warning response thresholds: Actual high-risk trigger threshold = , Actual medium risk trigger threshold = , The higher the rate of change, the smaller the degradation coefficient K, and the lower the threshold for triggering a high-level warning. This allows for a lower threshold in extreme situations such as sudden heavy rainfall or abrupt changes in displacement. Numerical values ​​trigger high-level early warnings, enabling early identification and timely response; when the rate of change of each indicator falls back to... The following is When the K value is restored to 1, the warning threshold is restored to the normal set value; based on the dynamically adjusted judgment conditions, the final risk assessment result and hazard level are output.

[0020] It should be further explained that the "hazard level" output by the disaster risk assessment module is directly based on the dynamically adjusted... The numerical value is mapped to the corrected trigger threshold within a range: when When, it is judged as high risk; when At that time, it was determined to be of medium risk; when At that time, it was determined to be low risk.

[0021] Furthermore, in the tiered early warning response module, the process of matching and pushing early warnings according to the level of danger includes: Obtain the comprehensive disaster risk index and the spatial scope of the affected area; subsequently, directly based on The specific values ​​are used for tiered decision matching, taking the conventionally set warning threshold as an example; The triggering rules are as follows: when At the same time, it initiates multi-terminal parallel push to all responsible department terminals, on-site handling personnel terminals, and disaster-affected people's mobile terminals within the affected area, and automatically generates an evacuation plan that includes evacuation routes, assembly point coordinates, and danger zone range, and simultaneously sends the early warning information and evacuation plan to the above-mentioned matching terminals. when At the same time, early warning information and on-site verification tasks are pushed to the terminals of responsible departments, on-site personnel, and mobile terminals of affected people within the affected area; when At that time, routine geological inspection instructions are sent only to the terminals of the responsible departments and on-site personnel within the affected area, without triggering evacuation warnings for the affected people; While sending out early warnings, the system renders the warnings based on a GIS map engine, marks the affected area on a 3D map, and dynamically draws isosurface maps of geological disaster risk. Combining the fusion data stream and risk level, it generates a comprehensive situational visualization early warning report that includes real-time reading curves of each monitoring point and the early warning status, and pushes it to the terminals of responsible departments, on-site personnel, and the mobile terminals of affected people. It should be further explained that the response terminal is a remote communication device used to receive and display early warning instructions; the terminal of the responsible department includes portable communication devices used by the rear disaster prevention command organization to receive early warning information and issue command and dispatch instructions; the terminal of the on-site personnel includes smartphones and walkie-talkies to receive on-site verification tasks and provide feedback on on-site execution; and the mobile terminal of the affected people includes smartphones to receive evacuation early warning information.

[0022] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications or equivalent substitutions made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A smart geological disaster safety early warning system based on the Internet of Things, characterized in that, include: The edge network construction module deploys sensing terminals, establishes a network and interconnects between sensing terminals based on a preset local communication protocol, establishes multi-hop data transmission links, and verifies the node status of sensing terminals through an edge computing gateway. The Internet of Things (IoT) sensing module is used to collect multi-parameter monitoring data of the geological environment within the target monitoring area and obtain the geospatial reference information corresponding to the target monitoring area. The multi-source data fusion module preprocesses the acquired geological environment multi-parameter monitoring data based on the geospatial reference information of the target monitoring area, generating a fused data stream with spatiotemporal correlation attributes. The disaster risk assessment module calls the constructed geological disaster evolution model to perform dynamic evolution analysis on the fused data stream, obtain the comprehensive disaster risk index and affected area of ​​the current geological disaster, and dynamically adjust the early warning threshold according to the rate of change of the fused data stream, and output the risk assessment results and hazard level. The tiered early warning and response module matches the corresponding response terminal according to the level of danger, executes the tiered push of early warning information and evacuation plans, and outputs a visual early warning report.

2. The intelligent geological disaster safety early warning system based on the Internet of Things according to claim 1, characterized in that, In the edge network construction module, the process of deploying and interconnecting sensing terminals in the network includes: Several sensing terminals are deployed within the target monitoring area. A preset local communication protocol is used to assign a node ID to each sensing terminal. The path with the best signal quality is selected as the relay node according to the network topology algorithm to network and interconnect the sensing terminals and establish a multi-hop data transmission link. The edge computing gateway sends a heartbeat polling command to the sensing terminals at a preset period. When a real-time heartbeat response is not received from a terminal node for a preset number of consecutive times, the terminal node is marked as abnormal and the adjacent node interpolation filling operation is triggered. Then, the link status and real-time connectivity status of each node are summarized and uploaded.

3. The intelligent geological disaster safety early warning system based on the Internet of Things according to claim 2, characterized in that, In the IoT sensing module, the process of collecting multi-parameter monitoring data of the geological environment and obtaining geospatial reference information includes: Through sensing terminals, data on slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level are collected according to preset sampling frequencies and reported in real time through multi-hop data transmission links. By calling the geospatial information database corresponding to the target monitoring area, high-precision digital elevation model and geospatial coordinate system data of the area are obtained as a geographical reference benchmark for multi-source data fusion processing.

4. The intelligent geological disaster safety early warning system based on the Internet of Things according to claim 3, characterized in that, In the multi-source data fusion module, the process of preprocessing the acquired multi-parameter monitoring data includes: The system acquires the deployment three-dimensional spatial coordinates of each sensing terminal and associates the multi-parameter monitoring data reported by each terminal with the corresponding deployment coordinates. To address the differences in preset sampling frequencies, the acquired multi-parameter monitoring data is aligned to the same time reference axis and then denoised and normalized to eliminate dimensional differences between different physical quantities. The normalized multi-parameter monitoring data is then associated and aggregated according to the three-dimensional spatial coordinates of the sensing terminals to generate a fused data stream with spatiotemporal correlation attributes.

5. The intelligent geological disaster safety early warning system based on the Internet of Things according to claim 4, characterized in that, In the disaster risk assessment module, the process of calling the geological disaster evolution model to perform dynamic evolution analysis on the fused data stream includes: Extract slope surface displacement, rainfall intensity and cumulative rainfall, soil volumetric moisture content and groundwater level data at the current monitoring moment from the fused data stream, and simultaneously calculate the real-time change rate and acceleration of each indicator; call the constructed geological disaster evolution model, and calculate the comprehensive disaster risk index at the current moment based on the extracted current values ​​and change rates, according to the contribution weight of each triggering factor to the disaster level; based on the value of the comprehensive disaster risk index and the spatial coordinate data of the current monitoring point, obtain the influence area of ​​the current potential landslide.

6. The intelligent geological disaster safety early warning system based on the Internet of Things according to claim 5, characterized in that, In the disaster risk assessment module, the process of dynamically adjusting the early warning threshold based on the rate of change of the fused data stream includes: When calculating the comprehensive disaster risk index, the rate of change of each indicator in the fused data stream is tracked simultaneously. If the rate of change of a certain indicator shows a sharp increase in the short term and exceeds the preset rate warning value, the early warning response threshold corresponding to the comprehensive disaster risk index is lowered. If the rate of change continues to be flat, it is restored to the normal threshold. Based on the dynamically adjusted judgment conditions, the final risk assessment result and hazard level are output.

7. The intelligent safety early warning system for geological disasters based on the Internet of Things according to claim 6, characterized in that, In the tiered early warning response module, the process of matching and pushing early warnings according to the level of danger includes: Obtain the comprehensive disaster risk index and the spatial range of the affected area; based on the comprehensive disaster risk index, conduct tiered decision matching, and push early warning information, on-site verification tasks or evacuation plans corresponding to the risk level to the terminals of responsible departments, on-site personnel, and mobile terminals of affected people within the spatial range of the affected area. While pushing the information, the system performs early warning rendering based on the GIS map engine, marks the scope of the affected area, and generates a visual early warning report to push to terminals at all levels.

Images