A risk prevention and mitigation method and system based on map data fusion

Abstract

This application relates to the field of smart city technology, and particularly to a risk prevention and management method and system based on map data fusion. The method includes: acquiring multi-dimensional geographic attribute data from a multi-source geographic information database; analyzing the multi-dimensional geographic attribute data to obtain multiple grid areas with risk coupling effects, which are then designated as risk areas to be investigated; retrieving refined geographic monitoring data and regional response data corresponding to each risk area to be investigated to analyze the geographic correlation of the regional responses; analyzing the refined geographic monitoring data and regional response data of each risk area to be investigated to identify specific impact information instances contained in each risk area; and determining risk management plans for the specific impact information instances based on these instances, thereby weaving people, places, events, things, and organizational elements into a comprehensive security and prevention network to enhance risk prevention capabilities.

Description

Technical Field

[0001] This application belongs to the field of smart city technology, and in particular relates to a risk prevention and control method and system based on map data fusion. Background Technology

[0002] With the continuous advancement of smart city construction, the integrated application of geographic information systems (GIS) and multi-source sensing technologies has become a core support for regional risk prevention and control. Among the current mainstream risk prevention methods, technicians can construct risk monitoring networks by integrating geospatial databases and deploying monitoring terminals to collect and issue early warnings of risk factors in specific areas. For example, they can use map data to divide monitoring grids and combine it with environmental sensor data to generate risk level distribution maps.

[0003] In existing risk prevention methods, when a comprehensive assessment combining spatial characteristics and regional feedback is required, it is necessary to separately call upon geographic information platforms and regional data analysis systems. The data switching and manual comparison processes are cumbersome and can easily cause the best opportunity for risk response to be missed. Especially in densely populated areas or in emergency scenarios, the speed of information flow and the ability to analyze geospatial location and potential flow directions are insufficient, resulting in untimely early warning responses or inadequate targeted response measures. Summary of the Invention

[0004] This application provides a risk prevention and control method and system based on map data fusion, which can solve the problems in existing urban governance methods, such as cumbersome data switching and manual comparison processes, insufficient information data flow speed and geospatial positioning and potential flow direction analysis capabilities, resulting in untimely early warning response or insufficient targeted measures.

[0005] In a first aspect, embodiments of this application provide a risk prevention and mitigation method based on map data fusion, including:

[0006] Obtain multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database;

[0007] The multi-dimensional geographic attribute data corresponding to each of the spatial grids are analyzed to obtain multiple grid areas with risk coupling effects, which are then identified as risk areas to be investigated; wherein, each grid area is a geographic area corresponding to a single spatial grid.

[0008] Retrieve refined geographic monitoring data and regional response data corresponding to each of the risk areas to be investigated from the multi-source geographic information database;

[0009] The refined geographic monitoring data and regional response data of each of the risk areas to be investigated are analyzed to identify specific impact information instances contained in each of the risk areas to be investigated; wherein, the specific impact information instance is an information instance in which the rate of change of information flow exceeds a threshold within a preset continuous time period.

[0010] Based on specific impact information instances of the risk area to be investigated, determine the risk management plan for the specific impact information instances.

[0011] The technical solutions described in this application embodiment have at least the following technical effects:

[0012] The risk prevention and mitigation method based on map data fusion provided in this application accurately grasps the geographical characteristics and potential risk basis of each spatial grid by acquiring multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database. Analyzing the multi-dimensional geographic attribute data corresponding to each spatial grid identifies multiple grid areas with risk coupling effects, which are then designated as risk areas to be investigated, achieving precise location of regional risks and effectively quantifying and analyzing the risk correlation characteristics between regions. Retrieving refined geographic monitoring data and regional response data corresponding to each risk area to be investigated from the multi-source geographic information database provides data support for analyzing the geographic correlation of regional responses. Analyzing the refined geographic monitoring data and regional response data of each risk area to be investigated identifies information instances that may cause risks within each risk area, reducing data switching and manual comparison processes, achieving targeted focus in risk assessment, and improving the accuracy and timeliness of risk identification. Based on specific impact information instances of the risk areas to be investigated, risk management plans for specific impact information instances are determined, forming an intelligent closed-loop governance capability, improving risk prevention and emergency response capabilities, realizing early warning, prediction, prevention, and handling of risk elements, making the security situation clear at a glance, and weaving people, places, events, things, and organizational elements into a comprehensive security prevention and control network.

[0013] Secondly, embodiments of this application provide a risk prevention and mitigation system based on map data fusion, including:

[0014] The acquisition unit is used to acquire multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database.

[0015] The analysis unit is used to analyze the multi-dimensional geographic attribute data corresponding to each of the spatial grids to obtain multiple grid areas with risk coupling effects and to identify them as risk areas to be investigated; wherein, the grid area is the geographic area corresponding to a single spatial grid.

[0016] The retrieval unit is used to retrieve the refined geographic monitoring data and regional response data corresponding to each of the risk areas to be investigated from the multi-source geographic information database.

[0017] The identification unit is used to analyze the refined geographic monitoring data and regional response data of each of the risk areas to be investigated, and to identify specific impact information instances contained in each of the risk areas to be investigated; wherein, the specific impact information instance is an information instance in which the rate of change of information flow exceeds a threshold within a preset continuous time period.

[0018] The handling unit is used to determine a risk handling plan for the specific impact information instance based on the specific impact information instance of the risk area to be investigated.

[0019] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any of the first aspects above.

[0020] Fourthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any of the above aspects.

[0021] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the above aspects, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a risk prevention and handling method based on map data fusion provided in an embodiment of this application;

[0024] Figure 2 This is a schematic diagram illustrating the execution of a risk prevention and handling method based on map data fusion provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of the structure of a risk prevention and handling system based on map data fusion provided in an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0028] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0029] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0030] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determination" or "if the described condition or event is detected" may be interpreted, depending on the context, as "once determination," "in response to determination," "once the described condition or event is detected," or "in response to the detection of the described condition or event."

[0031] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0033] In existing risk prevention methods, when a comprehensive assessment combining spatial characteristics and regional feedback is required, it is necessary to separately call upon geographic information platforms and regional data analysis systems. The data switching and manual comparison processes are cumbersome and can easily cause the best opportunity for risk response to be missed. Especially in densely populated areas or in emergency scenarios, the speed of information flow and the ability to analyze geospatial location and potential flow directions are insufficient, resulting in untimely early warning responses or inadequate targeted response measures.

[0034] To address the aforementioned issues, this application provides a risk prevention and management method and system based on map data fusion. This method acquires multi-dimensional geographic attribute data corresponding to each preset spatial grid from a pre-defined multi-source geographic information database, accurately grasping the geographic characteristics and potential risk basis of each spatial grid. Analyzing the multi-dimensional geographic attribute data corresponding to each spatial grid reveals multiple grid areas exhibiting risk coupling effects, which are then designated as risk areas to be investigated, achieving precise location of regional risks and effectively quantifying and analyzing the risk correlation characteristics between regions. Refined geographic monitoring data and regional response data corresponding to each risk area to be investigated are retrieved from the multi-source geographic information database, providing data support for analyzing the geographic correlation of regional responses. Analyzing the refined geographic monitoring data and regional response data of each risk area to be investigated identifies information instances that may cause risks within each risk area, reducing data switching and manual comparison processes, achieving targeted focus in risk assessment, and improving the accuracy and timeliness of risk identification. Based on specific impact information instances of the risk areas to be investigated, risk management plans for specific impact information instances are determined to enhance risk prevention and emergency response capabilities, realize early warning, prediction, prevention, and management of risk factors, make the security situation clear at a glance, and weave people, places, events, things, and organizational elements into a comprehensive security and prevention network.

[0035] The risk prevention and handling method based on map data fusion provided in this application can be applied to electronic devices. In this case, the electronic device is the subject of execution of the risk prevention and handling method based on map data fusion provided in this application. This application does not impose any restrictions on the specific type of electronic device.

[0036] For example, the electronic device can be various types of intelligent monitoring devices. This electronic device may include, but is not limited to, desktop computers, smart screens, smart TVs, handheld devices with wireless communication capabilities, computing devices, computers, laptops, etc.

[0037] To better understand the risk prevention and handling method based on map data fusion provided in the embodiments of this application, the specific implementation process of the risk prevention and handling method based on map data fusion provided in the embodiments of this application will be described by way of example below.

[0038] Figure 1 This illustration shows a schematic flowchart of a risk prevention and handling method based on map data fusion provided in an embodiment of this application. Figure 2 This paper illustrates a flowchart of the execution steps of a risk prevention and mitigation method based on map data fusion provided in an embodiment of this application. The risk prevention and mitigation method based on map data fusion includes:

[0039] S100 retrieves multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database.

[0040] As can be understood, a multi-source geographic information database refers to a collection of spatial data from multiple sources, including remote sensing imagery, location sensor data, public service basic data, trajectory data, event report records, and statistical yearbook data. Multi-source geographic information databases undergo format standardization, spatial registration, temporal alignment, and semantic mapping processing, possessing a complete metadata system and real-time update capabilities, supporting flexible access by time period, region, layer, and data type. Spatial grids are pre-divided, equal-area, regularly shaped analytical units representing the target governance area. Each grid has a unique number and boundary information; common grid sizes include 50m×50m and 100m×100m, used for high-resolution regional modeling. Multi-dimensional geographic attribute data refers to the descriptive geographic elements contained in each spatial grid within a specific monitoring time period, covering multiple dimensions such as physical terrain (e.g., elevation, slope), functional structure (e.g., roads, business districts, industrial zones), population characteristics (e.g., mobility density, age composition), facility distribution (e.g., education, healthcare, transportation nodes), and event frequency (e.g., sudden alarms, facility failures). Spatial grids can be located using spatial indexing techniques (such as R-trees and quadtrees). Then, based on their spatiotemporal and data layer labels, parallel data retrieval and caching operations are performed in a multi-source geographic information database. The acquired multi-dimensional geographic attribute data is organized in the form of multi-dimensional feature vectors or tensors, supporting structured analysis and graph computation input, ensuring data integrity, spatial coherence, and temporal synchronization for subsequent risk coupling and identification algorithms. The final result is the generation of a spatial grid set covering the target analysis area, and the establishment of a corresponding multi-dimensional attribute label cluster for each spatial grid unit, achieving holographic digital modeling of urban space and providing a high-quality spatiotemporal sample foundation for subsequent analysis.

[0041] S200 analyzes the multi-dimensional geographic attribute data corresponding to each spatial grid to obtain multiple grid areas with risk coupling effects and uses them as risk areas to be investigated; where a grid area is the geographic area corresponding to a single spatial grid.

[0042] It is understandable that multi-dimensional geographic attribute data corresponding to each spatial grid can be analyzed to identify sensitive areas with complex risk superposition structures—i.e., risk coupling areas—from the overall prevention and control area, and these areas can be selected as the focus of subsequent analysis and governance intervention. Risk coupling areas refer to the geographic areas corresponding to spatial grids where risk factors of different categories and sources have significant co-occurrence relationships in space and time. These areas may form a synergistic amplification effect, manifesting as a complex situation of simultaneous risk increases, enhanced event propagation efficiency, and increased governance difficulty. Risk status modeling and coupling degree identification for each spatial grid can be performed using various methods such as statistical modeling, graph structure analysis, and time series modeling on the acquired multi-dimensional geographic attribute data. For example, feature mapping methods can be used to convert the information of each risk point within the grid into a time series tensor. Then, abnormal trends can be identified using methods such as sliding window statistics, K-means clustering, or isolated forests. Finally, spatial propagation weights can be introduced through a spatial adjacency matrix to construct a risk transmission relationship network. Based on this, it is assessed whether each spatial grid is simultaneously located in a high-impact zone across multiple risk channels, or whether it has a strong structural coupling relationship with adjacent high-risk areas. This results in the output label of the coupling identification model, marking grid areas that meet the preset coupling strength threshold as risk areas to be investigated. Subsequent analysis will focus on the information evolution, information activity level, and adaptability of intervention measures within these risk areas, enabling the early detection of potential risk clusters and providing timely and accurate data support for resource allocation, intelligent early warning, and emergency response.

[0043] In one possible implementation, S200, the multi-dimensional geographic attribute data corresponding to each spatial grid is analyzed to obtain multiple grid areas with risk coupling effects, which are then designated as risk areas to be investigated, including:

[0044] S210. Based on the multi-dimensional geographic attribute data corresponding to each spatial grid, determine the spatial risk status value sequence and risk spatial correlation sequence corresponding to each spatial grid in the first monitoring period. Among them, the spatial risk status value sequence is used to reflect the evolution law of the risk level of a single spatial grid in the first monitoring period; the risk spatial correlation sequence is used to reflect the mutual influence intensity and transmission law of risk elements between different spatial grids.

[0045] It can be understood that the spatial risk situation value sequence is a dynamic trend value that summarizes risk-related characteristic indicators within a continuous time period (such as days or hours) of a certain spatial grid. The first monitoring period refers to a preset data monitoring period, such as a preset continuous time period of days or hours. The spatial risk situation value sequence is used to reflect the evolution of the risk level of a single spatial grid within the first monitoring period. It can be modeled by constructing a weighted aggregation function to model the weights of different types of risk factors within the grid. For example, factors such as building density, population density, traffic node density, and historical event frequency can be linearly or nonlinearly combined according to set weights to generate a continuous value sequence that changes over time, i.e., the spatial risk situation value sequence. The risk spatial correlation sequence is used to reflect the mutual influence and transmission law of risk elements between different spatial grids. The risk spatial correlation sequence can be obtained by establishing a spatial interaction graph model, treating each spatial grid as a graph node, and modeling the possibility of information flow, information resonance intensity, or attribute synergy probability between adjacent spatial grids as edge weights. Then, by using a sliding window to calculate the node centrality measure, structural embedding dimension, or signal strength synergy coefficient at each time point, a dynamic sequence measuring the influence of spatial interaction risks is generated. The spatial risk situation value sequence and the risk spatial correlation sequence constitute the input basis for multidimensional space-time analysis, which can be used for subsequent risk coupling function modeling and identification analysis, more accurate judgment of key areas and construction of multidimensional indicator linkage early warning mechanism.

[0046] Optionally, in step S210, based on the multi-dimensional geographic attribute data corresponding to each spatial grid, the spatial risk situation value sequence corresponding to each spatial grid within the first monitoring period is determined, including:

[0047] S211, perform the first analysis on the multi-dimensional geographic attribute data corresponding to each spatial grid to obtain the dynamic risk value sequence of various risk points contained in each spatial grid within the first monitoring period; wherein, the dynamic risk value sequence is used to reflect the real-time status change trend of a single risk point within a specific spatial grid within the first monitoring period.

[0048] It is understandable that fine-grained temporal deconstruction can be performed on the data of different types of risk points in each spatial grid to extract the dynamic change trajectory reflecting the fluctuation characteristics of individual risk sources. A risk point refers to a specific risk unit in the spatial grid with an independent identification number, classification label, and coordinate attributes, such as a high-traffic commercial area, a key facility area, or a densely populated traffic intersection. Risk point data can originate from IoT terminals, video monitoring equipment, business reporting systems, or citizen feedback records. Based on the risk point type, feature variables can be formed using preset feature extraction rules (such as sensor value standardization, image recognition labeling, and text event structuring). These feature variables are then arranged in chronological order within a specified monitoring period (such as the past 7 days or 30 days) to form a risk value sequence. Dynamic risk values ​​reflect the activity, rate of change, and degree of abnormal surge of a risk point over time, serving as an important signal source for capturing potential risk precursors.

[0049] S212, Based on the dynamic risk value sequence of various risk points contained in each spatial grid, calculate the spatial risk situation value sequence corresponding to each spatial grid in the first monitoring period.

[0050] It is understandable that the dynamic risk value sequences of multiple risk points in a spatial grid can be aggregated and normalized to form a spatial risk situation value sequence that represents the overall risk status of the grid over time. This transforms fine-grained information about local individual risks into time-series trend data expressing a global region level, facilitating subsequent global situation comparison and dynamic evolution modeling. For each set of risk points within a spatial grid, risk weights can be assigned based on risk point categories (e.g., pedestrian flow, facility, event). These weights can be set using methods such as expert scoring, the Analytic Hierarchy Process (AHP), or historical regression models. Multiple dynamic risk value sequences can then be combined using weighted averaging, principal component extraction, and anomaly weighted fusion to form a unique time series. For example, rapid changes in pedestrian density and increased facility failure frequency in a certain area can be mapped to an "increased risk" trend, outputting a continuous spatial risk situation curve with an hourly or daily cycle. The spatial risk situation value sequence will serve as the input source for downstream coupling analysis and risk propagation prediction, enhancing the dynamic perception and response capabilities of subsequent models.

[0051] Optionally, S210, based on the multi-dimensional geographic attribute data corresponding to each spatial grid, determine the spatial risk status value sequence and risk spatial correlation sequence corresponding to each spatial grid in the first monitoring period, including:

[0052] S213, perform a second analysis on the multi-dimensional geographic attribute data corresponding to each spatial grid to determine the spatial distribution information of risk points within each spatial grid; wherein, the spatial distribution information is used to reflect the spatial distribution pattern of risk points within the spatial grid.

[0053] Spatial distribution information refers to a set of spatial structural indicators, including the location coordinates, relative density, distribution balance, cluster center location, and clustering direction of risk points. The second analysis differs from the time-series dynamic analysis in S211; instead, it uses spatial statistical methods to mine structural relationships within the grid. Kernel density estimation (KDE) can be used to calculate a spatial concentration heatmap of risk points; Ripley's K function can be used to analyze clustering or dispersion trends; clustering methods such as DBSCAN, K-Means, and Mean-Shift can be introduced to identify hotspot areas and distribution cores; or spatial autocorrelation indices such as Moran's I and Geary's C can be used to evaluate distribution regularity. Spatial distribution information not only provides a basis for subsequent spatial correlation sequences but can also be used to intervene in the optimization of resource spatial layout, improving the spatial accuracy and efficiency of governance interventions.

[0054] S214. Based on the spatial distribution information of risk points within each spatial grid and the dynamic risk value sequence of various risk points in the first monitoring period, calculate the risk spatial correlation sequence corresponding to each spatial grid in the first monitoring period.

[0055] It is understandable that the spatial correlation sequence of risks reflects whether the risk of a spatial grid within a specific time window may be affected by the diffusion, transmission, or resonance of risks from neighboring areas. Spatial connectivity between grids can be determined by constructing an adjacency matrix or a spatial influence weighting map. This spatial connectivity can be determined based on dimensions such as shared boundaries, traffic connectivity, and functional similarity. The spatial distribution characteristics of the current grid (such as risk point cluster density, location centroid, and distribution pattern) are multiplied and coupled with the dynamic risk intensity of adjacent grids to form the external risk input of the current spatial grid at each time step. For example, if the internal risk value of grid A is low, but the risk of its adjacent grid B continues to increase, and A and B have strong functional connectivity (such as a traffic intersection connection), then the spatial correlation of risk in A will be marked as high at the current time. A continuous spatial correlation sequence of risks can be formed through time sliding windows, which can serve as a quantitative basis for the spatial external sensitivity of nodes. The spatial correlation sequence of risks can reveal which areas have strong "risk receiving" characteristics in spatiotemporal evolution, helping to construct urban risk response topology maps, discover potential interconnected core areas, and assist in risk early warning and prevention.

[0056] S220, the spatial risk situation value sequence and risk spatial correlation degree sequence corresponding to each spatial grid are analyzed to obtain the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid; wherein, the correlation equation is used to reflect the correlation pattern between the spatial risk situation value sequence and the risk spatial correlation degree sequence.

[0057] It is understandable that the mapping relationship between two spatial risk situation value sequences and risk spatial correlation sequences can be modeled using correlation equations. Specifically, this model determines whether the risk situation change trend of a spatial grid has a measurable functional relationship with its spatial risk transmission intensity. The spatial risk situation value sequence represents the dynamic evolution of risks within a region, while the risk spatial correlation sequence represents the spatial input influence of external risks. This helps to understand whether a spatial grid is an "internal-dominant risk zone" or a "spatial-driven risk zone," thus providing key indicators for subsequent risk coupling judgment and matching of regional governance strategies. Linear, quadratic curve, exponential, logistic regression, and support vector regression models can be applied to the spatial risk situation value sequence and risk spatial correlation sequence. The fitting function is determined based on the best fit (e.g., R², sum of squared residuals). For regions with prominent nonlinear relationships, deep fitting methods such as BP neural networks and LSTM can be introduced to uncover implicit multi-order relationships. If the fitting results are stable and the residuals are small, it indicates that the spatial risk situation of the grid has obvious spatial coupling response. A set of computable correlation function expressions are output for each spatial grid, including function form, fitting parameters, significance index, etc., which serve as an important mathematical basis for subsequent region selection and model evaluation.

[0058] Optionally, S220, the spatial risk situation value sequence and risk spatial correlation sequence corresponding to each spatial grid are analyzed to obtain the correlation equation between the spatial risk situation value sequence and the risk spatial correlation sequence corresponding to each spatial grid, including:

[0059] S221, perform nonlinear correlation calculations on the spatial risk situation value sequence and risk spatial correlation degree sequence corresponding to each spatial grid to obtain the correlation equation between the spatial risk situation value sequence and risk spatial correlation degree sequence corresponding to each spatial grid.

[0060] It is understandable that nonlinear correlation calculation refers to using statistical measures or modeling methods with nonlinear mapping capabilities, such as the maximum information coefficient (MIC), mutual information, kernel correlation coefficient (HSIC), Granger causality nonlinearity test, etc., to deeply mine the relationship between two sets of time series data. This can reveal phenomena such as delayed response, sudden covariance, and local high-intensity resonance, significantly outperforming linear indices such as Pearson. The spatial risk situation value sequences and risk spatial correlation sequences of each spatial grid can be preprocessed uniformly (normalization, smoothing, time alignment), and then nonlinear index calculations can be performed in parallel to output a correlation score matrix. Then, significant relationship pairs are selected based on the scores, and specific function expressions are generated through spline regression, support vector regression, or tree model fitting, forming a nonlinear correlation equation. The nonlinear correlation equation can not only be used to determine whether a grid belongs to a complex coupling mode region, but also to construct a risk response simulator to predict responses to specific external input risks, thereby assessing its resilience and vulnerability to internal situational evolution, significantly improving identification capabilities, and the ability to discover hidden risk linkages, sudden impact areas, and complex vulnerable areas, providing support for advanced situational awareness.

[0061] S230, based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, multiple grid areas with risk coupling effect are obtained and used as risk areas to be investigated.

[0062] Understandably, we can analyze the correlation equations corresponding to each spatial grid, examining their function structure, fitting effect, nonlinear characteristics, and other parameters to determine whether there are coupling relationships with a risk amplification trend. Judgment criteria can include: the equations are nonlinearly ascending (e.g., parabolic curves opening upwards), the correlation strength is higher than a threshold, and the dependent variable elasticity coefficient is significantly greater than 1. Furthermore, trend stability indicators (e.g., sliding window fitting consistency) and response time delay parameters can be introduced to determine whether they constitute easily propagated regions. Finally, spatial grids that meet these coupling conditions are extracted as "risk areas to be investigated," achieving effective convergence from comprehensive identification to targeted intervention, improving resource allocation efficiency and the accuracy of risk intervention.

[0063] Optionally, S230, based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, multiple grid regions with risk coupling effects are obtained and designated as risk regions to be investigated, including:

[0064] S231, based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, the grid area corresponding to the spatial grid whose correlation equation is a quadratic curve equation is selected as the risk area to be investigated.

[0065] It is understandable that in the risk evolution mechanism, the structure of the quadratic curve equation implies that the change in risk status value exhibits a nonlinear accelerating trend against the backdrop of increasing spatial correlation, i.e., there is a significant risk amplification or attenuation effect, depending on the sign of the quadratic coefficient. The correlation function equations of all grids can be uniformly converted into the standard polynomial expression ax² + bx + c, identifying functions that conform to the quadratic structure. Subsequently, the sign and absolute value of the quadratic coefficient (a) are analyzed to determine the response mechanism represented by the quadratic function. Generally, if a > 0, it indicates that the risk status increases at an accelerated rate with increasing correlation, belonging to a typical linkage amplification zone; if a < 0, it indicates the possible existence of spatial self-inhibition or negative feedback mechanisms. By setting a reasonable threshold (e.g., |a| > 0.1), grid regions with nonlinear amplification mechanisms can be accurately extracted. Spatial grids are marked as areas of significant structural coupling, added to the list of risk areas to be investigated, and presented on the visualization interface with highlights and borders, prioritizing their handling and allocating resources, providing an efficient means for the nonlinear discovery and rapid location of complex risks.

[0066] Optionally, S230, based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, multiple grid regions with risk coupling effects are obtained and designated as risk regions to be investigated, including:

[0067] S232, the significance of the correlation equations corresponding to each spatial grid is verified to obtain the reliability coefficients corresponding to each spatial grid.

[0068] It is understandable that statistical significance tests can be performed on the correlation equations to ensure that the adopted risk coupling judgments possess mathematical rationality and practical stability. Statistical indicators such as fit residuals, mean squared error, goodness of fit (R²), and p-values ​​can be calculated for the correlation equations of each spatial grid. The p-value is used to test whether there is a statistically significant correlation between the dependent variable (risk situation value) and the independent variable (spatial correlation), generally with a threshold of p < 0.05. Goodness of fit is used to assess whether the overall model's explanatory power is sufficient. Based on these statistical indicators, a "reliability coefficient" can be defined for each correlation equation. This coefficient can be achieved by using a linear weighting method to fuse the indicators, or by using machine learning methods (such as random forest regression) to output a confidence score. The reliability coefficient helps in subsequent classification of candidate risk areas; for example, high-reliability areas can be prioritized for intervention, while areas with insufficient reliability can be temporarily deferred or require supplementary data. Ultimately, this step improves the model's explanatory power and acceptability, constructing a credibility defense line in the risk assessment system and ensuring the scientific nature and stability of subsequent strategy formulation.

[0069] S233, based on reliability coefficient and correlation equation, the grid area corresponding to the spatial grid where the coefficient of the quadratic term of the correlation equation is negative and the reliability coefficient is greater than the preset critical value is regarded as the risk area to be investigated.

[0070] It is understandable that the mathematical characteristics of the correlation equation and the reliability verification results can be combined to achieve dual verification of risk areas. The correlation equation describes the quantitative relationship between a certain indicator and various influencing factors within a spatial grid. The sign of the quadratic coefficient has a clear physical meaning—when the quadratic coefficient is negative, it indicates that there is a nonlinear relationship between the influencing factors and the safety indicator within the spatial grid, with diminishing marginal effects or even inverse effects. That is, as the relevant factors change, the safety status may show a deteriorating trend (such as a sudden increase in risk after a certain parameter exceeds a threshold), which is an important mathematical signal for identifying potential risks. The reliability coefficient is used to measure the goodness of fit or predictive credibility of the correlation equation. Only when the reliability coefficient is greater than a preset critical value can it be said that the relationship reflected by the correlation equation is statistically significant, avoiding misjudgments caused by data noise or accidental correlations. Using a negative quadratic coefficient and a reliability coefficient greater than a preset critical value as joint screening conditions can simultaneously take into account the mathematical characteristics of risk and the reliability of the model. The quadratic coefficient identifies grids that may have a risk deterioration trend based on inherent laws, while the reliability coefficient ensures from a statistical validity perspective that this trend is not a spurious correlation. The dual screening mechanism of quadratic coefficient and reliability coefficient not only ensures the sensitivity of risk identification but also avoids over-warning, providing accurate and reliable target areas for subsequent risk investigation and control, and improving the efficiency and pertinence of risk prevention.

[0071] S300 retrieves refined geographic monitoring data and regional response data corresponding to each risk area to be investigated from a multi-source geographic information database.

[0072] It is understandable that refined geographic monitoring data can include: high-definition video images, drone aerial photography data, traffic flow information, population trajectory heatmaps, and real-time sensor data (such as PM2.5, noise, and light). Regional response data can include information from public channels, third-party monitoring, and related records, representing a collection of information reflecting the risk situation and emergencies within the grid area. By integrating with multi-source databases, such as retrieving micro-grid data from the city's operational brain, smart city IoT platform, and urban operation integrated platform, a unified data extraction interface can be constructed. Coordinate matching and data layering extraction can be performed according to the ID of the area to be investigated. Refined geographic monitoring data and regional response data corresponding to each risk area to be investigated can be retrieved from multi-source geographic information databases, enabling real-time and refined enhanced perception of the risk areas to be investigated. This supports subsequent information instance identification and empowers situational analysis.

[0073] S400 analyzes the refined geographic monitoring data and regional response data of each risk area to be investigated, and identifies specific impact information instances contained in each risk area to be investigated; among them, specific impact information instances are information instances in which the rate of change of information flow exceeds a threshold within a preset continuous time period.

[0074] Understandably, refined geographic monitoring data and regional response data can be used to accurately identify key information instances that may significantly impact regional operational order or residents' perceptions, and to label their location, scope, intensity, theme, and other elements. For example, an event recognition model can be pre-built, integrating algorithms such as text semantic analysis, time series clustering, and spatial hotspot detection, enabling real-time parsing of unstructured data in the area under investigation. Through event aggregation models, multi-dimensional manifestations of the same event can be identified and correlated with geographic monitoring data within the region (such as crowd gatherings, vehicle anomalies, and increased noise) for verification, thereby eliminating false judgments and improving recognition accuracy. Specific impact information instances are those where the rate of change in information flow exceeds a threshold within a preset continuous time period. These can be graded based on information flow indices and flow breadth, extracting the risky portions as specific impact information instances, significantly improving the region's dynamic perception capabilities and response timeliness.

[0075] In one possible implementation, the regional response data includes at least one information instance; S400, the refined geographic monitoring data and regional response data of each risk area to be investigated are analyzed to identify specific impact information instances contained in each risk area to be investigated, including:

[0076] S410, Perform data flow analysis on each information instance in each risk area to be investigated, and determine the data flow coefficient of each information instance in the second monitoring period; wherein, the data flow coefficient is used to reflect the degree of flow of information instances in the second monitoring period.

[0077] It is understandable that in each spatial grid containing regional response data, the regional response data includes at least one information instance. An information instance refers to a specific set of information related to a geographical feature, regional activity, or event of the risk area to be investigated, formed through various information channels within a specific time period. For each identified information instance, its activity level in various information channels can be assessed to quantify the intensity and scope of information flow in the short term, i.e., the output is a data flow coefficient. A data flow assessment framework can be constructed, consisting of modules such as indicator system construction, entropy weighting, and comprehensive coefficient calculation. The relevant text and metadata of each instance can be collected and merged to extract core indicators such as the number of flows and the growth rate per unit time, forming an assessment indicator set. The entropy weighting method is then used to objectively assign weights to these indicators, determining their weights by calculating the information entropy of each indicator.

[0078] For example, when using the entropy weight method, the j-th indicator of the i-th instance can be processed using the range standardization formula: when the indicator is a positive indicator, When the indicator is negative, ,in The original index value, , The first The maximum and minimum values ​​of the indicator. The value is the standardized value (range 0-1). Calculate the information entropy of the j-th indicator: ,in ,in, The total number of information instances, -6 is a correction term to avoid errors in logarithmic operations. Calculate the... Weight of each indicator: ,in For the total number of indicators, For the first Entropy weight of the item index (satisfying) The smaller the information entropy, the better. The smaller the value, the greater the difference between different instances of the indicator, and the more effective information it carries. The weight ( The higher the corresponding value, the better, thus avoiding bias caused by subjective weighting. Simultaneously, the standardized formula described above transforms each indicator into a standardized value between 0 and 1. The data flow coefficient is obtained by multiplying each standardized value by its corresponding entropy weight and then summing the results. A higher data flow coefficient indicates a stronger level of activity of information instances within the monitoring period.

[0079] S420, based on the data flow coefficient and the refined geographic monitoring data of each risk area to be investigated, determine the geographic impact index of each information instance in the second monitoring period; wherein, the geographic impact index is used to reflect the theoretical intensity of the effect of the information instance on a specific geographic area in the second monitoring period.

[0080] It is understandable that the calculation of the Geographic Impact Index (GPI) is the result of coupled analysis of the data flow coefficient and refined geographic monitoring data. The GPI reflects the theoretical strength of the impact of information instances on a specific geographic area within the second monitoring period. The second monitoring period is a pre-defined continuous future time period. Refined geographic monitoring data may include regional population density, population flow characteristics (such as average daily passenger flow and peak-hour flow rate), functional attribute weights (such as commercial areas with a weight of 1.2, residential areas with a weight of 1.0, and industrial areas with a weight of 0.8), and the distribution of sensitive locations (such as schools and hospitals, which are given additional weighting coefficients). The geographic data can first be standardized to the 0-1 interval, and then the entropy weight method can be used to obtain the GPI. Then, the data flow coefficient and the GPI can be integrated using a product formula. The specific formula is as follows: Geographic Impact Index = Data Flow Coefficient × Geographic Impact Coefficient × Regional Risk Baseline Value (reflecting the inherent vulnerability of the region). For example, an instance with a data flow coefficient of 0.8 will have a significantly higher geographic influence index in a commercial area with a population density of 0.9 (after standardization) and a functional attribute weight of 1.2 than an equivalent information instance in an industrial area with a population density of 0.3 and a functional attribute weight of 0.8. This quantifies the difference in the theoretical impact of information instances on a specific geographic area.

[0081] S430: Based on the geographic impact index, the information instances of each risk area to be investigated are initially screened to determine the candidate information instance set of each risk area to be investigated.

[0082] It is understandable that the initial screening process based on the geographic impact index (GPI) aims to focus on potentially high-impact information instances through dynamic thresholds or relative ranking. Differentiated screening rules can be set for different types of risk areas to be investigated. For core grid areas, an absolute threshold of an index value ≥ 1.5 times the regional mean can be used, while for other grids, a relative threshold based on percentages can be used. For example, if there are 20 information instances in a region to be investigated, with GPIs ranging from 0.1 to 0.9, information instances with an index ≥ 0.6 (assuming a regional mean of 0.4) can be selected to form a candidate set. This retains instances with significant impact while avoiding insufficient regional adaptability due to fixed thresholds, laying the foundation for subsequent refined screening.

[0083] S440, calculate the flow change rate for each candidate information instance in the candidate information instance set to determine the specific impact information instances contained in each risk area to be investigated.

[0084] Understandably, the data flow coefficient and geographic influence index of each candidate information instance can be sampled continuously over multiple periods to form a time series curve. Then, sliding window techniques are used to calculate the growth slope, amplitude, and persistence of each week. Simultaneously, exponential smoothing (such as Holt-Winters) or trend decomposition models (such as STL) are introduced to remove the seasonal and trend components of the information instance and extract its true flow change rate. A specific impact information instance is one whose flow change rate exceeds a threshold within a preset continuous time period. The flow change rate is dynamic trend data used to determine the influence of an information instance by tracking changes in the geographic influence index of the candidate information instance within a continuous time period. The specific formula for calculating the flow change rate is: Flow Change Rate = (Current Time Period Geographic Influence Index - Previous Time Period Geographic Influence Index) / Previous Time Period Geographic Influence Index × 100%. The time period can be preset according to the flow speed or the type of information instance, such as 1 hour or 6 hours per period. By calculating the flow change rate over multiple consecutive time periods, it is clear whether the information instance is in a state of increasing, decreasing, or stable influence. For example, if the flow change rate of a candidate instance is 30%, 25%, and 20% in three consecutive time periods, it indicates that its influence is continuously increasing and the growth rate is relatively stable; if the change rate is -10%, -15%, and -8%, it indicates that the influence is weakening. When determining specific impact information instances, instances with a consistently positive flow change rate and an average change rate exceeding a preset value (such as 15%) will be selected as specific impact information instances to achieve cross-platform early warning sharing, data visualization, and response decision guidance.

[0085] S500: Based on specific impact information instances of the risk area to be investigated, determine the risk management plan for those specific impact information instances.

[0086] It is understandable that identified specific impact information instances can be further transformed into specific intervention response measures to achieve proactive risk response and intelligent recommendation of intervention strategies. Specific impact information instances refer to specific information units that have significant effects and importance within a specific geographical area, reflecting the dynamic and changing characteristics of the risk situation in that area. Specific elements of specific impact information instances can be used as input into a pre-trained risk management solution model. The risk management solution model can be constructed using supervised learning methods, with the training dataset derived from a historical information instance case library, including information instance background features (time, space, type), information instance flow indicators, region, and corresponding optimal response action labels. During the training phase, decision tree-based ensemble learning methods (such as XGBoost and RandomForest) can be used to handle non-linear data mapping, or the Transformer structure from deep learning can be integrated to extract instance semantic context and flow dynamic features, and generate multi-level response suggestions. The risk management solution model outputs not only a "response or not" judgment, but also details the response level (such as Level I proactive guidance, Level II enhanced data monitoring, and Level III collaborative resource intervention), response path suggestions, and other dimensions. It also automatically matches available resource units, realizing the transformation of risk management response from "expert experience-driven" to "data model-driven". This significantly improves the systematicness, foresight, and adaptability of emergency response, enabling regional risk management agencies to deal with various types and complex information instances more efficiently and reduce the probability of potential risks.

[0087] In one possible implementation, S500 determines a risk management plan for a specific impact information instance based on that instance of impact information for the risk area to be investigated, including:

[0088] S510, based on the specific impact information instance of the risk area to be investigated, input into the preset risk management solution model to obtain the risk management solution for the specific impact information instance; wherein, the risk management solution model is a machine learning model that has been pre-trained.

[0089] It is understandable that specific impact information instances identified within the risk area to be investigated can be used as input. A pre-trained risk management solution model generates specific management recommendations best suited to the current situation and regional characteristics of that information instance. In other words, the risk management solution is a specific risk management recommendation generated by the risk management solution model for the input specific impact information instance. The input to the risk management solution model may include: the current activity value of the information instance, the activity change rate of the information instance, the expansion change curve of the information instance, etc.; the output is a set of risk management recommendation parameters, and the set of output risk management recommendation parameters is the risk management solution. Risk management solution models can be implemented based on the Transformer architecture, jointly encoding structured information of instances with unstructured text (such as instance content summaries) to generate high-dimensional embedded representations, and then outputting recommended strategies by the response generator. Alternatively, graph neural networks (GNNs) can be used to process the propagation graph structure between instances and geographic grids, improving the robustness of instance-region coupled response suggestions, completing the transformation of information instances into strategies, promoting multi-dimensional collaborative responses in the region, and realizing early warning, prediction, prevention, and management of risk factors through technological means, thereby improving risk prevention capabilities and providing a clear picture of the security situation. This provides strong support for formulating precise prevention measures and weaves a comprehensive security and prevention network by combining elements of people, places, events, things, and organizations.

[0090] For example, a training sample set containing historically specific impact information instances can be prepared. The training data can originate from multiple regional information instances, as well as the content of risk management plans for these instances, and effect feedback reports. The training samples use information instances, or the current activity value of information instances, the activity change rate of information instances, and the expansion change curve of information instances, as input samples, and the content of risk management plans for information instances and effect feedback reports as output samples. Each training sample contains structured and unstructured information. Structured information includes the grid number of the instance's occurrence area, instance category label, timestamp, data flow curve, and instance impact index; unstructured information includes instance text descriptions and content samples. The training process first standardizes the structured data, including normalized timestamps, standardized numerical indicators, and category label encoding, to ensure the uniformity and effectiveness of the model input. Simultaneously, natural language processing techniques are used to segment, denoise, and semantically vectorize the unstructured text information, generating high-dimensional semantic embeddings. Next, a supervised learning algorithm is used to train the model on the training samples, optimizing model performance through cross-validation and hyperparameter tuning. For Transformer-based models, the focus is on training their contextual understanding and dynamic feature capture capabilities; for graph neural network-based models, the emphasis is on learning the relationship between instances and region grids to improve spatial relevance representation. After training, the models are evaluated using independent test sets, employing multiple metrics such as accuracy, recall, and F1 score to comprehensively measure their performance in practical applications. This ensures that the models can accurately predict specific impact information instances and corresponding handling strategies, ultimately achieving intelligent auxiliary support for regional risk management methods.

[0091] Corresponding to the risk prevention and handling method based on map data fusion in the above embodiments, this application also provides a risk prevention and handling system based on map data fusion, wherein each unit of the system can implement each step of the risk prevention and handling method based on map data fusion. Figure 3 The diagram shows a structural block diagram of a risk prevention and control system based on map data fusion provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0092] Reference Figure 3 This risk prevention and handling system based on map data fusion includes:

[0093] The acquisition unit is used to acquire multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database.

[0094] The analysis unit is used to analyze the multi-dimensional geographic attribute data corresponding to each of the spatial grids to obtain multiple grid areas with risk coupling effects and to identify them as risk areas to be investigated; wherein, the grid area is the geographic area corresponding to a single spatial grid.

[0095] The retrieval unit is used to retrieve the refined geographic monitoring data and regional response data corresponding to each of the risk areas to be investigated from the multi-source geographic information database.

[0096] The identification unit is used to analyze the refined geographic monitoring data and regional response data of each of the risk areas to be investigated, and to identify specific impact information instances contained in each of the risk areas to be investigated; wherein, the specific impact information instance is an information instance in which the rate of change of information flow exceeds a threshold within a continuous time period.

[0097] The handling unit is used to determine a risk handling plan for the specific impact information instance based on the specific impact information instance of the risk area to be investigated.

[0098] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] This application also provides an electronic device. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 4 Only one is shown in the image), at least one memory 61 ( Figure 4(Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it causes the electronic device 6 to implement the steps in any of the above-described embodiments of the risk prevention and handling methods based on map data fusion, or causes the electronic device 6 to implement the functions of each unit in the above-described system embodiments.

[0101] For example, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the electronic device 6.

[0102] The electronic device can be of various types of intelligent monitoring devices. This electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0103] The processor 60 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0104] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may be an external storage device of the electronic device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 6. Furthermore, the memory 61 may include both internal and external storage units of the electronic device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0105] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0106] This application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the steps in any of the above method embodiments.

[0107] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0108] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0109] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0110] In the embodiments provided in this application, it should be understood that the disclosed risk prevention and handling system / electronic device and method based on map data fusion can be implemented in other ways. For example, the embodiments of the risk prevention and handling system / electronic device based on map data fusion described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0111] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A risk prevention and mitigation method based on map data fusion, characterized in that, include: Obtain multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database; The multi-dimensional geographic attribute data corresponding to each of the spatial grids are analyzed to obtain multiple grid areas with risk coupling effects, which are then identified as risk areas to be investigated; wherein, each grid area is a geographic area corresponding to a single spatial grid. Retrieve refined geographic monitoring data and regional response data corresponding to each of the risk areas to be investigated from the multi-source geographic information database; The refined geographic monitoring data and regional response data of each of the risk areas to be investigated are analyzed to identify specific impact information instances contained in each of the risk areas to be investigated; wherein, the specific impact information instance is an information instance in which the rate of change of information flow exceeds a threshold within a preset continuous time period. Based on specific impact information instances of the risk area to be investigated, determine the risk management plan for the specific impact information instances; The analysis of the multi-dimensional geographic attribute data corresponding to each of the spatial grids yields multiple grid areas with risk coupling effects, which are then designated as risk areas to be investigated. Based on the multi-dimensional geographic attribute data corresponding to each spatial grid, the spatial risk situation value sequence and risk spatial correlation sequence corresponding to each spatial grid in the first monitoring period are determined; wherein, the spatial risk situation value sequence is used to reflect the evolution law of the risk level of a single spatial grid in the first monitoring period; the risk spatial correlation sequence is used to reflect the mutual influence intensity and transmission law of risk elements between different spatial grids; The spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid are analyzed to obtain the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid; wherein, the correlation equation is used to reflect the correlation pattern between the spatial risk situation value sequence and the risk spatial correlation degree sequence. Based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, multiple grid regions with risk coupling effect are obtained and used as risk regions to be investigated. Based on the multi-dimensional geographic attribute data corresponding to each spatial grid, determine the spatial risk situation value sequence corresponding to each spatial grid within the first monitoring period, including: The multi-dimensional geographic attribute data corresponding to each of the spatial grids are first analyzed to obtain the dynamic risk value sequence of various risk points contained in each spatial grid within the first monitoring period; wherein, the dynamic risk value sequence is used to reflect the real-time status change trend of a single risk point within a specific spatial grid within the first monitoring period. Based on the dynamic risk value sequence of various risk points contained in each spatial grid, calculate the spatial risk situation value sequence corresponding to each spatial grid in the first monitoring period; The step of determining the spatial risk status value sequence and risk spatial correlation sequence corresponding to each spatial grid within the first monitoring period based on the multi-dimensional geographic attribute data corresponding to each spatial grid includes: A second analysis is performed on the multi-dimensional geographic attribute data corresponding to each spatial grid to determine the spatial distribution information of risk points within each spatial grid; wherein, the spatial distribution information is used to reflect the spatial distribution pattern of risk points within the spatial grid; Based on the spatial distribution information of risk points within each spatial grid and the dynamic risk value sequence of various risk points in the first monitoring period, the spatial correlation sequence of risk points for each spatial grid in the first monitoring period is calculated.

2. The risk prevention and handling method based on map data fusion as described in claim 1, characterized in that, The analysis of the spatial risk situation value sequence and the risk spatial correlation sequence corresponding to each spatial grid to obtain the correlation equation between the spatial risk situation value sequence and the risk spatial correlation sequence corresponding to each spatial grid includes: Nonlinear correlation degree calculations are performed on the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid to obtain the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid.

3. The risk prevention and handling method based on map data fusion as described in claim 1, characterized in that, The correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each of the spatial grids is used to obtain multiple grid regions with risk coupling effects, which are then identified as risk regions to be investigated, including: Based on the correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each spatial grid, the grid area corresponding to the spatial grid whose correlation equation is a quadratic curve equation is selected as the risk area to be investigated.

4. The risk prevention and handling method based on map data fusion as described in claim 1, characterized in that, The correlation equation between the spatial risk situation value sequence and the risk spatial correlation degree sequence corresponding to each of the spatial grids is used to obtain multiple grid regions with risk coupling effects, which are then identified as risk regions to be investigated, including: The significance of the correlation equations corresponding to each of the spatial grids is verified to obtain the reliability coefficients corresponding to each of the spatial grids. Based on the reliability coefficient and the correlation equation, the grid regions corresponding to the spatial grids where the coefficient of the quadratic term of the correlation equation is negative and the reliability coefficient is greater than a preset critical value are selected as the risk regions to be investigated.

5. The risk prevention and handling method based on map data fusion as described in claim 1, characterized in that, The regional response data includes at least one information instance; The analysis of the refined geographic monitoring data and regional response data of each of the aforementioned risk areas to be investigated identifies specific impact information instances contained in each of the aforementioned risk areas to be investigated, including: For each of the information instances in each of the aforementioned risk areas to be investigated, data flow analysis is performed to determine the data flow coefficient of each information instance within the second monitoring period; wherein, the data flow coefficient is used to reflect the degree of flow of the information instance within the second monitoring period; Based on the data flow coefficient and the refined geographic monitoring data of each of the risk areas to be investigated, the geographic impact index of each information instance in the second monitoring period is determined; wherein, the geographic impact index is used to reflect the theoretical intensity of the effect of the information instance on a specific geographic area in the second monitoring period; Based on the geographical impact index, the information instances of each of the risk areas to be investigated are initially screened to determine the candidate information instance set of each of the risk areas to be investigated. For each candidate information instance in the candidate information instance set, the flow change rate is calculated to determine the specific impact information instances contained in each of the risk areas to be investigated.

6. The risk prevention and handling method based on map data fusion as described in claim 1, characterized in that, The step of determining a risk management plan for a specific impact information instance based on a specific impact information instance of the risk area to be investigated includes: The specific impact information instance of the risk area to be investigated is input into a preset risk management solution model to obtain a risk management solution for the specific impact information instance; wherein, the risk management solution model is a pre-trained machine learning model.

7. A risk prevention and handling system based on map data fusion, characterized in that, For implementing the method according to any one of claims 1 to 6, the risk prevention and handling system based on map data fusion comprises: The acquisition unit is used to acquire multi-dimensional geographic attribute data corresponding to each preset spatial grid from a preset multi-source geographic information database. The analysis unit is used to analyze the multi-dimensional geographic attribute data corresponding to each of the spatial grids to obtain multiple grid areas with risk coupling effects and to identify them as risk areas to be investigated; wherein, the grid area is the geographic area corresponding to a single spatial grid. The retrieval unit is used to retrieve the refined geographic monitoring data and regional response data corresponding to each of the risk areas to be investigated from the multi-source geographic information database. The identification unit is used to analyze the refined geographic monitoring data and regional response data of each of the risk areas to be investigated, and to identify specific impact information instances contained in each of the risk areas to be investigated; wherein, the specific impact information instance is an information instance in which the rate of change of information flow exceeds a threshold within a preset continuous time period. The handling unit is used to determine a risk handling plan for the specific impact information instance based on the specific impact information instance of the risk area to be investigated.

Images