Urban disaster emergency management overall circle identification method, terminal and storage medium

Abstract

The invention discloses an urban disaster emergency management overall circle identification method, a terminal and a storage medium, and the method comprises the steps: obtaining mobile phone signaling data, and recognizing the main residence of residents before and during a disaster according to the mobile phone signaling data; according to the change characteristics of the main residences of the residents before the disaster and during the disaster, drawing residence change OD, and performing clustering analysis on the residence change OD to obtain resident residence change OD clusters; overlapping the boundary of the residential place change OD cluster with a community administrative boundary to determine a disaster prevention overall circle, and visually displaying the disaster prevention overall circle; the invention provides a new disaster emergency management overall planning district division method, the configuration of disaster prevention resources is optimized, and the evacuation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of new generation information technology, and in particular to a method, terminal and storage medium for identifying a city disaster emergency management coordination circle. Background Art

[0002] With the acceleration of urbanization, the risk of rain and flood disasters faced by cities is increasing. Effective disaster management and evacuation planning are of great significance to reducing the impact of disasters and protecting the lives and property of residents.

[0003] Existing disaster management and evacuation planning are mainly based on geographical features and administrative boundaries, with little consideration of the actual evacuation behavior of residents during disasters. It is also unable to effectively aggregate areas with close evacuation ties, thus affecting the accuracy and practicality of disaster prevention zoning.

[0004] Therefore, the prior art needs to be improved. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the defects of the existing technology, the present invention provides a method, terminal and storage medium for identifying an urban disaster emergency management coordination circle to solve the technical problem that the existing disaster emergency management coordination area division is difficult to reflect the rules of residents' evacuation.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0007] In a first aspect, the present invention provides a method for identifying a city disaster emergency management coordination circle, comprising:

[0008] Obtaining mobile phone signaling data and identifying the primary place of residence of residents before and during the disaster based on the mobile phone signaling data;

[0009] Describing the residence change OD according to the change characteristics of the main residence of the residents before and during the disaster, performing cluster analysis on the residence change OD to obtain the residence change OD clusters of the residents;

[0010] The boundaries of the residential change OD cluster are overlapped with the community administrative boundaries to determine the disaster prevention coordination circle, and the disaster prevention coordination circle is visualized.

[0011] In one implementation, obtaining mobile phone signaling data and identifying the main places of residence of residents before and during a disaster based on the mobile phone signaling data includes:

[0012] Acquire the mobile phone signaling data, and pre-process the mobile phone signaling data;

[0013] According to the probability of the user coordinates appearing in the mobile phone signaling data, the main activity areas in the preset time period one week before the disaster and during the disaster are calculated by a density-based clustering algorithm;

[0014] The main activity areas are divided into activity site categories by using a K-means clustering algorithm, and the main residences of the residents before and during the disaster are identified from the activity site categories.

[0015] In one implementation, the preprocessing of the mobile phone signaling data includes:

[0016] Acquiring population distribution data with geographic coordinates according to the mobile phone signaling data;

[0017] The format of the population distribution data is unified, and the device information without a tag ID is deleted to obtain the location coordinate data;

[0018] The position coordinate data whose positioning frequency is lower than a preset threshold is deleted to obtain pre-processed mobile phone signaling data.

[0019] In one implementation, describing the residence change OD according to the change characteristics of the main residence of the residents before and during the disaster, performing cluster analysis on the residence change OD to obtain the residence change OD cluster of the residents includes:

[0020] Divide the urban area into grids, and overlap the grids with the main residences of the residents before and during the disaster to obtain the grids where the residents' residences before the disaster are located and the grids where the residents' residences during the disaster are located;

[0021] Describe the change OD of the residence according to the change track of the grid where the residence was located before the disaster and the grid where the residence was located during the disaster;

[0022] The residence change OD is clustered to obtain the residence change OD cluster.

[0023] In one implementation, the overlapping of the boundary of the residential change OD cluster with the community administrative boundary to determine the disaster prevention coordination circle, and visually displaying the disaster prevention coordination circle, includes:

[0024] Clustering the residential change OD clusters by a density-based clustering algorithm, and grouping the residential change OD clusters according to the clustering results to obtain evacuation OD clusters;

[0025] The boundary of the evacuation OD cluster is depicted by a convex hull algorithm, and the boundary of the evacuation OD cluster is coupled with the community administrative boundary by using geographic information software to obtain the disaster prevention coordination circle;

[0026] The disaster prevention coordination circle is visualized through the geographic information software.

[0027] In one implementation, clustering the residential change OD clusters by a density-based clustering algorithm, and grouping the residential change OD clusters according to the clustering results to obtain evacuation OD clusters includes:

[0028] Based on the density-based clustering algorithm, clustering the residential change OD clusters according to a preset neighborhood radius and a minimum number of points;

[0029] According to the clustering result, the high-density areas are clustered to obtain the evacuated OD cluster;

[0030] According to the clustering result, isolated points in the low-density area are marked as noise points, and the noise points are deleted.

[0031] In one implementation, the step of delineating the boundary of the dispersed OD cluster by using a convex hull algorithm includes:

[0032] The convex hull of the sparse OD cluster is constructed by the convex hull algorithm, and the convex hull vertices of each cluster are connected to form a closed polygon to obtain the boundary of the sparse OD cluster.

[0033] In one implementation, the geographic information software is used to couple the boundary of the evacuation OD cluster with the community administrative boundary to obtain the disaster prevention coordination circle, including:

[0034] Generating a spatial segmentation map based on the community center point in the geographic information software according to the community center point;

[0035] The space segmentation map based on the community center point is superimposed with the boundary of the evacuation OD cluster, and the disaster prevention coordination circle is determined according to the superimposed area.

[0036] In a second aspect, the present invention further provides a terminal, comprising: a processor and a memory, wherein the memory stores a city disaster emergency management coordination circle identification program, and when the city disaster emergency management coordination circle identification program is executed by the processor, it is used to implement the operation of the city disaster emergency management coordination circle identification method as described in the first aspect.

[0037] In a third aspect, the present invention further provides a computer-readable storage medium, which stores a city disaster emergency management coordination circle identification program, and when the city disaster emergency management coordination circle identification program is executed by a processor, it is used to implement the operation of the city disaster emergency management coordination circle identification method as described in the first aspect.

[0038] The present invention adopts the above technical solution to achieve the following effects:

[0039] The present invention obtains mobile phone signaling data and identifies the main residences of residents before and during disasters according to the mobile phone signaling data; describes the change OD of the residence according to the change characteristics of the main residences of residents before and during disasters, which can more accurately reflect the actual evacuation behavior of the crowd when a disaster occurs, and provides more accurate data support for disaster prevention zoning. By clustering the change OD of the residence, the change OD cluster of the residents' residence can be obtained, which can effectively aggregate the areas with close evacuation associations to form a more reasonable disaster prevention coordination area; the boundaries of the change OD cluster of the residence are overlapped with the administrative boundaries of the community to form a disaster prevention coordination circle with practical guiding significance, and the disaster prevention coordination circle is visualized to reflect the self-organized evacuation mode of the residents in the case of disasters, provide a reference for formulating evacuation strategies, and form a disaster prevention area division guide; the present invention proposes a new method for disaster emergency management coordinated area division, which not only takes into account the actual evacuation behavior of the residents, but also takes into account the convenience of administrative management, so that the disaster prevention zoning is more scientific and reasonable, which is helpful to optimize the allocation of disaster prevention resources and improve evacuation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of a method for identifying a city disaster emergency management coordination circle in one implementation of the present invention.

[0042] Figure 2 It is a functional principle diagram of a terminal in one implementation of the present invention.

[0043] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] The present invention provides a method, terminal and storage medium for identifying a city disaster emergency management coordination circle. In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] Exemplary Methods

[0046] With the acceleration of urbanization, the risk of rain and flood disasters faced by cities is increasing. Effective disaster management and evacuation planning are of great significance to reducing the impact of disasters and protecting the lives and property of residents. However, the existing disaster management and evacuation planning is mainly based on the characteristics of geographical elements and administrative boundaries, and rarely considers the actual evacuation behavior of residents during disasters. It is also impossible to effectively aggregate areas with close evacuation connections, thus affecting the accuracy and practicality of disaster prevention zoning.

[0047] In response to the above technical problems, an embodiment of the present invention provides a method for identifying an urban disaster emergency management coordination circle, with the aim of proposing a new method for dividing disaster emergency management coordination areas, optimizing the allocation of disaster prevention resources, and improving evacuation efficiency.

[0048] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying a city disaster emergency management coordination circle, comprising the following steps:

[0049] Step S100, obtaining mobile phone signaling data, and identifying the main residence of residents before and during the disaster based on the mobile phone signaling data.

[0050] In this embodiment, the urban disaster emergency management coordination circle identification method is applied to a terminal, and the terminal includes but is not limited to: computers, mobile terminals and other devices.

[0051] In this embodiment, a method for identifying the coordinated circle of urban disaster emergency management based on mobile phone signaling is proposed. By analyzing the population activities and mobility characteristics before and during the disaster, refined evacuation planning and disaster prevention area division are realized. First, by analyzing the mobile phone signaling data, the main activity areas of residents before and during the disaster are identified, including residential areas, work areas, etc., which helps to understand the daily activity patterns of residents and behavioral changes when disasters occur, and provide a basis for evacuation planning. Then, based on the mobile phone signaling data, the OD of the living place changes of residents before and during the disaster is tracked. The evacuation coordinated area is depicted by the community discovery algorithm, and the naturally formed evacuation coordinated area is identified according to the evacuation and migration behavior of the residents. These coordinated areas reflect the self-organized evacuation mode of residents in disaster situations, providing a reference for the formulation of evacuation strategies. Finally, the identified evacuation coordinated area is coupled with the existing community boundaries to form a disaster prevention area division guide, which helps to optimize the allocation of disaster prevention resources and improve evacuation efficiency.

[0052] Specifically, in an implementation of this embodiment, step S100 includes the following steps:

[0053] Step S110, obtaining the mobile phone signaling data, and preprocessing the mobile phone signaling data.

[0054] In this embodiment, the mobile phone signaling spatiotemporal activity data is preprocessed. By cleaning and filtering, invalid and abnormal data are eliminated, the data quality can be improved and the accuracy and reliability of the data can be guaranteed. At the same time, it provides a basis for subsequent analysis. The preprocessed mobile phone signaling data can be more effectively used for subsequent disaster emergency management coordination circle identification, such as evacuation OD delineation, disaster prevention coordination area identification, etc.

[0055] Specifically, in an implementation of this embodiment, step S110 includes the following steps:

[0056] Step S111, acquiring population distribution data with geographic coordinates according to the mobile phone signaling data;

[0057] Step S112, unifying the format of the population distribution data and deleting the device information without a tag ID to obtain location coordinate data;

[0058] Step S113, deleting the position coordinate data whose positioning frequency is lower than a preset threshold, and obtaining pre-processed mobile phone signaling data.

[0059] In this embodiment, by unifying the format of population distribution data with geographic coordinates, subsequent data processing and analysis can be facilitated; by deleting device information without tag IDs, the user's privacy can be protected, and at the same time, valid data samples that can track the complete trajectory can be screened out; the location coordinate data with a positioning frequency lower than a preset threshold (set to 50% in this embodiment) is deleted because these data cannot accurately reflect the actual activity trajectory of residents and will affect the reliability of the analysis results.

[0060] In this embodiment, in order to unify the information reporting cycle of each device and protect the location information of residents, the ping coordinate information collection time interval is set to every 15 minutes. The road geographic information data of the corresponding city is obtained from Open Street Map (OSM), and the urban highways and main roads are identified. The mobile phone signaling ping coordinate data within the range is expanded 25m to both sides from the center line of the road and deleted. The mobile phone signaling data near the highway and main roads are eliminated because the movement speed in these areas is too fast and cannot accurately reflect the daily activities of residents. The relevant ping coordinate data can be deleted through system settings based on the geographic information coordinates of the highway and main roads.

[0061] In this embodiment, micro-population distribution data with geographic coordinates during a specific disaster period within a specific research scope is obtained through mobile phone signaling, the data format is unified, and the device information using untagged IDs and the data with coordinate information collected daily below 50% are deleted, thereby screening out valid data samples that can track the complete trajectory.

[0062] Specifically, in an implementation of this embodiment, step S100 further includes the following steps:

[0063] Step S120, according to the probability of the user coordinates appearing in the mobile phone signaling data, the main activity areas in the week before the disaster and in the preset time period during the disaster are calculated respectively by a density-based clustering algorithm.

[0064] In this embodiment, in order to determine the disaster stage, the daily change frequency of residential areas in the city can be counted according to mobile phone signaling data, and a change trajectory curve can be drawn, and the exponential weighted average EWMA can be used to reduce the noise of the trajectory curve data. The change point detection algorithm (Cumulative Sum Control Chart) is used to define the disaster stage for the residential change frequency trajectory curve. The change point detection algorithm is applied to identify the mutation time points in the change trajectory curve, and the average of the mutation time points in each community is taken. The date closest to the average value is selected as the date of occurrence and end of the disaster to determine the disaster stage.

[0065] In this embodiment, the density-based clustering algorithm (DBSCAN algorithm) is used to identify the main daily activity areas of users before and during the disaster. The user coordinates are located every 15 minutes, and the main activity areas in a specific time period one week before the disaster and during the disaster are calculated by the DBSCAN algorithm based on the probability of the user coordinates appearing.

[0066] N ε (p)={q∈C|dist(p,q)≤ε}∧|C|≥n;

[0067] N ε (p) represents the main activity area of ​​user p within a specific time and space range, which can be the main activity area every 6 hours in this embodiment. C is a cluster identified according to the density of user appearance, p represents the location coordinate, q represents the time point, ε represents the Euclidean distance parameter, which can be set to 500m and 6h in this embodiment, and n is the minimum number of identified coordinates, which can be set to 6 times in this embodiment.

[0068] Step S130, dividing the main activity area into activity site categories by using a K-means clustering algorithm, and identifying the main residences of the residents before and during the disaster from the activity site categories.

[0069] In this embodiment, the K-means clustering algorithm (K-means algorithm) is used to identify various types of activity locations before and during the disaster, and the activity location categories may include work, leisure, residence, etc. The K-means algorithm divides n samples x into k non-overlapping clusters C, which have equal variances, and each cluster is represented by its mean μ jDescription. The goal of the algorithm is to minimize the within-cluster sum-of-squares, which means that it tries to make the points within each cluster as close as possible to their mean (center point), thereby minimizing the variance within the cluster.

[0070]

[0071] After identifying the activity location category, select features related to residential behavior, such as the areas with peak behavior in the middle of the week evenings and the areas with peak behavior all day on weekends. These features help distinguish residential areas. By performing time series analysis on daily activity data, daily changes in residents' activity patterns and special patterns during disasters can be captured. According to the clustering results and time series characteristics, analyze the characteristics of each cluster, such as activity time distribution, activity location type, etc., and identify the main residential areas of residents day by day. The identification basis is the areas with peak behavior in the middle of the week evenings and the areas with peak behavior all day on weekends.

[0072] like Figure 1 As shown, in one implementation of the embodiment of the present invention, the method for identifying the urban disaster emergency management coordination circle further includes the following steps:

[0073] Step S200, describing the residence change OD according to the change characteristics of the main residence of the residents before and during the disaster, performing cluster analysis on the residence change OD, and obtaining the residence change OD clusters of the residents.

[0074] In this embodiment, the city is divided into a grid of preset size, and the daily residences of residents before and during the disaster are integrated with the grid to depict the OD clusters of daily residence changes of residents before and during the disaster. The OD clusters of residence changes can be used to further analyze the spatiotemporal evacuation characteristics of residents during the disaster, such as the concentrated period of evacuation, the congestion of the evacuation route, the acceptance capacity of the shelter, etc.; through statistical analysis, areas with high or low evacuation efficiency and possible bottleneck areas in the evacuation process can be identified. Through highly refined spatial grid processing combined with time series analysis, the complex dynamics of evacuation of residents during the disaster are effectively captured and analyzed, providing refined decision-making support for emergency management and evacuation of urban rain and flood disasters.

[0075] Specifically, in an implementation of this embodiment, step S200 includes the following steps:

[0076] Step S210, dividing the urban area into grids, and superimposing the grids with the main residences of the residents before and during the disaster to obtain the grids where the residents' residences before the disaster are located and the grids where the residents' residences during the disaster are located;

[0077] Step S220, describing the change OD of the residence according to the change track of the grid where the residence is located before the disaster and the grid where the residence is located during the disaster;

[0078] Step S230, clustering the residence change OD to obtain the residence change OD cluster.

[0079] In this embodiment, the city is divided into multiple grid units, for example, the city is divided into a 500m x 500m grid. Grid processing is conducive to discretizing the continuous geographic space, which is convenient for subsequent data processing and analysis. Each grid is used as a basic unit, and the activities of residents therein can be independently counted and analyzed.

[0080] In this embodiment, the city grid is superimposed with the main residence of the residents before and during the disaster, and the grid where the residents' residences are located before and during the disaster can be obtained. By identifying the daily residences of the residents before and during the disaster, and then connecting each residence into a line, the OD of the daily residence change of the residents before and during the disaster is obtained. OD represents the starting point and the end point, where the starting point is the grid where the residents' initial residence is located, and the end point is the grid where the residents' residence after transfer is located. By depicting the OD of the change of the residents' residences before and during the disaster, the evacuation path and evacuation destination of the residents during the disaster can be intuitively displayed.

[0081] In this embodiment, a clustering algorithm is used to cluster the daily residential change OD of residents before and during a disaster, and residential change OD clusters can be obtained. Each residential change OD cluster represents a group of residents with similar evacuation paths and evacuation destinations. Through cluster analysis, the main evacuation paths and evacuation destinations, as well as the evacuation patterns of different groups of people can be identified. By analyzing the residential change OD clusters, a scientific basis can be provided for evacuation planning when a disaster occurs, for example, determining the best evacuation route, evacuation destination, and evacuation time. At the same time, according to the residential change OD clusters, the city can be divided into different disaster prevention zones to better manage disasters and allocate resources; select suitable locations to build shelters, and optimize the layout and capacity of shelters; formulate relevant disaster prevention and mitigation policies, for example, strengthen the construction of evacuation facilities, and improve residents' awareness of disaster prevention.

[0082] like Figure 1 As shown, in one implementation of the embodiment of the present invention, the method for identifying the urban disaster emergency management coordination circle further includes the following steps:

[0083] Step S300, overlapping the boundary of the residential change OD cluster with the community administrative boundary to determine the disaster prevention coordination circle, and visually displaying the disaster prevention coordination circle.

[0084] In this embodiment, the boundary of each OD cluster is drawn by the convex hull algorithm (Graham algorithm) scanning algorithm, and then matched with the community administrative boundary in the geographic information software (ArcGIS) to finally determine the disaster prevention coordination circle. By superimposing the identified OD cluster of residential changes with the community administrative boundary, a disaster prevention coordination circle with practical guidance is formed. This method not only takes into account the actual evacuation behavior of residents, but also takes into account the convenience of administrative management, making the disaster prevention zoning more scientific and reasonable.

[0085] Specifically, in an implementation of this embodiment, step S300 includes the following steps:

[0086] Step S310 , clustering the residential change OD clusters by using a density-based clustering algorithm, and grouping the residential change OD clusters according to the clustering results to obtain evacuation OD clusters.

[0087] In this embodiment, the DBSCAN algorithm is used again to cluster the OD clusters of residential changes to identify areas with similar evacuation patterns. The purpose of the DBSCAN algorithm is to distinguish high-density areas (evacuation OD clusters) with significant evacuation characteristics from a large amount of residential change data, while excluding interfering low-density isolated points to obtain a more accurate evacuation area division, providing a scientific basis for disaster emergency management and evacuation planning.

[0088] Specifically, in an implementation of this embodiment, step S310 includes the following steps:

[0089] Step S311, clustering the residential change OD clusters according to a preset neighborhood radius and a minimum number of points based on the density-based clustering algorithm;

[0090] Step S312, according to the clustering result, the high-density areas are clustered to obtain the evacuated OD cluster;

[0091] Step S313: marking isolated points in the low-density area as noise points according to the clustering result, and deleting the noise points.

[0092] In this embodiment, before applying the DBSCAN algorithm, two key parameters need to be set in advance: the neighborhood radius (ε) and the minimum number of points (MinPts). These two parameters will affect the formation of clusters and the identification of boundaries. ε defines the boundaries of the cluster: if the distance between two data points is less than ε, they are considered to belong to the same cluster; MinPts defines the minimum number of points to form a cluster: if the number of data points in an area is less than MinPts, the area is considered to be noise. In this embodiment, ε is set to 1000m, which means that if the distance between two data points is less than 1000m, they are considered to belong to the same evacuation OD cluster; the minimum number of points MinPts is not less than the number of dates during the identified disaster, ensuring that the identified evacuation coordination area is based on a sufficient number of samples of residents' evacuation behavior, filtering out those evacuation points that may be accidental or random, thereby improving the stability and representativeness of the clustering results. The settings of these two parameters work together to enable the DBSCAN algorithm to effectively distinguish high-density crowd gathering areas when processing evacuation residence change data, while excluding isolated points or noise, thereby more accurately depicting the natural pattern of resident evacuation during disasters.

[0093] In this embodiment, the DBSCAN algorithm is used to traverse the geographic coordinate information of the grid center point of each OD cluster of residential change, and the algorithm checks whether the area around each point contains at least MinPts points. If the conditions are met, the point is considered to be a core point, and a cluster is formed around the point; if there are not enough points around the point but it belongs to the neighborhood of other core points, it is considered a boundary point; otherwise, the point is marked as a noise point. By continuously iterating the above process, the DBSCAN algorithm divides the points into different clusters, and the points within each cluster are relatively dense, while the points between clusters are relatively sparse. In this way, based on the similarity and geographical proximity of residents' evacuation behaviors, the OD clusters of residential change are grouped into several evacuation OD clusters.

[0094] In this embodiment, high-density areas are clustered according to the clustering results to obtain sparse OD clusters; isolated points in low-density areas are marked as noise points and deleted, thereby improving the accuracy and reliability of the clustering results.

[0095] Specifically, in an implementation of this embodiment, step S300 further includes the following steps:

[0096] Step S320, depicting the boundary of the evacuated OD cluster by using a convex hull algorithm;

[0097] Step S330, using geographic information software to couple the boundary of the evacuation OD cluster with the community administrative boundary to obtain the disaster prevention coordination circle.

[0098] In this embodiment, the Graham algorithm is used to depict the boundaries of the evacuation OD cluster, and ArcGIS is used to couple the boundaries of the disaster prevention coordination circle. The Graham algorithm's precise boundary recognition capability is combined with ArcGIS's spatial analysis and visualization functions, so that the disaster prevention coordination circle can be divided more scientifically and reasonably to ensure that these areas can effectively cover the evacuated population and meet actual administrative management needs. At the same time, through the precise division of the disaster prevention coordination circle, disaster prevention resources can be allocated more effectively, such as the establishment of emergency shelters and the pre-positioning of rescue materials, thereby improving the efficiency and effectiveness of disaster response. Planning disaster prevention areas based on the actual evacuation behavior of residents will help to formulate more efficient evacuation plans, reduce confusion during the evacuation process, and protect the lives and property of residents.

[0099] Specifically, in an implementation of this embodiment, step S320 includes the following steps:

[0100] Step S321 : constructing the convex hull of the sparse OD cluster by the convex hull algorithm, and connecting the convex hull vertices of each cluster to form a closed polygon, thereby obtaining the boundary of the sparse OD cluster.

[0101] In this embodiment, the Graham algorithm is used to depict the boundary. For each evacuated OD cluster, a reference point is selected, usually the point with the smallest y coordinate in the cluster (if there are multiple such points, the one with the smallest x coordinate is selected). This point will be used as the starting point of the Graham scanning algorithm. The points in the cluster are sorted according to the polar angle of each point relative to the reference point (i.e., the angle between the line connecting the point and the reference point and the x-axis). If two points have the same polar angle, the point farther from the reference point is placed in front. The convex hull is constructed using the Graham scanning algorithm: a stack is initialized, and the first three points after sorting are pushed into the stack. β For each of the remaining points after sorting, check the turn formed by the two points at the top of the stack and the current point. If a right turn (or clockwise turn) is formed, the stack vertex is popped out until a left turn (or counterclockwise turn) is formed. Then the current point is pushed into the stack. After the above steps, the remaining points in the stack constitute the convex hull of the evacuated OD cluster. Based on the convex hull vertices of each cluster, the cluster boundary is drawn, which can be achieved by connecting the line segments of the convex hull vertices to form a closed polygon representing the spatial extent of the cluster.

[0102] Step S322, generating a space segmentation map based on the community center point in the geographic information software according to the community center point;

[0103] Step S323, superimposing the community center point-based space segmentation map with the boundary of the evacuation OD cluster, and determining the disaster prevention coordination circle according to the superimposed area.

[0104] In this embodiment, ArcGIS, as a powerful geographic information system software, is capable of complex spatial data processing, analysis and visualization. In the present invention, it is used to process and analyze geographic information related to disaster prevention. ArcGIS matching is used to couple the boundary range with the community administrative boundary. In ArcGIS, a spatial segmentation map (Voronoi diagram) based on the community center point is generated according to the community center point, and the Voronoi diagram is superimposed with the evacuation OD cluster boundary map. The disaster prevention coordination circle is determined based on the inclusion of the evacuation OD cluster boundary and the community center point (if the center point is included in the specific cluster boundary, the community can be included in the disaster prevention coordination circle).

[0105] In this embodiment, the evacuation OD cluster boundary calculated by the Graham algorithm is overlapped with the community Voronoi diagram to determine which communities or regions should be included in a specific disaster prevention coordination circle. This step ensures that the division of the evacuation area not only conforms to the actual evacuation path, but also coordinates with the existing community administrative boundaries, which facilitates administrative management and resource allocation.

[0106] Specifically, in an implementation of this embodiment, step S300 further includes the following steps:

[0107] Step S330, visually displaying the disaster prevention coordination circle through the geographic information software.

[0108] In this embodiment, GIS software is used to visualize the disaster prevention coordination circles, and different colors or symbols can be used to distinguish different disaster prevention coordination circles, so as to intuitively understand the boundaries and scope of each coordination circle, and facilitate relevant departments and personnel to understand and grasp the division of disaster evacuation areas; the visualization results can provide important reference basis for disaster prevention and mitigation planning and emergency response, and help relevant departments to formulate more scientific and reasonable evacuation plans and resource allocation plans; through visualization, areas and people affected by disasters can be quickly identified, thereby improving the efficiency and effectiveness of emergency response.

[0109] In this embodiment, by analyzing the evacuation characteristics of residents during disasters based on spatiotemporal big data, a clustering algorithm is used to identify the disaster prevention emergency coordination area, and finally combined with the administrative boundaries to form a disaster prevention coordination area division method with strong practical guidance value. This method is of great value for refuge space planning and disaster prevention and mitigation resource allocation.

[0110] This embodiment achieves the following technical effects through the above technical solution:

[0111] This embodiment obtains mobile phone signaling data and identifies the main residence of residents before and during the disaster according to the mobile phone signaling data; describes the change OD of the residence according to the change characteristics of the main residence of the residents before and during the disaster, which can more accurately reflect the actual evacuation behavior of the crowd when the disaster occurs, and provides more accurate data support for disaster prevention zoning. By clustering the change OD of the residence, the change OD cluster of the residents' residence can be obtained, which can effectively aggregate the areas with close evacuation associations to form a more reasonable disaster prevention coordination area; the boundaries of the change OD cluster of the residence are overlapped with the administrative boundaries of the community to form a disaster prevention coordination circle with practical guidance significance, and the disaster prevention coordination circle is visualized to reflect the self-organized evacuation mode of the residents in the disaster situation, provide a reference for formulating evacuation strategies, and form a disaster prevention area division guide; the present invention proposes a new method for disaster emergency management coordinated area division, which not only takes into account the actual evacuation behavior of the residents, but also takes into account the convenience of administrative management, so that the disaster prevention zoning is more scientific and reasonable, which helps to optimize the allocation of disaster prevention resources and improve evacuation efficiency.

[0112] Exemplary Devices

[0113] Based on the above embodiments, the present invention also provides a terminal, comprising: a processor, a memory, an interface, a display screen and a communication module connected via a system bus; wherein the processor is used to provide computing and control capabilities; the memory includes a storage medium and an internal memory; the storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and the computer program in the storage medium; the interface is used to connect external devices, such as mobile terminals and computers; the display screen is used to display corresponding information; and the communication module is used to communicate with a cloud server or a mobile terminal.

[0114] When the computer program is executed by the processor, it is used to implement the operation of a method for identifying a city disaster emergency management coordination circle.

[0115] It can be understood by those skilled in the art that Figure 2 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0116] In one embodiment, a terminal is provided, which includes: a processor and a memory, wherein the memory stores a city disaster emergency management coordination circle identification program, and the city disaster emergency management coordination circle identification program is used to implement the operation of the city disaster emergency management coordination circle identification method as described above when executed by the processor.

[0117] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a city disaster emergency management coordination circle identification program, and when the city disaster emergency management coordination circle identification program is executed by the processor, it is used to implement the operation of the city disaster emergency management coordination circle identification method as described above.

[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory.

[0119] In summary, the present invention provides a method, terminal and storage medium for identifying an urban disaster emergency management coordination circle, the method comprising: obtaining mobile phone signaling data, and identifying the main residence of residents before and during the disaster according to the mobile phone signaling data; describing the residence change OD according to the change characteristics of the main residence of the residents before and during the disaster, performing cluster analysis on the residence change OD, and obtaining the residence change OD cluster of the residents; overlapping the boundaries of the residence change OD cluster with the community administrative boundaries to determine the disaster prevention coordination circle, and visually displaying the disaster prevention coordination circle; the present invention proposes a new method for dividing disaster emergency management coordination areas to optimize the allocation of disaster prevention resources and improve evacuation efficiency.

[0120] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for identifying an urban disaster emergency management coordination circle, characterized in that: include: Obtaining mobile phone signaling data and identifying the primary place of residence of residents before and during the disaster based on the mobile phone signaling data; Describing the residence change OD according to the change characteristics of the main residence of the residents before and during the disaster, performing cluster analysis on the residence change OD to obtain the residence change OD clusters of the residents; The boundaries of the residential change OD cluster are overlapped with the community administrative boundaries to determine the disaster prevention coordination circle, and the disaster prevention coordination circle is visualized.

2. The method for identifying the urban disaster emergency management coordination circle according to claim 1 is characterized in that: The obtaining of mobile phone signaling data and identifying the main places of residence of residents before and during the disaster according to the mobile phone signaling data include: Acquire the mobile phone signaling data, and pre-process the mobile phone signaling data; According to the probability of the user coordinates appearing in the mobile phone signaling data, the main activity areas in the preset time period one week before the disaster and during the disaster are calculated by a density-based clustering algorithm; The main activity areas are divided into activity site categories by using a K-means clustering algorithm, and the main residences of the residents before and during the disaster are identified from the activity site categories.

3. The method for identifying the urban disaster emergency management coordination circle according to claim 2, characterized in that: The preprocessing of the mobile phone signaling data includes: Acquiring population distribution data with geographic coordinates according to the mobile phone signaling data; The format of the population distribution data is unified, and the device information without a tag ID is deleted to obtain the location coordinate data; The position coordinate data whose positioning frequency is lower than a preset threshold is deleted to obtain pre-processed mobile phone signaling data.

4. The method for identifying the urban disaster emergency management coordination circle according to claim 1, characterized in that: The step of describing the OD of the change of the main residence of the residents before and during the disaster according to the change characteristics of the main residence of the residents before and during the disaster, and performing cluster analysis on the OD of the change of the residence to obtain the OD cluster of the change of the residence of the residents includes: Divide the urban area into grids, and overlap the grids with the main residences of the residents before and during the disaster to obtain the grids where the residents' residences before the disaster are located and the grids where the residents' residences during the disaster are located; Describe the change OD of the residence according to the change track of the grid where the residence was located before the disaster and the grid where the residence was located during the disaster; The residence change OD is clustered to obtain the residence change OD cluster.

5. The method for identifying the urban disaster emergency management coordination circle according to claim 1, characterized in that: The method of overlaying the boundary of the residential change OD cluster with the community administrative boundary to determine the disaster prevention coordination circle, and visually displaying the disaster prevention coordination circle, includes: Clustering the residential change OD clusters by a density-based clustering algorithm, and grouping the residential change OD clusters according to the clustering results to obtain evacuation OD clusters; Describing the boundary of the sparse OD cluster by a convex hull algorithm; Using geographic information software to couple the boundary of the evacuation OD cluster with the community administrative boundary to obtain the disaster prevention coordination circle; The disaster prevention coordination circle is visualized through the geographic information software.

6. The method for identifying the urban disaster emergency management coordination circle according to claim 5, characterized in that: The step of clustering the residential change OD clusters by using a density-based clustering algorithm, and grouping the residential change OD clusters according to the clustering results to obtain evacuation OD clusters includes: Based on the density-based clustering algorithm, clustering the residential change OD clusters according to a preset neighborhood radius and a minimum number of points; According to the clustering result, the high-density areas are clustered to obtain the evacuated OD cluster; According to the clustering result, isolated points in the low-density area are marked as noise points, and the noise points are deleted.

7. The method for identifying the urban disaster emergency management coordination circle according to claim 5, characterized in that: Describing the boundary of the evacuated OD cluster by using a convex hull algorithm includes: The convex hull of the sparse OD cluster is constructed by the convex hull algorithm, and the convex hull vertices of each cluster are connected to form a closed polygon to obtain the boundary of the sparse OD cluster.

8. The method for identifying the urban disaster emergency management coordination circle according to claim 5, characterized in that: The geographic information software is used to couple the boundary of the evacuation OD cluster with the community administrative boundary to obtain the disaster prevention coordination circle, including: Generating a spatial segmentation map based on the community center point in the geographic information software according to the community center point; The space segmentation map based on the community center point is superimposed with the boundary of the evacuation OD cluster, and the disaster prevention coordination circle is determined according to the superimposed area.

9. A terminal, characterized in that: include: A processor and a memory, wherein the memory stores a city disaster emergency management coordination circle identification program, and when the city disaster emergency management coordination circle identification program is executed by the processor, it is used to implement the operation of the city disaster emergency management coordination circle identification method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a city disaster emergency management coordination circle identification program, which, when executed by a processor, is used to implement the operation of the city disaster emergency management coordination circle identification method as described in any one of claims 1-8.

Images