A fire point fusion positioning method, device and electronic equipment

Abstract

The present application provides a method, device and electronic device for fusion positioning of fire points, the method comprising: obtaining multiple fire point data, the fire point data comprising: longitude and latitude coordinates and data source type; clustering the multiple fire point data according to the longitude and latitude coordinates to obtain multiple clusters; for each cluster in the multiple clusters, clustering all the fire point data under the cluster according to the data source type and the spatial distance between the fire point data to obtain multiple sub-clusters under the cluster; for each sub-cluster in the multiple sub-clusters under the cluster, fusion positioning of all the fire point data under the sub-cluster to obtain the positioning coordinates of the sub-cluster. In the implementation process of the above scheme, the fire point data in the sub-cluster is processed through two clustering processes and fusion positioning technology to obtain more accurate positioning coordinates, distinguish multiple independent fire events occurring simultaneously in the same area, thereby enhancing the accuracy of fire point fusion positioning and improving the recall rate of fire point fusion positioning.

Description

Technical Field

[0001] The present application relates to the technical field of big data and computer software algorithms, and more specifically, to a method, device and electronic equipment for fusion positioning of fire points. Background Art

[0002] At present, when clustering the coordinates of fire starting points using clustering algorithms, it is easy to classify two fire points in close locations in the same area into the same cluster. For example, if two fire points are very close in space, especially when fires occur simultaneously in the same area, these fire points can easily be mistakenly classified into the same cluster. In this case, even if there are actually multiple independent fires, they may be mistaken for a large-scale fire incident. Therefore, it is difficult for current clustering algorithms to identify multiple independent fire incidents occurring simultaneously in the same area, resulting in a low recall rate for fire point location. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a fire point fusion positioning method, device and electronic device for improving the problem of low recall rate of fire point positioning.

[0004] An embodiment of the present application provides a fire point fusion positioning method, including: acquiring multiple fire point data, the fire point data including: longitude and latitude coordinates and data source type; clustering the multiple fire point data according to the longitude and latitude coordinates to obtain multiple clusters; for each cluster in the multiple clusters, clustering all the fire point data under the cluster according to the data source type and the spatial distance between the fire point data to obtain multiple sub-clusters under the cluster, the spatial distance between the fire point data is calculated based on the longitude and latitude coordinates of the fire point data; for each sub-cluster in the multiple sub-clusters under the cluster, fusing and positioning all the fire point data under the sub-cluster to obtain the positioning coordinates of the sub-cluster. In the implementation process of the above scheme, the fire points are initially divided from the perspective of spatial position through the first clustering, and the second clustering is based on the source of the fire points in the same cluster and the spatial distance relationship between the fire points of different sources, and the fire points of the same source are divided into different clusters, thereby further distinguishing the fire points of the same source type in the original cluster of the same type, preventing the fire points of multiple fires that have been discovered from being mixed into one cluster, and improving the situation of missed fire points due to the close spatial distance of the data, so that the recall rate of fire point positioning can be improved. Therefore, by processing the fire point data in the sub-cluster through two clustering processes and fusion positioning technology, more accurate positioning coordinates can be obtained, effectively distinguishing multiple independent fire events that occurred simultaneously in the same area, thereby improving the recall rate of fire point fusion positioning.

[0005] Optionally, in an embodiment of the present application, clustering multiple fire point data according to longitude and latitude coordinates includes: calculating the longitude and latitude coordinates of two fire point data among the multiple fire point data to obtain the spatial distance between the two fire points; clustering the multiple fire point data according to the spatial distance. In the implementation process of the above scheme, by calculating the spatial distance between the fire points and clustering them accordingly, the location of the fire points can be more accurately identified, taking into account the actual spatial relationship between the fire points, thereby enhancing the accuracy of the fire point fusion positioning.

[0006] Optionally, in an embodiment of the present application, all fire point data under the cluster are clustered according to the spatial distance between the data source type and the fire point data, including: counting all the fire point data under the cluster according to the data source type to obtain the number of fire points of multiple data source types; screening out the target source type and remaining source types with the largest number of fire points from the multiple data source types; creating multiple sub-clusters under the cluster based on all the fire point data of the target source type; respectively dividing all the fire point data of the target source type into the multiple sub-clusters under the cluster; for each fire point data in the remaining source types, dividing the fire point data into the multiple sub-clusters under the cluster according to the spatial distance between the fire point data and the fire point data of the target source type. In the implementation process of the above scheme, by clustering all the fire point data under the cluster according to the data source type and the spatial distance between the fire point data, sub-clusters are established for the fire point data of different source types, and the fire point data are allocated to the corresponding sub-clusters based on the spatial distance. The location of the fire point can be identified more accurately, taking into account the actual spatial relationship between the fire points and the differences in data sources, and effectively verifying the positioning coordinates of the fire point data from multiple angles, thereby effectively improving the accuracy of the acquisition of the fire point positioning coordinates.

[0007] Optionally, in an embodiment of the present application, the fire point data is divided into multiple subclusters under the cluster according to the spatial distance between the fire point data and the fire point data of the target source type, including: for each fire point data in the remaining source types, the Haversine distance between the fire point data and the fire point data of the target source type is calculated according to the longitude and latitude coordinates; the subcluster where the target fire point with the smallest Haversine distance between the fire point data of the target source type and the fire point data in the subcluster is located is screened out from multiple subclusters; the fire point data is divided into the subcluster where the target fire point is located. In the implementation process of the above scheme, the Haversine formula is introduced in combination with the clustering algorithm, thereby improving the phenomenon of inaccurate clustering caused by using the Euclidean distance between the longitude and latitude coordinates as a metric, and effectively increasing the accuracy of clustering multiple fire point data according to spatial distance.

[0008] Optionally, in an embodiment of the present application, all the fire point data under the sub-cluster are fused and positioned, including: assigning initial weights to all the fire point data under the sub-cluster according to the data source type; performing weighted calculation on the longitude and latitude coordinates of all the fire point data under the sub-cluster according to the initial weights of all the fire point data under the sub-cluster to obtain the center point coordinates of the sub-cluster; for each fire point data among all the fire point data under the sub-cluster, calculating the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster; optimizing and updating the initial weights of the fire point data according to the spatial distance to obtain the updated weights of the fire point data; performing iterative optimization on the center point coordinates of the sub-cluster according to the updated weights of all the fire point data under the sub-cluster until the iteration stop condition is met to obtain the positioning coordinates of the sub-cluster; wherein the iteration condition includes: the number of iterations in which the weighted calculation of the center point coordinates of the sub-cluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the sub-cluster and the center point coordinates weighted calculated in the previous iteration of the sub-cluster is less than a preset distance threshold. In the implementation of the above scheme, by assigning initial weights to fire point data of different source types and performing weighted calculations, more accurate center point coordinates can be obtained. The weights are adjusted in a dynamic iterative optimization manner based on the spatial distance between the fire point data and the center point coordinates, ensuring that data closer to the center point accounts for a larger proportion in the calculation. This iterative optimization process effectively considers the importance of different data sources, so that the geographic coordinates of the center point are closer to the actual coordinates of the fire point, effectively improving the accuracy of the fire point fusion positioning.

[0009] Optionally, in an embodiment of the present application, the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster is calculated, including: using the Haversine algorithm formula to calculate the Haversine distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster; determining the Haversine distance as the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster. In the implementation process of the above scheme, the Haversine formula is introduced in combination with the two-time clustering algorithm, thereby improving the phenomenon of inaccurate clustering caused by using the Euclidean distance between the longitude and latitude coordinates as a metric, and effectively increasing the accuracy of clustering multiple fire point data according to spatial distance.

[0010] The embodiment of the present application also provides a fire point fusion positioning device, including: a fire point data acquisition module, used to acquire multiple fire point data, the fire point data including: longitude and latitude coordinates and data source type; a first data clustering module, used to cluster the multiple fire point data according to the longitude and latitude coordinates to obtain multiple clusters; a second data clustering module, used to cluster all the fire point data under each cluster in the multiple clusters according to the data source type and the spatial distance between the fire point data, to obtain multiple sub-clusters under the cluster, the spatial distance between the fire point data is calculated based on the longitude and latitude coordinates of the fire point data; a positioning coordinate acquisition module, used to fuse and locate all the fire point data under each sub-cluster in the multiple sub-clusters under the cluster, to obtain the positioning coordinates of the sub-cluster.

[0011] Optionally, in an embodiment of the present application, the first data clustering module includes: a spatial distance calculation submodule, used to calculate the longitude and latitude coordinates of two fire point data among multiple fire point data to obtain the spatial distance between the two fire points; and a fire point data clustering submodule, used to cluster multiple fire point data according to the spatial distance.

[0012] Optionally, in an embodiment of the present application, the second data clustering module includes: a fire point number acquisition submodule, which is used to count all the fire point data under the cluster according to the data source type, and obtain the number of fire points of multiple data source types; a source type screening submodule, which is used to screen out the target source type and the remaining source types with the largest number of fire points from the multiple data source types; a cluster subcluster creation submodule, which is used to create multiple subclusters under the cluster according to all the fire point data of the target source type; a target fire point classification submodule, which is used to classify all the fire point data of the target source type into the multiple subclusters under the cluster; and a remaining fire point classification submodule, which is used to classify each fire point data in the remaining source types into the multiple subclusters under the cluster according to the spatial distance between the fire point data and the fire point data of the target source type.

[0013] Optionally, in an embodiment of the present application, the remaining fire points are divided into submodules, including: a Haversine distance calculation unit, which is used to calculate the Haversine distance between the fire point data and the fire point data of the target source type according to the latitude and longitude coordinates for each fire point data in the remaining source types; a minimum distance subcluster screening unit, which is used to screen out from multiple subclusters the subcluster where the target fire point with the smallest Haversine distance between the fire point data of the target source type in the subcluster and the fire point data is located; and a fire point data subcluster classification unit, which is used to classify the fire point data into the subcluster where the target fire point is located.

[0014] Optionally, in an embodiment of the present application, the positioning coordinate acquisition module includes: an initial weight assignment submodule, which is used to assign initial weights to all fire point data under the subcluster according to the data source type; a central coordinate fire point submodule, which is used to perform weighted calculation on the longitude and latitude coordinates of all fire point data under the subcluster according to the initial weights of all fire point data under the subcluster to obtain the central point coordinates of the subcluster; a coordinate distance calculation submodule, which is used to calculate the spatial distance between the longitude and latitude coordinates in the fire point data and the central point coordinates of the subcluster for each fire point data in all fire point data under the subcluster; The re-optimization and updating submodule is used to optimize and update the initial weight of the fire point data according to the spatial distance to obtain the updated weight of the fire point data; the center coordinate optimization submodule is used to iteratively optimize the center point coordinates of the subcluster according to the updated weights of all the fire point data under the subcluster until the conditions for stopping iteration are met to obtain the positioning coordinates of the subcluster; wherein the iteration conditions include: the number of iterations of the weighted calculation of the center point coordinates of the subcluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the subcluster and the center point coordinates calculated by weighted calculation of the subcluster in the previous iteration is less than a preset distance threshold.

[0015] Optionally, in an embodiment of the present application, the coordinate distance calculation submodule includes: a coordinate distance calculation unit, used to use the Haversine algorithm formula to calculate the Haversine distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster; a spatial distance determination unit, used to determine the Haversine distance as the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster.

[0016] An embodiment of the present application further provides an electronic device, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions execute the method described above when executed by the processor.

[0017] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is executed.

[0018] The embodiment of the present application also provides a computer program product, including: a computer program or a computer instruction, and the computer program or the computer instruction executes the method described above when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of the flow of the fire point fusion positioning method provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram of fire point data of different data source types under a cluster provided by an embodiment of the present application is shown;

[0022] Figure 3 A schematic diagram of a process of clustering according to data source type and spatial distance between fire point data provided by an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram of the process of the fire point fusion positioning device provided in an embodiment of the present application is shown;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the embodiment of the present application only serve the purpose of explanation and description, and are not used to limit the protection scope of the embodiment of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in the embodiment of the present application shows the operation implemented according to some embodiments of the embodiment of the present application. It should be understood that the operation of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the embodiment of the present application, or remove one or more operations from the flowchart.

[0026] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application described and shown in the drawings generally here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the embodiments of the present application claimed, but merely represents the selected embodiments of the embodiments of the present application.

[0027] It is understandable that the "first" and "second" in the embodiments of the present application are used to distinguish similar objects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity and execution order, and the words "first" and "second" do not necessarily limit the difference. In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of the associated objects, indicating that there may be three relationships, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship. The term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups).

[0028] Before introducing the fire point fusion positioning method provided in the embodiment of the present application, some concepts involved in the embodiment of the present application are first introduced:

[0029] Fire point fusion positioning refers to the process of using positioning technology to fuse and locate the fire point at a fire scene from multiple data sources. For example, the fire point data at a fire scene acquired by a satellite (lower resolution) and the fire point data at a fire scene monitored by a drone (higher resolution) are fused to obtain more accurate fire point coordinates.

[0030] It should be noted that the fire point fusion positioning method provided in the embodiment of the present application can be executed by an electronic device, where the electronic device refers to a device terminal with a function of executing a computer program or the above-mentioned server, such as a smart phone, a personal computer, a tablet computer, a personal digital assistant or a mobile Internet device. A server refers to a device that provides computing services through a network, such as an x86 server and a non-x86 server, and the non-x86 server includes a mainframe, a minicomputer and a UNIX server.

[0031] See also Figure 1 The flowchart of the fire point fusion positioning method provided by the embodiment of the present application is shown; the main idea of ​​the fire point fusion positioning method is to process the fire point data in the sub-cluster through two clustering processes and fusion positioning technology, so as to obtain more accurate positioning coordinates, effectively distinguish multiple independent fire events occurring simultaneously in the same area, thereby improving the recall rate of fire point fusion positioning. The implementation method of the above-mentioned fire point fusion positioning method may include:

[0032] Step S110: Acquire multiple fire point data, the fire point data includes: longitude and latitude coordinates and data source type.

[0033] It can be understood that the above-mentioned multiple fire point data may include data of different resolutions, or data of the same resolution, and the latitude and longitude coordinates of the fire point data may be similar or the same, or different.

[0034] Step S120: clustering the multiple fire point data according to the longitude and latitude coordinates to obtain multiple clusters.

[0035] It can be understood that the above-mentioned preliminary clustering of multiple fire point data based on longitude and latitude coordinates can distinguish different fire points from multiple fire points through the spatial positions represented by the longitude and latitude coordinates, that is, distinguish fire points with larger distances from a spatial perspective.

[0036] Step S130: For each cluster among the multiple clusters, all the fire point data under the cluster are clustered according to the data source type and the spatial distance between the fire point data to obtain multiple sub-clusters under the cluster. The spatial distance between the fire point data is calculated based on the latitude and longitude coordinates of the fire point data.

[0037] It is understandable that in the above-mentioned process of clustering multiple fire point data according to longitude and latitude coordinates, fire points with similar longitude and latitude coordinates may be classified into one cluster, but in fact, fire points with similar longitude and latitude coordinates may be two different fire points, resulting in the problem of missing fire points in the final output result. In order to reduce this phenomenon, further, all fire point data under the cluster are clustered again according to the data source type and the spatial distance between the fire point data, which can effectively improve the problem of missing fire points in the final output result, thereby improving the recall rate of fire point fusion positioning. Among them, the spatial distance between the above-mentioned fire point data is calculated based on the longitude and latitude coordinates of the fire point data, and the specific calculation process can refer to the implementation method of step S121 below.

[0038] Step S140: for each sub-cluster in the multiple sub-clusters under the cluster, all the fire point data under the sub-cluster are fused and positioned to obtain the positioning coordinates of the sub-cluster.

[0039] It can be understood that the above-mentioned fusion positioning of all fire point data under the sub-cluster can effectively utilize the information of multiple data source types and can mutually verify the positioning coordinates of the fire point data from multiple angles. Therefore, this two-time clustering combined with multiple data source types effectively improves the accuracy of obtaining the fire point positioning coordinates compared to the single clustering process.

[0040] In the implementation process of the above scheme, the fire points are initially divided by the angle e of the spatial position through the first clustering, and the second clustering is based on the source of the fire points in the same cluster and the spatial distance relationship between the fire points of different sources. The fire points of the same source are divided into different clusters, thereby further distinguishing the fire points of the same source type in the original cluster of the same type, preventing the fire points of multiple fires that have been discovered from being mixed into one cluster, improving the situation of missed fire reports due to the close spatial distance of the data, and thus being able to improve the recall rate of fire point positioning. Therefore, by processing the fire point data in the sub-cluster through two clustering processes and fusion positioning technology, more accurate positioning coordinates can be obtained, effectively distinguishing multiple independent fire events occurring simultaneously in the same area, thereby enhancing the accuracy of fire point fusion positioning and improving the recall rate of fire point fusion positioning.

[0041] As an optional implementation of the above step S110, for example, an executable program written in Python language reads multiple fire point data from a file system or a database, and each fire point data may include: longitude and latitude coordinates and data source type. The above multiple fire point data may be fire point data of different data source types, and these fire point data of different data source types may have different resolutions.

[0042] See also Figure 2 A schematic diagram of fire point data of different data source types under a cluster provided by an embodiment of the present application is shown; the fire point data of the above-mentioned different data source types may include: space-based data (Space), near-based data (Near), air-based data (Sky) and / or ground-based data (Surface). Among them, space-based data is fire point data collected by artificial satellites (represented by stars in the figure), near-based data is data collected by airborne aircraft (for example, aircraft similar to airships used in airborne areas) (represented by cylinders in the figure), air-based data is data collected by drones flying over the ground (represented by circles in the figure), and ground-based data is data collected by monitors or watchtowers installed on the ground (represented by triangles in the figure). The above space-based data, near-based data, air-based data and ground-based data have differences in the predicted spatial resolution. Among these four types of data sources, the farther the data is from the fire point, the lower the spatial classification rate. Therefore, the spatial resolution of these four types of data increases successively.

[0043] As an optional implementation of the above step S120, the above implementation of clustering multiple fire point data according to latitude and longitude coordinates may include:

[0044] Step S121: Calculate the longitude and latitude coordinates of two fire point data among the multiple fire point data to obtain the spatial distance between the two fire points.

[0045] The implementation method of the above step S121 is, for example: first, modify the Haversine formula to obtain the modified Haversine formula. The Haversine formula is also called the Haversine formula, which is a formula for calculating the shortest distance between two points on the earth's surface. The formula can be expressed as ;in, represents the angle between two points, The Haversine formula above calculates the shortest distance between two points. d According to the formula To transform Replace with , thus obtaining Then, we transform the above formula into ; Among them, the latitude and longitude coordinates of the first fire point (such as point A) can be expressed as ( , ), the latitude and longitude coordinates of the second fire point (for example, point B) can be expressed as ( , ), α Represents the latitude coordinate in the above longitude and latitude coordinates, It represents the calculated distance between the first fire point (such as point A) and the second fire point (such as point B) on the earth's surface. Represents the radius of the earth (which can be 6371 kilometers). Then, for two fire point data with the same data source type, the modified Haversine formula is used to calculate the longitude and latitude coordinates of the two fire point data to obtain the spatial distance between the two fire points.

[0046] Step S122: clustering multiple fire point data according to spatial distance.

[0047] The implementation method of the above step S122 is, for example: using the density-based spatial clustering of applications with noise (DBSCAN) algorithm or the ST-DBSCAN (Spatial Temporal-DBSCAN) clustering algorithm to cluster multiple fire point data according to the spatial distance calculated by the modified Haversine formula. It is understandable that the clustering process using only longitude and latitude coordinates cannot well predict the spatial distance between two fire points. For example, when a fire occurs near the equator, the distance difference of 1° longitude is about 111 kilometers; while at 50° north and south latitude, it is 55 kilometers per degree, and there is almost no difference near the poles. Therefore, the above scheme clusters multiple fire point data by introducing the modified Haversine formula combined with the DBSCAN clustering algorithm or the ST-DBSCAN clustering algorithm, thereby improving the phenomenon of inaccurate clustering caused by using the Euclidean distance between longitude and latitude coordinates as a metric in the DBSCAN clustering algorithm or the ST-DBSCAN clustering algorithm, and effectively increasing the accuracy of clustering multiple fire point data according to spatial distance.

[0048] For ease of understanding and explanation, the following is an example of clustering multiple fire point data using the DBSCAN clustering algorithm based on the spatial distance calculated by the modified Haversine formula:

[0049] The first step is to define parameters, for example: define the epsilon (eps) parameter, which is used to determine the neighborhood range of a point, that is, the distance threshold within which other points can be found. Define the minimum number of samples in the neighborhood (min_samples), where min_samples is used to determine the core point (described below).

[0050] The second step is state initialization. For example, all points are marked as unvisited, which means that no data points have been processed before the algorithm starts. By marking all points as unvisited, the algorithm can correctly traverse each data point and process it accordingly according to its state. Initialization can avoid repeatedly processing the same point during the execution of the algorithm and ensure that each point is processed only once.

[0051] The third step is to identify core points. For example, select an unvisited data point from the data set as the starting point. For each point in the data set, calculate the number of points in its eps neighborhood. If there are at least min_samples other points around a point (including itself), then these points constitute the neighborhood of the point. If the eps neighborhood of a point contains at least min_samples points (including the point itself), it is marked as a core point. If a point is not a core point but is in the neighborhood of a core point, then the point is called a boundary point.

[0052] The fourth step is cluster expansion. For example, select an unvisited core point from the data set as the starting point. If a point is a core point, all points in its eps-neighborhood are divided into a cluster (including the core point itself). For non-core points, if they are in the eps-neighborhood of a core point (excluding the core point itself), they are classified into the cluster where the core point is located. After processing a point and its neighborhood, mark these points as "visited".

[0053] Step 5: Repeat the above steps until all core points have been visited. For example, if there are still unvisited core points, go back to step 1 and select the next unvisited core point to continue processing. When all core points have been visited and correctly classified as core points, boundary points or noise points, the algorithm ends.

[0054] See also Figure 3 The schematic diagram of the process of clustering according to the spatial distance between the data source type and the fire point data provided by the embodiment of the present application is shown; as an optional implementation of the above step S130, the above implementation of clustering all the fire point data under the cluster according to the spatial distance between the data source type and the fire point data may include:

[0055] Step S131: Count all fire point data under the cluster according to the spatial distance between the data source type and the fire point data to obtain the number of fire points of multiple data source types.

[0056] The implementation method of the above step S131 is, for example: Figure 2 By counting the fire point data of different data source types displayed, the number of fire points of each data source type can be obtained, for example: there is 1 space-based data (represented by stars in the figure), 2 temporary-based data (represented by cylinders in the figure), 2 air-based data (represented by circles in the figure), and 3 ground-based data (represented by triangles in the figure).

[0057] Step S132: Filter out the target source type with the largest number of fire points and the remaining source types from the multiple data source types.

[0058] For example, the implementation method of the above step S132 is as follows: since there is 1 space-based data (represented by stars in the figure), 2 temporary-based data (represented by cylinders in the figure), 2 air-based data (represented by circles in the figure), and 3 ground-based data, the ground-based data has the largest number of fire points among these four types. Therefore, the ground-based data type can be used as the target source type, and the space-based data, temporary-based data and space data can be used as the remaining source types.

[0059] Step S133: Create multiple sub-clusters under the target source type based on all the fire point data of the target source type.

[0060] The implementation method of the above step S133 is as follows: Figure 3 As shown in the first row of sub-figures, since there are 3 ground-based data of the target source type, 3 sub-clusters can be directly created. In actual operation, n-1 clusters can be newly created, and 1 original cluster can be merged into n sub-clusters under the cluster, where n here refers to the total number of fire points in the target source type.

[0061] Step S134: All fire point data of the target source type are divided into multiple sub-clusters under the type cluster.

[0062] The implementation method of the above step S134 is as follows: Figure 3 As shown in the second row of sub-figures, all the fire point data of the ground-based data, a total of 3, are respectively divided into the 3 newly created sub-clusters under the cluster, so that each cluster is divided into one fire point data.

[0063] Step S135: for each fire point data in the remaining source types, the fire point data is classified into multiple sub-clusters under the class cluster according to the spatial distance between the fire point data and the fire point data of the target source type.

[0064] As an optional implementation of the above step S135, the above implementation of classifying the fire point data into multiple sub-clusters under the class cluster may include:

[0065] Step S135a: For each fire point data in the remaining source types, the Haversine distance between the fire point data and the fire point data of the target source type is calculated based on the longitude and latitude coordinates.

[0066] The implementation method of the above step S135a is as follows: Figure 3 As shown in the third row of sub-figures, for each fire point data in the remaining source types of space-based data, temporary data and spatial data, the modified Haversine formula is used The latitude and longitude coordinates of every two fire point data in the remaining source types are calculated to obtain the Haversine distance between the fire point data and the fire point data of the target source type. The latitude and longitude coordinates of the first fire point (for example, point A) can be expressed as ( , ), the latitude and longitude coordinates of the second fire point (for example, point B) can be expressed as ( , ), α Represents the latitude coordinate in the above longitude and latitude coordinates, Represents the longitude coordinate in the above latitude and longitude coordinates, represents the calculated distance between the first fire point (e.g. point A) and the second fire point (e.g. point B) on the earth's surface. Represents the radius of the earth (which can be 6371 kilometers). Then, for two fire point data with the same data source type, the modified Haversine formula is used to calculate the longitude and latitude coordinates of the two fire point data to obtain the spatial distance between the two fire points.

[0067] Step S135b: Filter out from the multiple sub-clusters the sub-cluster where the target fire point having the smallest Haversine distance between the fire point data of the target source type in the sub-cluster and the fire point data is located.

[0068] Step S135c: classify the fire point data into the sub-cluster where the target fire point is located.

[0069] The implementation method of the above steps S135b to S135c is, for example: the fire point data is classified into multiple sub-clusters under the cluster according to their respective spatial distances, and specifically the sub-cluster where the target fire point is located with the smallest Haversine distance between the fire point data of the target source type in the sub-cluster and the fire point data is located is selected from the multiple sub-clusters, and the fire point data is classified into the sub-cluster where the target fire point is located. The next cluster is selected, and the above steps S131 to S135 are repeated until all clusters are processed.

[0070] As an optional implementation of the above step S140, when the above-mentioned fusion positioning of all the fire point data under the sub-cluster is performed, an iterative method can be used to perform fusion positioning, and this implementation may include:

[0071] Step S141: assigning initial weights to all the fire point data under the sub-cluster according to the data source type.

[0072] An implementation example of the above-mentioned step S141 is as follows: taking the fire point data from four different sources, namely, space-based data (Space), near-based data (Near), air-based data (Sky) and / or ground-based data (Surface), as an example, assuming that the error range of the fire point data from these four different sources from the actual fire point is arranged from small to large (10m, 50m, 250m, 1000m); the ratio is 1:5:25:100; the weight of the smallest error is fixed at 250, and the remaining sources are assigned values ​​in proportion, such as if the error of 50m is five times that of 10m, its weight is set to one-fiftieth of 250, that is, 5; and if the error of 250m is five times that of 50m, its weight is set to one-fiftieth of 5, that is, 0.1; similarly, if the error of 1000m is four times that of 250m, its weight is set to one-fortieth of 0.1, that is, 0.0025.

[0073] Therefore, the formula Assign initial weights to all fire point data under the sub-cluster according to the data source type; The error range is Small data source type, The error range is Small data source type errors, The error range is Initial weights for small data source types.

[0074] Step S142: According to the initial weights of all the fire point data under the sub-cluster, weighted calculation is performed on the longitude and latitude coordinates in all the fire point data under the sub-cluster to obtain the coordinates of the center point of the sub-cluster.

[0075] The implementation method of the above step S142 is, for example, to use the formula The initial weights of all the fire point data under the sub-cluster and the longitude and latitude coordinates of all the fire point data under the sub-cluster are weighted to obtain the center point coordinates of the sub-cluster. are the (temporary) center coordinates of the subcluster, Indicates the first Fire point data, is the first The longitude and latitude coordinates of the fire point data, Indicates the total number of all fire point data under this sub-cluster, Indicates the first The weight corresponding to each fire point data.

[0076] Step S143: for each fire point data in all the fire point data under the sub-cluster, calculate the spatial distance between the longitude and latitude coordinates in the fire point data and the coordinates of the center point of the sub-cluster.

[0077] As an optional implementation of the above step S143, the above implementation of calculating the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster may include: using the modified Haversine algorithm formula The Haversine distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster is calculated, and the Haversine distance is determined as the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster. The longitude and latitude coordinates in the fire point data can be expressed as ( , ), the coordinates of the center point of the subcluster can be expressed as ( , ), α Represents the latitude coordinate in the above longitude and latitude coordinates, Represents the longitude coordinate in the above latitude and longitude coordinates, Represents the calculated distance between the longitude and latitude coordinates of the fire point data on the earth's surface and the coordinates of the center point of the subcluster. Represents the radius of the earth (which can be 6371 kilometers). Then, the modified Haversine formula is used to calculate the longitude and latitude coordinates of the two fire point data to obtain the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster.

[0078] Step S144: Optimize and update the initial weight of the fire point data according to the spatial distance to obtain the updated weight of the fire point data.

[0079] The implementation method of the above step S144 is, for example: The spatial distance and the initial weight of the fire point data are optimized and updated to obtain the updated weight of the fire point data; wherein, represents the update weight of the fire point data, Represents an empirical value, which can be determined by binary search to find the best value, for example, 2.09, etc. It is the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the subcluster.

[0080] Step S145: According to the update weights of all the fire point data under the sub-cluster, the coordinates of the center point of the sub-cluster are iteratively optimized until the iteration stop condition is met to obtain the positioning coordinates of the sub-cluster.

[0081] An example of an implementation of the above step S145 is as follows: since the initial weight of the fire point data has been optimized and updated, it is necessary to iteratively optimize the original center point coordinates of the sub-cluster based on the updated weights of all the fire point data under the sub-cluster, that is, to calculate the new center point coordinates of the sub-cluster using the updated weights of all the fire point data under the sub-cluster. Then, since the center point coordinates of the sub-cluster have changed, that is, from the original center point coordinates to the new center point coordinates, it is necessary to re-update the weights of all the fire point data under the sub-cluster based on the new center point coordinates, and the optimization is iteratively repeated in sequence. Among them, the iteration conditions include: the number of iterations of the weighted calculation of the center point coordinates of the sub-cluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the sub-cluster and the center point coordinates calculated by the weighted calculation of the sub-cluster in the last iteration is less than a preset distance threshold.

[0082] In the implementation of the above scheme, by assigning initial weights to fire point data of different source types and performing weighted calculations, more accurate center point coordinates can be obtained. The weights are adjusted in a dynamic iterative optimization manner based on the spatial distance between the fire point data and the center point coordinates, ensuring that data closer to the center point accounts for a larger proportion in the calculation. This iterative optimization process effectively considers the importance of different data sources, so that the geographic coordinates of the center point are closer to the actual coordinates of the fire point, effectively improving the accuracy of the fire point fusion positioning.

[0083] See also Figure 4 The flowchart of the fire point fusion positioning device provided in the embodiment of the present application is shown; the embodiment of the present application provides a fire point fusion positioning device 200, including:

[0084] The fire point data acquisition module 210 is used to acquire a plurality of fire point data, and the fire point data includes: longitude and latitude coordinates and data source type.

[0085] The first data clustering module 220 is used to cluster the multiple fire point data according to the longitude and latitude coordinates to obtain multiple clusters.

[0086] The second data clustering module 230 is used to cluster all the fire point data under each cluster among the multiple clusters according to the data source type and the spatial distance between the fire point data to obtain multiple sub-clusters under the cluster, and the spatial distance between the fire point data is calculated based on the latitude and longitude coordinates of the fire point data.

[0087] The positioning coordinate obtaining module 240 is used to perform fusion positioning on all the fire point data under each of the multiple subclusters under the cluster type, so as to obtain the positioning coordinates of the subcluster.

[0088] As an optional implementation of the above device, the first data clustering module includes:

[0089] The spatial distance calculation submodule is used to calculate the longitude and latitude coordinates of two fire point data among the multiple fire point data to obtain the spatial distance between the two fire points.

[0090] The fire point data clustering submodule is used to cluster multiple fire point data according to spatial distance.

[0091] As an optional implementation of the above device, the second data clustering module includes:

[0092] The fire point number acquisition submodule is used to count all fire point data under the cluster according to the data source type, and obtain the number of fire points of multiple data source types.

[0093] The source type screening submodule is used to screen out the target source type with the largest number of fire points and the remaining source types from multiple data source types.

[0094] The cluster sub-cluster creation sub-module is used to create multiple sub-clusters under the cluster based on all the fire point data of the target source type.

[0095] The target fire point classification submodule is used to classify all fire point data of the target source type into multiple subclusters under the type cluster.

[0096] The remaining fire point classification submodule is used to classify each fire point data in the remaining source type into multiple subclusters under the type cluster according to the spatial distance between the fire point data and the fire point data of the target source type.

[0097] As an optional implementation of the above device, the remaining fire points are divided into submodules, including:

[0098] The Haversine distance calculation unit is used to calculate the Haversine distance between each fire point data in the remaining source types and the fire point data of the target source type according to the longitude and latitude coordinates.

[0099] The minimum distance sub-cluster screening unit is used to screen out the sub-cluster where the target fire point with the minimum Haversine distance between the fire point data of the target source type in the sub-cluster and the fire point data is located from multiple sub-clusters.

[0100] The fire point data is divided into sub-cluster units, which are used to divide the fire point data into the sub-cluster where the target fire point is located.

[0101] As an optional implementation of the above device, the positioning coordinate acquisition module includes:

[0102] The initial weight assignment submodule is used to assign initial weights to all the fire point data under the subcluster according to the data source type.

[0103] The central coordinate fire point submodule is used to perform weighted calculation on the longitude and latitude coordinates of all the fire point data under the subcluster according to the initial weights of all the fire point data under the subcluster to obtain the central point coordinates of the subcluster.

[0104] The coordinate distance calculation submodule is used to calculate the spatial distance between the longitude and latitude coordinates in each fire point data in all the fire point data under the subcluster and the coordinates of the center point of the subcluster.

[0105] The weight optimization and updating submodule is used to optimize and update the initial weight of the fire point data according to the spatial distance to obtain the updated weight of the fire point data.

[0106] The center coordinate optimization submodule is used to iteratively optimize the center point coordinates of the subcluster according to the update weights of all the fire point data under the subcluster until the stop iteration condition is met to obtain the positioning coordinates of the subcluster.

[0107] The iteration conditions include: the number of iterations of weighted calculation of the center point coordinates of the sub-cluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the sub-cluster and the center point coordinates of the sub-cluster calculated by weighted calculation in the previous iteration is less than a preset distance threshold.

[0108] As an optional implementation of the above device, the coordinate distance calculation submodule includes:

[0109] The coordinate distance calculation unit is used to calculate the Haversine distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster using the Haversine algorithm formula.

[0110] The spatial distance determination unit is used to determine the Haversine distance as the spatial distance between the longitude and latitude coordinates in the fire point data and the center point coordinates of the sub-cluster.

[0111] It should be understood that the device corresponds to the above-mentioned fire point fusion positioning method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the description above, and the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0112] See also Figure 5The electronic device 300 provided in the embodiment of the present application includes: a processor 310 and a memory 320, wherein the memory 320 stores machine-readable instructions executable by the processor 310, and when the machine-readable instructions are executed by the processor 310, the above method is executed.

[0113] The embodiment of the present application also provides a computer-readable storage medium 330, on which a computer program is stored, and the computer program is executed by the processor 310 to execute the above method. The computer-readable storage medium 330 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.

[0114] The embodiment of the present application also provides a computer program product, including: a computer program or a computer instruction, and the computer program or the computer instruction executes the method described above when executed by a processor.

[0115] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0116] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiments described above are only schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, a program segment or a code, and a part of a module, a program segment or a code includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also be different from the order of occurrence marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which is mainly determined by the functions involved.

[0117] In addition, each functional module of each embodiment in the embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. In addition, in the description of this specification, the description of reference terms "one embodiment", "some embodiments", "example", "specific example", "some examples", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present application. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples without contradiction.

[0118] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. A fire point fusion positioning method, characterized in that: include: Acquire multiple fire point data, wherein the fire point data includes: longitude and latitude coordinates and data source type; Clustering the plurality of fire point data according to the latitude and longitude coordinates to obtain a plurality of clusters; For each cluster among the multiple clusters, clustering all the fire point data under the cluster according to the data source type and the spatial distance between the fire point data to obtain multiple subclusters under the cluster, wherein the spatial distance between the fire point data is calculated based on the latitude and longitude coordinates of the fire point data; For each of the multiple subclusters under the cluster, all the fire point data under the subcluster are fused and located to obtain the location coordinates of the subcluster; Among them, all the fire point data under the cluster are clustered according to the spatial distance between the data source type and the fire point data, including: counting all the fire point data under the cluster according to the data source type to obtain the number of fire points of multiple data source types; screening out the target source type and the remaining source types with the largest number of fire points from the multiple data source types; creating multiple sub-clusters of the same number under the cluster according to all the fire point data of the target source type; dividing all the fire point data of the target source type into multiple sub-clusters under the cluster respectively; for each fire point data in the remaining source types, calculating the Haversine distance between the fire point data and the fire point data of the target source type according to the latitude and longitude coordinates; screening out the sub-cluster where the target fire point is located with the smallest Haversine distance between the fire point data of the target source type and the fire point data among the multiple sub-clusters; and dividing the fire point data into the sub-cluster where the target fire point is located; The method of fusing and locating all the fire point data under the subcluster includes: assigning an initial weight to all the fire point data under the subcluster according to the data source type; performing weighted calculation on the longitude and latitude coordinates of all the fire point data under the subcluster according to the initial weight of all the fire point data under the subcluster to obtain the coordinates of the center point of the subcluster; for each fire point data in all the fire point data under the subcluster, using the Haversine algorithm formula to calculate the Haversine distance between the longitude and latitude coordinates in the fire point data and the coordinates of the center point of the subcluster; and determining the Haversine distance as the fire point number. The spatial distance between the longitude and latitude coordinates in the data and the center point coordinates of the sub-cluster; the initial weight of the fire point data is optimized and updated according to the spatial distance to obtain the updated weight of the fire point data; according to the updated weight of all the fire point data under the sub-cluster, the center point coordinates of the sub-cluster are iteratively optimized until the stopping iteration condition is met to obtain the positioning coordinates of the sub-cluster; wherein the iterative condition includes: the number of iterations of the weighted calculation of the center point coordinates of the sub-cluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the sub-cluster and the center point coordinates of the sub-cluster calculated by weighted calculation in the last iteration is less than a preset distance threshold.

2. The method according to claim 1, characterized in that The clustering of the plurality of fire point data according to the latitude and longitude coordinates comprises: Calculating the longitude and latitude coordinates of two fire point data among the plurality of fire point data to obtain a spatial distance between the two fire points; The plurality of fire point data are clustered according to the spatial distance.

3. A fire point fusion positioning device, characterized in that: include: A fire point data acquisition module, used to acquire multiple fire point data, wherein the fire point data includes: longitude and latitude coordinates and data source type; A first data clustering module, used for clustering the plurality of fire point data according to the latitude and longitude coordinates to obtain a plurality of clusters; A second data clustering module is used for clustering all the fire point data under each cluster among the multiple clusters according to the data source type and the spatial distance between the fire point data to obtain multiple sub-clusters under the cluster; A positioning coordinate acquisition module is used to perform fusion positioning on all fire point data under each of the multiple subclusters under the cluster to obtain the positioning coordinates of the subcluster; Among them, all the fire point data under the cluster are clustered according to the spatial distance between the data source type and the fire point data, including: counting all the fire point data under the cluster according to the data source type to obtain the number of fire points of multiple data source types; screening out the target source type and the remaining source types with the largest number of fire points from the multiple data source types; creating multiple sub-clusters of the same number under the cluster according to all the fire point data of the target source type; dividing all the fire point data of the target source type into multiple sub-clusters under the cluster respectively; for each fire point data in the remaining source types, calculating the Haversine distance between the fire point data and the fire point data of the target source type according to the latitude and longitude coordinates; screening out the sub-cluster where the target fire point is located with the smallest Haversine distance between the fire point data of the target source type and the fire point data among the multiple sub-clusters; and dividing the fire point data into the sub-cluster where the target fire point is located; The method of fusing and locating all the fire point data under the subcluster includes: assigning an initial weight to all the fire point data under the subcluster according to the data source type; performing weighted calculation on the longitude and latitude coordinates of all the fire point data under the subcluster according to the initial weight of all the fire point data under the subcluster to obtain the coordinates of the center point of the subcluster; for each fire point data in all the fire point data under the subcluster, using the Haversine algorithm formula to calculate the Haversine distance between the longitude and latitude coordinates in the fire point data and the coordinates of the center point of the subcluster; and determining the Haversine distance as the fire point number. The spatial distance between the longitude and latitude coordinates in the data and the center point coordinates of the sub-cluster; the initial weight of the fire point data is optimized and updated according to the spatial distance to obtain the updated weight of the fire point data; according to the updated weight of all the fire point data under the sub-cluster, the center point coordinates of the sub-cluster are iteratively optimized until the stopping iteration condition is met to obtain the positioning coordinates of the sub-cluster; wherein the iterative condition includes: the number of iterations of the weighted calculation of the center point coordinates of the sub-cluster exceeds a preset threshold, or the spatial distance between the center point coordinates of the sub-cluster and the center point coordinates of the sub-cluster calculated by weighted calculation in the last iteration is less than a preset distance threshold.

4. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions are executed by the processor to perform the method according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 2 is executed.

6. A computer program product, characterized in that include: A computer program or a computer instruction, wherein when the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 2 is executed.

Images