Urban and rural area identification method and device, and medium
Through density aggregation and rasterization processing of POI data, combined with DBSCAN and Alpha Shape algorithms, the boundary characteristics of urban and rural areas are extracted, and the problem of insufficient efficiency and accuracy of urban and rural areas in the existing technology is solved, and efficient and accurate region recognition is achieved. and data analysis.
Patent Information
- Application Number
- CN202411344517.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2024-12-31
AI Technical Summary
The prior art cannot efficiently and accurately extract key features of urban and rural areas from a large number of POI data, resulting in insufficient efficiency and accuracy of urban and rural areas identification.
The density aggregation and rasterization processing of POI data are adopted, combined with the DBSCAN algorithm and the Alpha Shape algorithm, the boundary features of the cluster set are extracted, and the marking point sets of cities and township areas are generated, and the area to which the coordinate points to be identified belong is quickly identified through the ray method. .
It improves the efficiency and accuracy of urban and rural area identification, can automatically fit the regional profile, deeply analyze data characteristics, and continuously improve the calculation results without additional research and analysis.
Smart Images
Figure CN119226834A_ABST
Abstract
Description
[0001] Technology Neighborhood
[0002] The present application relates to the field of urban and rural management technology, and in particular to a method, device and medium for identifying urban and rural areas. Background Art
[0003] Urban-rural regional identification is a highly comprehensive and complex process that aims to accurately and meticulously divide geographic space based on a series of rigorous principles and standards, thereby clearly defining urban areas (areas in urban areas) and township areas. This process not only helps to clarify the development characteristics and resource conditions of different regions, but also provides valuable decision-making basis for public facility configuration and layout, land use and management, and urban and rural economic development research.
[0004] The identification of urban and rural areas is not a simple binary division made at random. Its comprehensiveness and complexity are reflected in the extensiveness and multidimensionality of the factors involved. In this process, POI data plays an indispensable role. As the core data of location services, it can provide rich geographic entity information. However, it is impossible to efficiently and accurately extract key features from a large amount of POI data for effective identification of urban and rural areas. Summary of the invention
[0005] The embodiments of the present application provide a method, device and medium for identifying urban and rural areas, which are used to solve the problem that key features cannot be efficiently and accurately extracted from a large amount of POI data to effectively identify urban and rural areas.
[0006] The present application embodiment adopts the following technical solutions:
[0007] On the one hand, an embodiment of the present application provides a method for identifying urban and rural areas, the method comprising: determining a POI category for identifying urban and rural areas; calling POI data for the target area for the POI category from a map platform; the POI data comprising the longitude, latitude and category of the POI; density clustering the POI data to generate multiple cluster sets, and screening out multiple available cluster sets from the multiple cluster sets; determining the maximum enclosing rectangle of each available cluster set, and rasterizing the available cluster sets according to the maximum enclosing rectangle to obtain a set of marked points for each available cluster set; extracting boundary features of the marked point set according to a scatter contour extraction algorithm to generate a set of boundary points for each available cluster set; determining the area surrounded by the boundary point set as an urban area, and determining the area in the target area other than the urban area as a township area.
[0008] In one example, the POI data is density clustered to generate multiple cluster sets, and multiple available cluster sets are screened out from the multiple cluster sets, specifically including: determining a neighborhood radius parameter value and a minimum number of points parameter value of a DBSCAN algorithm; clustering the POI data using the DBSCAN algorithm according to the neighborhood radius parameter value and the minimum number of points parameter value to obtain multiple cluster sets; sorting the multiple cluster sets in descending order according to the number of POIs in each cluster set, starting from the cluster set with the highest order, selecting a preset number of target cluster sets in turn, and determining the target cluster sets as available cluster sets; the preset number is related to the number of urban areas in the target area; determining non-target cluster sets other than the target cluster set in the multiple cluster sets; and determining the non-target cluster sets whose POI number difference with the target cluster set is less than a preset difference threshold as available cluster sets.
[0009] In one example, the available clustering sets are rasterized according to the maximum enclosing rectangle to obtain a marking point set for each available clustering set, specifically including: dividing the maximum enclosing rectangle into grids according to preset single grid data to obtain grid rectangles; calculating the center point of each grid in the grid rectangle to obtain a grid center point set for each available clustering set; calculating the number of internal POIs of the grid where each grid center point in the grid center point set is located; determining a target grid whose number of POIs is higher than a preset number threshold, and determining the grid center point of the target grid as a marking point.
[0010] In one example, the calculation of the number of internal POIs of the grid in which each grid center point in the grid center point set is located specifically includes: determining the longitude length and latitude length of the grid in which each grid center point in the grid center point set is located; determining a POI point whose absolute value of the longitude difference from the grid center point is less than or equal to half of the longitude length and whose absolute value of the latitude difference is less than or equal to half of the latitude length as the internal POI point of the grid in which the grid center point is located; and counting the number of internal POI points of the grid in which the grid center point is located.
[0011] In one example, the extraction of boundary features of the marked point set according to the scattered point contour extraction algorithm and the generation of the boundary point set of each available cluster set specifically include: determining the Alpha value interval of the Alpha Shape algorithm; determining the middle value of the Alpha value interval as the selected parameter, inputting the selected parameter and the marked point set of a single available cluster set into the Alpha Shape algorithm to obtain an output result, wherein the output result is a single or multiple boundary point sets; partitioning the Alpha value interval to extract Alpha value sub-intervals; based on the currently selected parameter, when the output boundary point set is single, the Alpha value sub-interval starts with the selected parameter and ends with the right endpoint of the Alpha value interval; when the output boundary point set is multiple, the Alpha value sub-interval starts with the left endpoint of the Alpha value interval and ends with the selected parameter; determining the middle value of the Alpha value sub-interval as the selected parameter; repeating the above-mentioned determination process of the selected parameter until partitioning cannot be performed, and determining the middle value corresponding to the last output boundary point set being single as the Alpha The Alpha parameter value of the Shape algorithm; and determining the boundary point set corresponding to the Alpha parameter value as the boundary point set of the single available cluster set.
[0012] In one example, after the area enclosed by the boundary point set is determined as an urban area and the area in the target area other than the urban area is determined as a township area, the method further includes: receiving the coordinate point to be identified uploaded by the client, and determining whether the coordinate point to be identified exists inside the maximum enclosing rectangle of a single boundary point set; if not, determining that the coordinate point to be identified is in the township area; if existing, determining whether the coordinate point to be identified is inside the boundary area of a single boundary point set; if so, determining that the coordinate point to be identified is in the urban area; if not, determining that the coordinate point to be identified is in the township area.
[0013] In one example, before determining whether the coordinate point to be identified exists inside the maximum enclosing rectangle of a single boundary point set, the method further includes: determining whether the coordinate point to be identified is inside the target area; if so, determining the coordinate point to be identified as a valid identification point.
[0014] On the other hand, an embodiment of the present application provides an urban and rural area identification device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the urban and rural area identification methods described above.
[0015] On the other hand, an embodiment of the present application provides a non-volatile computer storage medium for urban and rural area identification, which stores computer executable instructions, and the computer executable instructions can execute any of the above-mentioned methods for urban and rural area identification.
[0016] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0017] Driven by POI data, there is no need for additional research and analysis, and the calculation results can be continuously improved as the POI data is updated. Clustering and rasterization processing methods are used to obtain the marked point set of the available cluster set through clustering grouping and rasterization screening of POI data, which can improve data processing efficiency, deeply analyze and mine data features, and use the scattered point contour extraction algorithm to extract the boundary features of the marked point set. It can automatically fit the regional contour based on the overall distribution of POI data, which can improve the efficiency and accuracy of regional recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings, in which:
[0019] Figure 1 A schematic diagram of a flow chart of a method for identifying urban and rural areas provided in an embodiment of the present application;
[0020] Figure 2 A schematic diagram of a POI data cluster analysis provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of extracting boundary features from POI data provided in an embodiment of the present application;
[0022] Figure 4 A schematic diagram of a flow chart of another method for identifying urban and rural areas provided in an embodiment of the present application;
[0023] Figure 5 A schematic diagram of the structure of a device for identifying urban and rural areas provided in an embodiment of the present application. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0025] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0026] Figure 1 A schematic diagram of a process flow of a method for identifying urban and rural areas provided in an embodiment of the present application. Certain input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.
[0027] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
[0028] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.
[0029] Figure 1 The process in includes the following steps:
[0030] S101: Determine a POI category for identifying urban and rural areas.
[0031] Among them, POI is usually used to identify a specific point in a geographical location. Taking into account the correlation between the distribution of different categories of POIs and the distribution of urban and rural areas, the category of POI used can be determined through in-depth analysis of the problem of urban and rural area identification. In an example, the POI category used for urban and rural area identification is shown in Table 1.
[0032] Table 1
[0033]
[0034] S102: calling POI data of the target area for the POI category from the map platform; the POI data includes the longitude, latitude and category of the POI.
[0035] It should be noted that based on the request preset parameters, using a script program based on the corresponding programming language, by calling the open interface of the relevant map platform, the relevant data of all kinds of POI categories pre-set in the target area are obtained, and after parsing the obtained data, the POI ID, longitude, latitude, category name and other data are screened and extracted, and stored in a structured form as a csv file or a data table in a database as a POI dataset of the target area.
[0036] The POI ID refers to the unique identifier of the POI point, which is a number or string used to identify and distinguish different POIs. The category name refers to the category or type to which the POI belongs, for example, the category name is Chinese restaurant.
[0037] It should be noted that a single POI point refers to a specific point in a geographical location. For example, community A corresponds to a POI point.
[0038] S103: performing density clustering on the POI data to generate a plurality of cluster sets, and screening out a plurality of available cluster sets from the plurality of cluster sets.
[0039] In some embodiments of the present application, the POIs in S101 are usually densely distributed in urban areas, while they are relatively dispersed in township areas. Therefore, the available clustering set describing the urban distribution is screened to reduce the interference of outlier POIs that exist alone or in small clusters on the description of urban distribution characteristics. For example, the collected POI data is density clustered, and after cluster screening, an available clustering set is determined, in which a large number of available POI points are densely distributed and highly correlated with the overall distribution of the urban area.
[0040] Based on this, firstly, the neighborhood radius parameter value and the minimum number of points parameter value of the DBSCAN algorithm are determined.
[0041] It should be noted that the above-mentioned neighborhood radius parameter value and minimum number of points parameter value can be set according to actual needs.
[0042] Then, according to the neighborhood radius parameter value and the minimum number of points parameter value, the DBSCAN algorithm is used to cluster the POI data to obtain multiple cluster sets.
[0043] Then, according to the number of POIs in each cluster set, the multiple cluster sets are sorted in descending order, starting from the cluster set with the highest sorting, a preset number of target cluster sets are selected in turn, and the target cluster sets are determined as available cluster sets.
[0044] It should be noted that the preset number is related to the number of urban areas in the target area. For example, if the target area has 3 urban areas, the preset number may be 3. It should be noted that the preset number is not less than the number of urban areas.
[0045] Then, non-target cluster sets other than the target cluster set are determined among the plurality of cluster sets.
[0046] Finally, the non-target cluster set whose POI quantity difference with the target cluster set is less than a preset difference threshold is determined as an available cluster set.
[0047] It should be noted that, in theory, when a large area in a single urban area is relatively dense, it should be divided into one cluster set. However, due to the existence of isolated POI points during the clustering process, a large area in a single urban area may be divided into multiple cluster sets, which may cause a cluster set to be ranked relatively low. Therefore, a non-target cluster set with a similar number of POIs to the target cluster set is determined as an available cluster set.
[0048] For example, cluster set A includes 20 POI points, cluster set B includes 15 POI points, cluster set C includes 12 POI points, cluster set D includes 13 POI points, and cluster set E includes 8 POI points, then the descending order is cluster set A, cluster set B, cluster set D, cluster set C, and cluster set E. When the preset number is 3, the available cluster sets are cluster set A, cluster set B, and cluster set D.
[0049] When the preset difference threshold is 5, cluster set C will also be used as an available cluster set.
[0050] More intuitively, Figure 2 A schematic diagram of a POI data cluster analysis provided in an embodiment of the present application is shown in FIG. Figure 2 In the example, there is one available cluster set, multiple isolated POI points, and multiple unavailable cluster sets.
[0051] In some embodiments of the present application, the process of clustering POI data to obtain multiple cluster sets is as follows:
[0052] First, an unprocessed POI point is randomly selected in the POI data, and the neighborhood radius parameter is used as the radius to determine the neighboring POI points within the radius.
[0053] When the number of neighboring POI points is greater than or equal to the minimum number of points parameter, the POI point is marked as a core point, and the point set composed of neighboring POI points is used as its corresponding temporary cluster.
[0054] After processing all POI points in the POI data, a core point set and a temporary cluster corresponding to each core point can be determined.
[0055] A core point is randomly selected from the core point set, and the selected core point is removed from the core point set, and the temporary clustering cluster of the core point is used as the clustering set.
[0056] Find the overlapping points between the cluster set and the core point set, add the POI points in the temporary cluster corresponding to the overlapping points to the cluster set, and remove the overlapping points from the core point set.
[0057] Repeat the above process. If there are no overlapping points between the cluster set and the core point set, a cluster set is obtained, and core points are reselected from the core point set. Repeat the above process to continue generating new cluster sets until the core point set is empty.
[0058] S104: Determine the maximum enclosing rectangle of each available cluster set, and rasterize the available cluster set according to the maximum enclosing rectangle to obtain a set of marked points of each available cluster set.
[0059] In some embodiments of the present application, the process of obtaining the set of marked points for each available cluster set is as follows:
[0060] First, according to the preset single grid data, the maximum enclosing rectangle is divided into grids to obtain grid rectangles.
[0061] It should be noted that the grid data refers to the length of the grid in the longitude direction and the length in the latitude direction. The length here is not the distance, but the difference between the longitude and latitude. For example, starting from the coordinates of the lower left vertex of the largest enclosing rectangle, the grid is divided in sequence. Among them, the grid data of the upper right, lower right, and upper left vertices of the largest enclosing rectangle may be different from the preset grid data.
[0062] Then, the center point of each grid in the grid rectangle is calculated to obtain the grid center point set of each available cluster set.
[0063] The grid center point set can be expressed by the following expression:
[0064]
[0065] Among them, (x0, y0) is the coordinate of the lower left vertex of the maximum enclosing rectangle, l and h are the longitude and latitude lengths of the maximum enclosing rectangle respectively, α and β are the longitude and latitude lengths of the preset grid respectively, i and j are used to specify the grid position within the maximum enclosing rectangle, the grid cell in the i-th row and j-th column.
[0066] Then, the number of internal POIs of each grid center point in the grid center point set is calculated.
[0067] Finally, a target grid whose number of POIs is higher than a preset number threshold is determined, and the grid center point of the target grid is determined as a marking point.
[0068] In some embodiments of the present application, the process of calculating the number of internal POIs of each grid center point in the grid center point set is as follows:
[0069] First, the length in the longitude direction and the length in the latitude direction of the grid where each grid center point in the grid center point set is located are determined.
[0070] Then, the POI points whose absolute value of longitude difference from the grid center point is less than or equal to half of the longitude length and whose absolute value of latitude difference is less than or equal to half of the latitude length are determined as the internal POI points of the grid where the grid center point is located.
[0071] Finally, the number of POI points inside the grid where the center point of the grid is located is counted.
[0072] S105: extracting the boundary features of the marked point set according to the scattered point contour extraction algorithm, and generating a boundary point set for each available cluster set.
[0073] In some embodiments of the present application, the process of generating a boundary point set for each available cluster set is as follows:
[0074] First, determine the Alpha value range of the Alpha Shape algorithm.
[0075] It should be noted that the left endpoint of the Alpha value interval is 0, and the right endpoint can be set according to actual needs. You can also determine a value that makes the number of areas generated by the scattered contour extraction algorithm (the number of output boundary point sets) not 1, and use this value as the right endpoint.
[0076] Then, the middle value of the Alpha value interval is determined as the selected parameter, and the selected parameter and the marked point set of a single available cluster set are input into the Alpha Shape algorithm to obtain an output result, which is a single or multiple boundary point sets. It should be noted that when it is a single boundary point set, it means that the extracted boundary is a single area.
[0077] Then, the Alpha value interval is partitioned and the Alpha value sub-interval is extracted; for the selected parameter, when the number of output boundary point sets is single, the Alpha value sub-interval starts with the selected parameter and ends with the right endpoint of the Alpha value interval; when the number of output boundary point sets is multiple, the Alpha value sub-interval starts with the left endpoint of the Alpha value interval and ends with the selected parameter.
[0078] Then, the middle value of the Alpha value sub-interval is determined as the selected parameter.
[0079] Then, the above-mentioned process of determining the selected parameters is repeated until partitioning cannot be performed, and the intermediate value corresponding to the last output when the number of boundary point sets is a single one is determined as the Alpha parameter value of the Alpha Shape algorithm.
[0080] Finally, the boundary point set corresponding to the Alpha parameter value is determined as the boundary point set of a single available clustering set.
[0081] That is, when the number of output boundary point sets corresponding to the intermediate value is single, the intermediate value is continued to be searched from the right half of the intermediate value; when the number of output boundary point sets corresponding to the intermediate value is multiple, the intermediate value is continued to be searched from the left half of the intermediate value. It should be noted that the number of output boundary point sets input to the Alpha Shape algorithm by the intermediate value of the last partition must be single.
[0082] That is, for the process of extracting urban boundary features, a binary search algorithm is used to search for the algorithm preset parameters (Alpha rolling ball radius parameters) in a preset ordered array (Alpha value interval), and the Alpha parameter values and the marked point set are substituted into the AlphaShape algorithm. According to the algorithm's internal search and recognition rules, reasonable boundary points in the marked point set are identified, and the corresponding boundary point set is generated in the recognition order.
[0083] The boundary point set is obtained by extracting boundary features based on the marked point set corresponding to the available cluster set, and is used to define the urban area corresponding to the available cluster set. Figure 2 On the basis of determining the available clustering set corresponding to the marked point set, the Alpha Shape algorithm is used to automatically extract its boundary features in the two-dimensional plane, and the corresponding boundary point set can be obtained. The area defined by its contour is as follows Figure 3 As shown, it is highly consistent with the overall distribution of urban areas that can be described by available cluster sets. Figure 3 A schematic diagram of extracting boundary features from POI data provided in an embodiment of the present application, in Figure 3 It is shown in Figure 2 The set of labeled points and the set of boundary points of the available clustering sets.
[0084] S106: Determine the area surrounded by the boundary point set as an urban area, and determine the area in the target area other than the urban area as a township area.
[0085] In some embodiments of the present application, after urban and rural areas are identified for a target area, when receiving coordinate points to be identified uploaded by a client, a ray method is used to identify the type of area to which the coordinate points belong.
[0086] Based on this, the coordinate point to be identified uploaded by the client is received, and it is determined whether the coordinate point to be identified is inside the target area.
[0087] When , the coordinate point to be identified is determined as a valid identification point.
[0088] When it is not, the coordinate point to be identified is determined as an invalid identification point.
[0089] When the coordinate point to be identified is determined to be a valid identification point, it is determined whether the coordinate point to be identified exists inside the maximum enclosing rectangle of a certain boundary point set.
[0090] It should be noted that the positional relationship between the coordinate point and the maximum enclosing rectangle of a single boundary point set is identified by directly comparing the longitude and latitude.
[0091] When it does not exist, it is determined that the coordinate point to be identified is in the township area.
[0092] If it exists, it is determined whether the coordinate point to be identified is within the boundary area of the single boundary point set.
[0093] It should be noted that the positional relationship between the coordinate point and the boundary area is identified using the ray method.
[0094] When it is in, it is determined that the coordinate point to be identified is in the urban area.
[0095] When it is not in the township area, it is determined that the coordinate point to be identified is in the township area.
[0096] It should be noted that since the boundary area is irregular and the distribution of boundary point sets is irregular and numerous, the calculation is complicated. Therefore, it is necessary to pre-judge whether it is in the target area and continue to judge whether it is inside the maximum enclosing rectangle corresponding to the boundary point set, rather than directly judging whether it is inside the boundary area. This can quickly identify that the coordinate point is in the township area, especially when the amount of data is large, thereby improving the recognition efficiency.
[0097] In summary, in order to extract key features from a large amount of POI data, realize the effective identification of urban and rural areas, and provide a scientific and reliable decision-making basis for the subsequent configuration and layout of public facilities, a method for urban and rural area identification based on POI data is proposed. The core of this method is to combine clustering algorithm and scattered point contour extraction algorithm to conduct in-depth mining and analysis of POI data, efficiently extract regional boundary features, clearly define urban areas and township areas, and combine ray method to realize rapid and accurate identification of the area type to which the coordinate points to be identified belong.
[0098] It should be noted that although the embodiments of the present application are based on Figure 1 Steps S101 to S106 are described in sequence, but this does not mean that steps S101 to S106 must be performed in a strict order. Figure 1 The order shown in the figure is to introduce and explain step S101 to step S106 in sequence, in order to facilitate the technical personnel in the field to understand the technical solution of the embodiment of the present application. In other words, in the embodiment of the present application, the order between step S101 to step S106 can be appropriately adjusted according to actual needs.
[0099] pass Figure 1The method is driven by POI data, does not require additional research and analysis, and can continuously improve the calculation results as the POI data is updated. Clustering and rasterization processing methods are used to obtain the marked point set of the available cluster set through clustering grouping and rasterization screening of POI data, which can improve data processing efficiency, deeply analyze and mine data features, and use the scattered point contour extraction algorithm to extract the boundary features of the marked point set. It can automatically fit the regional contour based on the overall distribution of POI data, which can improve the efficiency and accuracy of regional recognition.
[0100] More intuitively, Figure 4 A flowchart of another method for identifying urban and rural areas provided in an embodiment of the present application. Figure 4 In the method, the server interface calls the POI data source, collects POI data to obtain POI raw data, parses and filters the POI data, obtains the ID, longitude, latitude, and category name of the POI, obtains the POI data set of the target area, clusters the POI coordinates according to the DBSCAN algorithm to obtain a cluster set, filters the cluster set to obtain available cluster set 1, available cluster set 2...available cluster set n, uses a rasterization processing method to determine the marking points, obtains marking point set 1, marking point set 2...marking point set n, uses the Alpha Shape algorithm to extract boundary features, obtains boundary point set 1, boundary point set 2...boundary point set n.
[0101] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above methods.
[0102] Figure 5 A schematic diagram of a structure of a device for identifying urban and rural areas provided in an embodiment of the present application includes:
[0103] at least one processor; and,
[0104] a memory communicatively connected to the at least one processor; wherein,
[0105] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned methods for identifying urban and rural areas.
[0106] Some embodiments of the present application provide a non-volatile computer storage medium for urban and rural area identification, which stores computer executable instructions, and the computer executable instructions can execute any of the above-mentioned methods for urban and rural area identification.
[0107] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0108] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0109] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0113] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0114] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0115] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0117] The above description is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the technical principle of the present application shall fall within the protection scope of the present application.
Claims
1. A method for identifying urban and rural areas, characterized in that: The method comprises: Determine POI categories for identifying urban and rural areas; Calling POI data of the target area for the POI category from the map platform; the POI data includes the longitude, latitude and category of the POI; Performing density clustering on the POI data to generate a plurality of cluster sets, and screening out a plurality of available cluster sets from the plurality of cluster sets; Determine the maximum enclosing rectangle of each available cluster set, and rasterize the available cluster set according to the maximum enclosing rectangle to obtain a set of marked points of each available cluster set; Extracting the boundary features of the marked point set according to a scattered point contour extraction algorithm to generate a boundary point set for each available cluster set; The area surrounded by the boundary point set is determined as the urban area, and the area in the target area other than the urban area is determined as the township area.
2. The method according to claim 1, characterized in that The step of performing density clustering on the POI data to generate a plurality of cluster sets, and screening out a plurality of available cluster sets from the plurality of cluster sets specifically includes: Determine the neighborhood radius parameter value and the minimum number of points parameter value of the DBSCAN algorithm; Clustering the POI data using a DBSCAN algorithm according to the neighborhood radius parameter value and the minimum number of points parameter value to obtain a plurality of cluster sets; According to the number of POIs in each cluster set, the plurality of cluster sets are sorted in descending order, starting from the cluster set with the highest sorting, a preset number of target cluster sets are selected in turn, and the target cluster sets are determined as available cluster sets; the preset number is related to the number of urban areas in the target area; Determine a non-target cluster set other than the target cluster set among the multiple cluster sets; A non-target cluster set whose POI quantity difference with the target cluster set is less than a preset difference threshold is determined as an available cluster set.
3. The method according to claim 1, characterized in that The step of rasterizing the available cluster sets according to the maximum enclosing rectangle to obtain a set of marking points for each available cluster set specifically includes: According to the preset single grid data, the maximum outer bounding rectangle is divided into grids to obtain grid rectangles; Calculate the center point of each grid in the grid rectangle to obtain a grid center point set for each available cluster set; Calculate the number of POIs inside the grid where each grid center point in the grid center point set is located; A target grid having a number of POIs greater than a preset number threshold is determined, and a grid center point of the target grid is determined as a marking point.
4. The method according to claim 3, characterized in that The calculating the number of POIs inside the grid where each grid center point in the grid center point set is located specifically includes: Determine the length in the longitude direction and the length in the latitude direction of the grid where each grid center point in the grid center point set is located; Determine a POI point whose absolute value of longitude difference from the center point of the grid is less than or equal to half of the length in the longitude direction and whose absolute value of latitude difference is less than or equal to half of the length in the latitude direction as an internal POI point of the grid where the center point of the grid is located; The number of POI points inside the grid where the center point of the grid is located is counted.
5. The method according to claim 1, characterized in that The step of extracting the boundary features of the marked point set according to the scattered point contour extraction algorithm and generating the boundary point set of each available cluster set specifically includes: Determine the Alpha value range of the Alpha Shape algorithm; Determine the middle value of the Alpha value interval as a selected parameter, input the selected parameter and a marked point set of a single available cluster set into the Alpha Shape algorithm to obtain an output result, wherein the output result is a single or multiple boundary point sets; Partition the Alpha value interval to extract Alpha value subintervals; based on the currently selected parameter, when the output boundary point set is single, the Alpha value subinterval starts with the selected parameter and ends with the right endpoint of the Alpha value interval; when the output boundary point set is multiple, the Alpha value subinterval starts with the left endpoint of the Alpha value interval and ends with the selected parameter; Determine the middle value of the Alpha value sub-interval as the selected parameter; Repeat the above-mentioned process of determining the selected parameters until partitioning cannot be performed, and determine the intermediate value corresponding to the last output when the number of boundary point sets is a single one as the Alpha parameter value of the Alpha Shape algorithm; The boundary point set corresponding to the Alpha parameter value is determined as the boundary point set of the single available cluster set.
6. The method according to claim 1, characterized in that After determining the area surrounded by the boundary point set as the urban area and determining the area in the target area other than the urban area as the township area, the method further includes: Receive the coordinate point to be identified uploaded by the client, and determine whether the coordinate point to be identified exists inside the maximum bounding rectangle of a single boundary point set; If it does not exist, determining that the coordinate point to be identified is in a township area; If it exists, determining whether the coordinate point to be identified is within the boundary area of the single boundary point set; When the coordinate point to be identified is in an urban area, determining that the coordinate point to be identified is in an urban area; When it is not located in the township area, it is determined that the coordinate point to be identified is located in the township area.
7. The method according to claim 6, characterized in that Before determining whether the coordinate point to be identified exists inside the maximum bounding rectangle of a single boundary point set, the method further includes: Determine whether the coordinate point to be identified is inside the target area; When , the coordinate point to be identified is determined as a valid identification point.
8. A device for identifying urban and rural areas, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for identifying urban and rural areas as described in any one of claims 1 to 7.
9. A non-volatile computer storage medium for urban and rural area identification, storing computer executable instructions, characterized in that: The computer executable instructions can execute the method for identifying urban and rural areas as described in any one of claims 1 to 7.