A POI-based land classification subdivision method, device, storage medium and terminal device
Through the POI-based land subdivision method, urban land use is subdivided, which solves the problems of insufficient classification refinement and time-consuming and labor-consuming in the existing technology, and realizes efficient land use data conversion and update.
Patent Information
- Application Number
- CN202210012976.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-06
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-01-06
AI Technical Summary
The existing technology is difficult to meet the detailed hierarchical requirements in urban land use classification. The effect of remote sensing classification is limited, manual investigation is time-consuming and labor-intensive and difficult to meet the data update requirements.
Using the POI-based land subdivision method, the POI data and surface data are classified and processed, and the plots are divided and classified according to the requirements of the target land use classification system. The POI category priority and quantity are used to assign the plots. Category and buffer analysis if necessary to determine the category of the plot.
The subdivision of land use classification data is realized, the time and manpower of manual investigation is saved, the timeliness of data is improved, and data conversion can be carried out between different land use classification systems.
Smart Images

Figure CN114663442B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of land use classification, and in particular to a POI-based land classification method, device, storage medium and terminal equipment. Background Art
[0002] Urban land use classification is the premise of urban construction and planning management, and can provide a basis for the realization of sustainable use of land resources. At present, there are many land use classification systems in various countries and regions around the world, and there are large differences between different classification systems. To convert land use data under one classification system into data under another classification system, it is generally necessary to reclassify and subclassify the data before conversion. At the same time, land use classification (land type) under a single land use classification system generally has different levels. Each first-level land type (coarser class) contains several second-level classes (finer classes), and a second-level class can be subdivided into several third-level classes, etc. Using the existing coarse class data to form finer class data also requires the subdivision of land types.
[0003] When performing land classification subdivision, the existing methods are mostly remote sensing-based classification methods and manual survey methods. The use of remote sensing-based classification methods for land classification subdivision is effective for natural land, but the classification effect on urban internal land and construction land is limited, and it is difficult to meet the requirements of a more detailed level of the classification system. Using manual surveys to subdivide urban internal land and construction land can meet the requirements of a more detailed level of the classification system, but it consumes a lot of manpower, financial resources, and time-consuming, and it is difficult to meet the requirements for frequent updates of land classification data.
[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention
[0005] In view of the above-mentioned deficiencies in the prior art, an object of the present invention is to provide a POI-based land classification method, apparatus, storage medium and terminal device to achieve conversion between different land use classification systems.
[0006] The technical solution of the present invention is as follows:
[0007] A land classification method based on POI, comprising the steps of:
[0008] Classify the collected POI data and surface data to obtain classification results;
[0009] Determine the category and quantity of POIs contained in each block in the original land use classification data based on the classification result;
[0010] If the land parcel contains only one type of POI, assign the category to which the POI belongs to the land parcel;
[0011] If the land parcel contains multiple types of POIs, the land parcel is segmented by plane data, and then the types of plane data and POIs are assigned to the segmented land parcels according to a predetermined priority. For the land parcels that still have no categories after segmentation, they are classified into the categories to which the land parcels closest to them belong;
[0012] If the land parcel does not contain a POI or contains a POI but has no category, a buffer analysis is performed on the land parcel to determine the category and quantity of the POI contained in the land parcel again, and then the land parcel is classified based on the category and quantity of the POI contained in the land parcel.
[0013] The POI-based land classification method, wherein the steps of classifying the collected POI data and surface data to obtain the classification results include:
[0014] Reclassify POI data with category information according to the classification requirements of the target land use classification system;
[0015] For the area data without category information, firstly calculate the number of various POIs from government-published data contained in the area data, and combine the priority of POI categories to take the category with high priority or the largest number of POIs as the category of the area data; if the area data still has no category, calculate the number of various POIs from non-government-published data contained in the area data, and combine the priority of POI categories to take the category with high priority or the largest number of POIs as the category of the area data;
[0016] According to the classification requirements of the target land use classification system, the surface data with existing category information is classified.
[0017] The POI-based land classification method, wherein the POI data collection method includes: obtaining existing POI data from various platforms, including government-published data and non-government-published data, including but not limited to POI data obtained from government websites, Amap, Baidu Map, Tencent Map, or converting surface data into POI data.
[0018] The POI-based land classification method, wherein the surface data includes surface data of a single place and surface data of a combination of multiple places, the surface data of a single place includes building data and transportation station polygon data; the surface data of a combination of multiple places includes data of buildings and their annexes, and the surface data is obtained from government-published data and non-government-published data, including but not limited to surface data obtained from government websites and OpenStreetMap.
[0019] The POI-based land classification method, wherein judging the category and quantity of POIs contained in each block in the original land use classification data based on the classification result, comprises the following steps:
[0020] According to the categories and numbers of POIs contained in each plot in the original land use classification data, the plots are divided into plots containing only one category of POI, plots containing multiple categories of POIs, plots containing no POI, and plots containing POIs but no category.
[0021] The POI-based land classification method, wherein if the land parcel contains multiple types of POIs, the land parcel is subjected to hierarchical segmentation of surface data, and then the surface data and the types of POIs are assigned to the segmented land parcels according to a predetermined priority, and for the land parcels that still have no categories after segmentation, the steps of classifying them into the categories to which the land parcels closest to them belong include:
[0022] The surface data P1 representing multiple place combinations is preferentially used to segment the plots containing multiple POIs. Before segmentation, the ratio S of the sum of the areas of all the surface data P1 contained in each plot to be segmented to the area of the plot is calculated. i , i=1,2,...,p, p is the number of plots containing multiple POIs, the threshold value δ1 of the area ratio is determined according to the actual situation, for the plots to be segmented whose area ratio is greater than or equal to the threshold δ1, only the surface data P1 in the plot is used for segmentation, and the segmented plots are assigned the categories corresponding to the surface data P1;
[0023] For the area ratio S i For the plots to be divided that are smaller than the threshold δ1 and the plots to be divided that do not intersect with the surface data P1, if the plot to be divided contains surface data P representing a single location, the ratio BS of the sum of the areas of all the surface data P contained in the plot to be divided to the area of the plot is calculated. j , j = 1, 2, ..., q, q is the area ratio S i The number of plots to be divided that are less than the threshold δ1 and do not intersect with the surface data P1, and the threshold δ2 of the area ratio is determined according to the actual situation. For area BS j For the plots to be segmented that are greater than or equal to the threshold δ2, only the surface data P inside the plots are used for segmentation, and the corresponding surface data P is assigned to the segmented plots;
[0024] For area BS jFor a plot of land to be segmented that is smaller than the threshold value δ2, if the plot of land to be segmented contains both the surface data P representing a single place and the surface data P1 representing a combination of multiple places, the surface data P1 representing the combination of multiple places is preferentially used for segmentation, and then the surface data P representing a single place that does not intersect with the surface data P1 is used for segmentation, and the categories of the corresponding surface data P1 and P are respectively assigned to the segmented plot. If the plot of land to be segmented only contains the surface data P representing a single place, only the surface data P is used for segmentation, and the category of the corresponding surface data P is assigned to the segmented plot;
[0025] For the plots of land that have been segmented into layers using the surface data, the fragmented plots that still have no category after segmentation are classified into the category to which the nearest existing category plot belongs within a certain distance;
[0026] When using POI to determine the land parcel category, the POI category is set with corresponding priority for different land use categories;
[0027] For plots of land that do not contain polygon data and contain POIs of multiple categories, we first calculate the number of POIs of each category from government-published data in each plot, and combine the priority of the POI category to take the category with a high priority or the largest number of POIs as the category of the plot. If the plot still has no category, we calculate the number of POIs of each category from non-government-published data in each plot, and combine the priority of the POI category to take the category with a high priority or the largest number of POIs as the category of the plot.
[0028] A POI-based land classification device, comprising:
[0029] The classification module is used to classify the collected POI data and surface data to obtain classification results;
[0030] A judgment module, used for judging the category and quantity of POIs contained in each block in the original land use classification data based on the classification result;
[0031] A first category assigning module, used for assigning the category to which the POI belongs to the land parcel when the land parcel contains only one category of POI;
[0032] The second category assignment module is used to perform hierarchical segmentation of the surface data of the land parcel when the land parcel contains multiple categories of POIs, and then assign the categories of the surface data and POIs to the segmented land parcels according to a predetermined priority, and for the land parcels that still have no category after segmentation, classify them into the category to which the land parcel closest to them belongs;
[0033] The third category assignment module is used to perform a buffer analysis on the land parcel, and then determine the category and number of POIs contained in the land parcel again when the land parcel does not contain a POI or the land parcel contains a POI but has no category, and then classify the land parcel based on the category and number of POIs contained in the land parcel.
[0034] The POI-based land classification device, wherein the classification module includes:
[0035] The first classification unit is used to reclassify the POI data with category information according to the classification requirements of the target land use classification system;
[0036] The second classification unit is used for calculating the number of various POIs from government-published data contained in the surface data without category information, and taking the category with high priority or the largest number of POIs as the category of the surface data in combination with the priority of the POI category; if the surface data still has no category, calculating the number of various POIs from non-government-published data contained in the surface data, and taking the category with high priority or the largest number of POIs as the category of the surface data in combination with the priority of the POI category;
[0037] The third classification unit is used to classify the surface data with existing category information according to the classification requirements of the target land use classification system.
[0038] A storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the POI-based land classification method of the present invention.
[0039] A terminal device, comprising: a processor, a memory and a communication bus; the memory stores a computer-readable program executable by the processor;
[0040] The communication bus realizes the connection and communication between the processor and the memory;
[0041] When the processor executes the computer-readable program, the steps in the POI-based land classification method of the present invention are implemented.
[0042] Beneficial effects: The present invention uses POI data and surface data to segment and classify the original land use data according to certain rules, which can better achieve the subdivision of land use classification data, save a lot of manpower and time consumed by manual investigation in traditional land use subdivision methods, and improve the timeliness of data. The present invention can be used for land use subdivision and conversion between two different land use classification systems, and can also be used for land use subdivision under a single land use classification system. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 The figure is a flow chart of a preferred embodiment of a POI-based land classification method of the present invention.
[0044] Figure 2a A land use classification diagram of a certain land type of "government, institutions and community facilities" provided in an embodiment of the present invention.
[0045] Figure 2b A reference map of the target land use classification system provided for the embodiment of the present invention.
[0046] Figure 3 A schematic diagram of the classification results of the land use subclassification method provided in an embodiment of the present invention.
[0047] Figure 4 It is a schematic diagram of the terminal device of the present invention. DETAILED DESCRIPTION
[0048] The present invention provides a POI-based land classification subdivision method, device, storage medium and terminal device. In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0049] See also Figure 1 , Figure 1 A flowchart of a preferred embodiment of a POI-based land classification method provided by the present invention is shown in the figure, which includes the following steps:
[0050] S10, classifying the collected POI data and surface data to obtain classification results;
[0051] S20, determining the category and quantity of POIs contained in each block in the original land use classification data based on the classification result;
[0052] S30, if the land parcel contains only one category of POI, assigning the category to which the POI belongs to the land parcel;
[0053] S40, if the land parcel contains multiple types of POIs, the land parcel is segmented by plane data, and the types of the plane data and POIs are assigned to the segmented land parcels according to a predetermined priority, and for the land parcels that still have no categories after segmentation, they are classified into the categories to which the land parcels closest to them belong;
[0054] S50: If the land parcel does not contain a POI or the land parcel contains a POI but has no category, then after performing a buffer analysis on the land parcel, determine again the category and quantity of the POI contained in the land parcel, and then classify the land parcel based on the category and quantity of the POI contained in the land parcel.
[0055] This embodiment uses POI data and building and other surface data in combination, and divides and classifies the original land use data according to certain rules, which can better achieve the subdivision of land use classification data, save a lot of manpower and time consumed by manual surveys using traditional land use subdivision methods, and improve the timeliness of data. The present invention can be used for land use subdivision and conversion of data between two different land use classification systems, and can also be used for land use subdivision under a single land use classification system.
[0056] In some embodiments, the steps of classifying the collected POI data and surface data to obtain the classification results include: reclassifying the POI data with category information according to the classification requirements of the target land use classification system; for surface data without category information, firstly calculating the number of various POIs from government-published data contained in the surface data, combining the priority of the POI category, taking the category with high priority or the largest number of POIs as the category of the surface data; if the surface data still has no category, then calculating the number of various POIs from non-government-published data contained in the surface data, combining the priority of the POI category, taking the category with high priority or the largest number of POIs as the category of the surface data; classifying the surface data with existing category information according to the classification requirements of the target land use classification system. According to the classification results, a new "category" field is created in the attribute table of the POI data and the surface data to store the classified categories.
[0057] In this embodiment, the method of obtaining POI data includes but is not limited to: obtaining existing POI data from various platforms, including government-published data and non-government-published data, including but not limited to POI data obtained from government websites, Amap, Baidu Map, Tencent Map, or converting surface data into POI data. In this embodiment, the surface data obtained includes but is not limited to: surface data representing a single place, such as building data, transportation station polygon data, etc.; surface data representing a combination of multiple places, such as surface data containing buildings and their annexes, etc. The sources of obtaining surface data include government-published data and non-government-published data, including but not limited to surface data obtained from government websites and OpenStreetMap.
[0058] In some embodiments, the plots are divided into plots containing only one category of POI, plots containing multiple categories of POI, plots containing no POI, and plots containing POI but no category according to the category and number of POIs contained in each plot in the original land use classification data, so as to facilitate the subsequent classification of the plots according to different situations.
[0059] In some embodiments, for a land parcel containing only one type of POI, the category to which the POI belongs is assigned to the land parcel. Here, the "category" field in the attribute table of the POI contained in the land parcel containing only one type of POI is connected to the corresponding land parcel attribute table.
[0060] In some embodiments, if the land parcel contains multiple categories of POIs, the surface data of the land parcel is hierarchically segmented, and the categories of the surface data and POIs are assigned to the segmented land parcels according to predetermined priorities. For the land parcels that still have no categories after segmentation, they are classified into the category to which the land parcel closest to them belongs.
[0061] Specifically, first calculate the ratio Si of the total area of all the surface data P1 representing multiple place combinations contained in the plot to the area of the plot, i = 1, 2, ..., p. Here, the surface data P1 representing multiple place combinations is clipped with the plot as the range, and a spatial connection is established between each plot and the surface data P1 in the plot, marking the plot where the surface data P1 is located. Then calculate the total area of all the surface data P1 in each plot and the area of each plot, and obtain the ratio S of the total area of all the surface data P1 in each plot to the area of each plot. i , i = 1, 2, ..., p, p is the number of plots containing multiple POIs.
[0062] Then, the area ratio S is divided by the surface data P1 i The land parcels that are greater than or equal to the threshold δ1 are divided, and the category of the surface data P1 is assigned to the corresponding land parcel after segmentation. Here, in order to make the land parcels as complete as possible after segmentation, the surface data P1 representing multiple place combinations is preferentially used to segment the land parcels. In this embodiment, the threshold δ1 is determined by the adaptive threshold method so that the area ratio S i The surface data P1 in the plot that is greater than or equal to the threshold δ1 can basically represent the plot, and the plot is then segmented using the surface data P1, and the category of the surface data P1 is assigned to the segmented plot through spatial connection.
[0063] After that, calculate the area ratio S i The ratio BS of the sum of the areas of all the surface data P representing a single location contained in the plots that are smaller than the threshold δ1 and the plots that do not intersect with the surface data P1 to the area of the plot j , j=1,2,...,q, q is the area ratio S iThe number of plots to be segmented that are less than the threshold δ1 and do not intersect with the surface data P1. Here, the area ratio S is extracted. i For plots smaller than the threshold δ1 and plots that do not intersect with the surface data P1, the surface data P is clipped with the plot as the range, and a spatial connection is established between each plot and the surface data P in the plot, marking the plot where the surface data P is located. Then the sum of the areas of all surface data P in each plot and the area of each plot are calculated, and the ratio BS of the sum of the areas of all surface data P contained in each plot to the area of the plot is obtained. j , j = 1, 2, ..., q, q is the area ratio S i The number of plots to be segmented that are smaller than the threshold δ1 and do not intersect with the surface data P1.
[0064] Next, use the surface data P to divide the area ratio BS j The land parcels that are greater than or equal to the threshold δ2 are selected, and the category of the surface data P is assigned to the corresponding land parcels after segmentation. Here, the threshold δ2 is determined using the adaptive threshold method so that the area ratio BS j The surface data P in the plot that is greater than or equal to the threshold δ2 can basically represent the plot. The plot is then segmented using the surface data P, and the category of the surface data P is assigned to the segmented plot through spatial connection.
[0065] Next, use the surface data P1 to split the area ratio BS j For plots smaller than the threshold δ2, the surface data P that does not intersect with the surface data P1 is used to segment them, and the segmented plots are assigned the categories corresponding to the surface data P1 and the surface data P. Here, in order to fully segment and classify the plots and maintain the integrity of the segmented plots, the area ratio BS j For plots smaller than the threshold δ2, the surface data P1 in the plot is first used to segment it, and then the surface data P in the plot that does not intersect with the surface data P1 is used to segment it again. The categories of the surface data P1 and the surface data P are assigned to the segmented plots through spatial connection.
[0066] For plots without polygon data, they are classified according to the number of POIs of each type and the priority of the POI category. Here, the priority of the POI category is set for different categories in the original land use classification data. If the original category of the plot is "Rest and Recreation", when the categories of the POIs contained in the plot include both "Parks and Green Spaces" and "Land for Science, Education, Culture and Health", the plot will be classified into the "Parks and Green Spaces" category first.
[0067] For the land parcel categories that do not specify the POI category priority, in order to improve the classification accuracy, the number of various POIs from government-published data contained in each land parcel of this category is calculated first, and the category with the largest number of POIs is used as the category of the land parcel. If the land parcel still has no category, the number of various POIs from non-government-published data contained in the land parcel is calculated, and the category with the largest number of POIs is used as the category of the land parcel.
[0068] Finally, the fragmented plots that are still unclassified after segmentation are classified into the category of the nearest existing plot within a certain distance. Here, since the surface data and the range of the plot do not completely match, there will be plots without categories after segmentation and classification. For these plots, a distance range is set, and the unclassified plots are classified into the category of the nearest existing plot within the distance range.
[0069] In some implementations, a buffer analysis is performed on the plots that do not contain POIs and the plots that contain POIs but have no categories, and the POIs contained are determined again and classified using the POIs.
[0070] Here, since there is a certain error between the POI data and the actual location, and there is a matching accuracy problem between the POI data and the original land use classification data, it is necessary to select an appropriate buffer distance to perform buffer analysis on the plots that do not contain POIs and the plots that contain POIs without categories, and judge the POIs contained in the plots after buffering according to the method in step S20. For the plots with one POI after buffering, the category of the POI contained in the plot is assigned through spatial connection. For the plots with multiple POIs after buffering, the category with the largest number of POIs is used as the category of the plot.
[0071] In some embodiments, in order to illustrate the classification effect of the land use subdivision method provided in an embodiment of the present invention, taking the subdivision of a certain place from the "government, institutions and community facilities" category in land use classification system A to land use classification system B as an example, Figure 2(a) shows the land use classification data of a certain place with the category of "government, institutions and community facilities", and Figure 2(b) shows a reference map of the target land use classification system B of the place. Figure 3 The classification result diagram of the land use sub-classification method provided by the embodiment of the present invention is given. Figure 3 From the classification result diagram of FIG. 2( b ) and the classification reference diagram of FIG. 2( b ), it can be found that the classification result obtained by the embodiment of the present invention is basically close to the actual classification situation.
[0072] Table 1 further provides quantitative analysis indicators of the classification results of the embodiment of the present invention. The overall accuracy of the indicator represents the ratio of the number of classified plots to the number of all plots. From Table 1, it can be seen that the overall accuracy of the change detection results provided by the embodiment of the present invention is high in each category. Therefore, the land use subclassification method provided by the embodiment of the present invention can obtain better land use subclassification results.
[0073] Table 1 Quantitative analysis indicators of classification results
[0074] Target land use classification system category Overall accuracy Special land 96.4% Land for press and publication by government agencies and organizations 90.7% Land for science, education, culture and health 95.1% Parks and green spaces 98.3% Public utility land 92.8% Transportation service station land 80% Commercial service facilities land 97.5%
[0075] In some embodiments, a POI-based land classification device is also provided, which includes:
[0076] The classification module is used to classify the collected POI data and surface data to obtain classification results;
[0077] A judgment module, used for judging the category and quantity of POIs contained in each block in the original land use classification data based on the classification result;
[0078] A first category assigning module, used for assigning the category to which the POI belongs to the land parcel when the land parcel contains only one category of POI;
[0079] The second category assignment module is used to perform hierarchical segmentation of the surface data of the land parcel when the land parcel contains multiple categories of POIs, and then assign the categories of the surface data and POIs to the segmented land parcels according to a predetermined priority, and for the land parcels that still have no category after segmentation, classify them into the category to which the land parcel closest to them belongs;
[0080] The third category assignment module is used to perform a buffer analysis on the land, and then determine the category and quantity of POIs contained in the land again when the land does not contain POI or the land contains POI but has no category, and then classify the land based on the category and quantity of POIs contained in the land.
[0081] In some specific embodiments, the classification module includes: a first classification unit, which is used to reclassify POI data with category information according to the classification requirements of the target land use classification system; a second classification unit, which is used to first calculate the number of various POIs from government-published data contained in the surface data without category information, and in combination with the priority of the POI category, use the category with high priority or the largest number of POIs as the category of the surface data; if the surface data still has no category, then calculate the number of various POIs from non-government-published data contained in the surface data, and in combination with the priority of the POI category, use the category with high priority or the largest number of POIs as the category of the surface data; a third classification unit, which is used to classify the surface data with existing category information according to the classification requirements of the target land use classification system.
[0082] In some embodiments, a storage medium is further provided, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the POI-based land classification method of the present invention.
[0083] In some embodiments, a terminal device includes: a processor, a memory, and a communication bus; the memory stores a computer-readable program executable by the processor;
[0084] The communication bus realizes the connection and communication between the processor and the memory;
[0085] When the processor executes the computer-readable program, the steps in the POI-based land classification method of the present invention are implemented.
[0086] In some implementations, the present application also provides a terminal device, such as Figure 4 As shown, it includes at least one processor (processor) 20; display screen 21; and memory (memory) 22, and may also include a communication interface (Communications Interface) 23 and a bus 24. Among them, the processor 20, the display screen 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a preset user guide interface in the initial setting mode. The communication interface 23 can transmit information. The processor 20 can call the logic instructions in the memory 22 to execute the method in the above embodiment.
[0087] In addition, the logic instructions in the memory 22 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.
[0088] The memory 22 is a computer-readable storage medium that can be configured to store software programs, computer executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions or modules stored in the memory 22, that is, implementing the methods in the above embodiments.
[0089] The memory 22 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, may also be a transient storage medium.
[0090] In addition, the specific process of loading and executing multiple instruction processors in the storage medium and the terminal device has been described in detail in the above method and will not be described here one by one.
[0091] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.
Claims
1. A POI-based land classification method, characterized in that: Includes steps: The collected POI data and surface data are classified and processed to obtain classification results; the POI data with category information are reclassified according to the classification requirements of the target land use classification system; for surface data without category information, the number of various POIs from government-published data contained in the surface data is first calculated, and the category with high priority or the largest number of POIs is taken as the category of the surface data in combination with the priority of the POI category; if the surface data still has no category, the number of various POIs from non-government-published data contained in the surface data is calculated again, and the category with high priority or the largest number of POIs is taken as the category of the surface data in combination with the priority of the POI category; According to the classification requirements of the target land use classification system, the surface data with existing category information is classified; Determine the category and quantity of POIs contained in each block in the original land use classification data based on the classification result; If the land parcel contains only one type of POI, assign the category to which the POI belongs to the land parcel; If the land parcel contains multiple types of POIs, the land parcel is segmented by plane data, and then the types of plane data and POIs are assigned to the segmented land parcels according to a predetermined priority. For the land parcels that still have no categories after segmentation, they are classified into the categories to which the land parcels closest to them belong; If the land parcel does not contain a POI or contains a POI but has no category, a buffer analysis is performed on the land parcel to determine the category and quantity of the POI contained in the land parcel again, and then the land parcel is classified based on the category and quantity of the POI contained in the land parcel.
2. The POI-based land classification method according to claim 1, characterized in that: The POI data collection method includes: obtaining existing POI data from various platforms, including government-published data and non-government-published data, including but not limited to POI data obtained from government websites, Amap, Baidu Map, and Tencent Map, or converting surface data into POI data.
3. The POI-based land classification method according to claim 1, characterized in that: The surface data includes surface data of a single place and surface data of a combination of multiple places. The surface data of a single place includes building data and transportation station polygon data; the surface data of a combination of multiple places includes data of buildings and their annexes. The sources of obtaining the surface data include government-published data and non-government-published data, including but not limited to surface data obtained from government websites and OpenStreetMap.
4. The POI-based land classification method according to claim 1, characterized in that: Determining the category and quantity of POIs contained in each block in the original land use classification data based on the classification result includes the following steps: According to the categories and numbers of POIs contained in each plot in the original land use classification data, the plots are divided into plots containing only one category of POI, plots containing multiple categories of POIs, plots containing no POI, and plots containing POIs but no category.
5. The POI-based land classification method according to claim 1, characterized in that: If the land parcel contains multiple categories of POIs, the land parcel is segmented into layers according to the surface data, and the categories of the surface data and POIs are assigned to the segmented land parcels according to a predetermined priority. For the land parcels that still have no category after segmentation, the steps of classifying them into the category to which the land parcel closest to them belongs include: The surface data P1 representing multiple place combinations is preferentially used to segment the plots containing multiple POIs. Before segmentation, the ratio S of the sum of the areas of all the surface data P1 contained in each plot to be segmented to the area of the plot is calculated. i , i=1,2,...,p, p is the number of plots containing multiple POIs, the threshold value δ1 of the area ratio is determined according to the actual situation, for the plots to be segmented whose area ratio is greater than or equal to the threshold δ1, only the surface data P1 in the plot is used for segmentation, and the segmented plots are assigned the categories corresponding to the surface data P1; For the area ratio S i For the plots to be divided that are smaller than the threshold δ1 and the plots to be divided that do not intersect with the surface data P1, if the plot to be divided contains surface data P representing a single location, the ratio BS of the sum of the areas of all the surface data P contained in the plot to be divided to the area of the plot is calculated. j , j = 1, 2, ..., q, q is the area ratio S i The number of plots to be divided that are less than the threshold δ1 and do not intersect with the surface data P1, and the threshold δ2 of the area ratio is determined according to the actual situation. For area BS j For the plots to be segmented that are greater than or equal to the threshold δ2, only the surface data P inside the plots are used for segmentation, and the corresponding surface data P is assigned to the segmented plots; For area BS j For a plot of land to be divided that is smaller than the threshold value δ2, if the plot of land to be divided contains both the surface data P representing a single place and the surface data P1 representing a combination of multiple places, the surface data P1 representing the combination of multiple places is preferentially used for division, and then the surface data P representing a single place that does not intersect with the surface data P1 is used for division, and the categories of the corresponding surface data P1 and P are respectively assigned to the divided plot; if the plot of land to be divided only contains the surface data P representing a single place, only the surface data P is used for division, and the category of the corresponding surface data P is assigned to the divided plot; For the plots of land that have been segmented into layers using the surface data, the fragmented plots that still have no category after segmentation are classified into the category to which the nearest existing category plot belongs within a certain distance; When using POI to determine the land parcel category, the POI category is set with corresponding priority for different land use categories; For plots of land that do not contain polygon data and contain POIs of multiple categories, we first calculate the number of POIs of each category from government-published data in each plot, and combine the priority of the POI category to take the category with a high priority or the largest number of POIs as the category of the plot. If the plot still has no category, we calculate the number of POIs of each category from non-government-published data in each plot, and combine the priority of the POI category to take the category with a high priority or the largest number of POIs as the category of the plot.
6. A POI-based land classification device, characterized in that: include: The classification module is used to classify the collected POI data and surface data to obtain classification results; The classification module includes: a first classification unit, which is used to reclassify POI data with category information according to the classification requirements of the target land use classification system; a second classification unit, which is used to first calculate the number of various POIs from government-published data contained in the surface data without category information, and combine the priority of the POI category to take the category with high priority or the largest number of POIs as the category of the surface data; if the surface data still has no category, then calculate the number of various POIs from non-government-published data contained in the surface data, and combine the priority of the POI category to take the category with high priority or the largest number of POIs as the category of the surface data; a third classification unit, which is used to classify the surface data with existing category information according to the classification requirements of the target land use classification system; A judgment module, used for judging the category and quantity of POIs contained in each block in the original land use classification data based on the classification result; A first category assigning module, used for assigning the category to which the POI belongs to the land parcel when the land parcel contains only one category of POI; The second category assignment module is used to perform hierarchical segmentation of the surface data of the land parcel when the land parcel contains multiple categories of POIs, and then assign the categories of the surface data and POIs to the segmented land parcels according to a predetermined priority, and for the land parcels that still have no category after segmentation, classify them into the category to which the land parcel closest to them belongs; The third category assignment module is used to perform a buffer analysis on the land parcel, and then determine the category and number of POIs contained in the land parcel again when the land parcel does not contain a POI or the land parcel contains a POI but has no category, and then classify the land parcel based on the category and number of POIs contained in the land parcel.
7. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the POI-based land classification method as described in any one of claims 1-5.
8. A terminal device, characterized in that: include: A processor, a memory and a communication bus; the memory stores a computer-readable program that can be executed by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, the steps in the POI-based land classification method according to any one of claims 1 to 5 are implemented.
