A method and system for constructing a land use intelligent engine

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for constructing a land use intelligent engine. The method comprises the following steps: obtaining land use data and land population data; extracting land use features from the land use data and land population data to obtain land use feature data; performing spatial data processing on the land use data to obtain land use spatial data; constructing a land use engine based on the land use feature data and land use spatial data to obtain land use engine data to assist land use intelligent decision-making. The present invention analyzes data such as land use and population distribution, which can help users better understand the current status and future trends of land use, optimize resource allocation, rationally plan land use, and maximize economic, social and ecological benefits.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for constructing a land use intelligent engine. Background Art

[0002] GIS is a technology used to capture, store, manage, analyze and display geospatial data. It combines maps, geospatial data, geolocation information and other related data so that users can analyze and understand geographic phenomena and spatial relationships. Traditional GIS systems lack intelligent and automated functions, and generally require users to manually process and analyze data, which cannot achieve prediction and analysis for land use planning, management and decision-making. Artificial Intelligence (AI) is a scientific and engineering field that studies how to enable computers to perform intelligent tasks like humans. Its goal is to develop intelligent systems that can perceive, understand, learn, reason, plan, make decisions and perform tasks. The scope of AI research is very broad, covering a variety of problems from simple pattern recognition to complex autonomous robots. How to combine artificial intelligence with GIS has become a problem. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a method and system for constructing a land use intelligent engine to solve at least one of the above technical problems.

[0004] This application provides a method for constructing a land use intelligent engine, comprising the following steps:

[0005] Step S1: Obtain land use data and land population data;

[0006] Step S2: extracting land use characteristics from land use data and land population data to obtain land use characteristic data;

[0007] Step S3: performing spatial data processing on the land use data to obtain land use spatial data;

[0008] Step S4: construct a land use engine based on the land use characteristic data and the land use spatial data to obtain land use engine data for assisting land use intelligent decision making.

[0009] The present invention combines various information such as land use and population distribution by acquiring land use data and land population data, realizes comprehensive data analysis, and provides more reliable information support for land use decision-making. By performing feature extraction and spatial data processing on land use data and land population data, important feature information can be extracted from massive data, and the data can be spatially analyzed and processed, thereby improving the availability and effectiveness of the data. Based on land use feature data and spatial data, a land use engine is constructed, which can construct and optimize data models, thereby realizing intelligent analysis and decision-making assistance for land use. Through the construction of the land use engine, simulation prediction and intelligent decision-making assistance for land use can be realized, providing a scientific basis for decisions such as urban planning and land management, and improving the accuracy and efficiency of decisions. By comprehensively analyzing data such as land use and population distribution, decision makers can better understand the current status and future trends of land use, optimize resource allocation, rationally plan land use, and maximize economic, social and ecological benefits.

[0010] Preferably, step S1 specifically includes:

[0011] Step S11: collecting land use data and land population data through a land use database and land population data to obtain original land use data and original land population data;

[0012] Step S12: collecting land space images through the Internet or geographic information system to obtain land space image data;

[0013] Step S13: Projecting the land space image data according to the original land use data to obtain land use data;

[0014] Step S14: performing association processing on the land space image data according to the original land population data to obtain land population data.

[0015] In the present invention, the land use database and land population data are collected to obtain the original land use data and land population data, realizing the collection and integration of information such as land use and population distribution, and providing basic data support. The land space image is collected by using the Internet or geographic information system to obtain the land space image data, providing information on the current land use status and landform characteristics. The land space image data is projected and associated with the original land population data to obtain the association result of land use data and land population data, which helps to associate geographic space data with land use data and population data, and improves the accuracy and availability of the data.

[0016] Preferably, step S13 is specifically:

[0017] Step S131: performing geographic coordinate conversion on the land space image data according to the original land use data to obtain land use image conversion data;

[0018] Step S132: performing topological relationship analysis based on the land use image conversion data to obtain land use topological relationship data;

[0019] Step S133: Perform multi-scale spatial analysis on the land use topological relationship data to obtain land use data.

[0020] In the present invention, the original land use data and land space image data are converted into geographic coordinates, and the image data is mapped to the geographic space coordinate system, so as to ensure the spatial consistency and accuracy of the land use data and the image data, and improve the reliability and accuracy of the subsequent analysis. The land use image conversion data is used to perform topological relationship analysis, and the spatial relationship between the land use areas, such as adjacent and overlapping, is analyzed to obtain the topological relationship data of land use, which is helpful to identify the spatial connection and interaction between the land use areas, and provides important information for the subsequent spatial analysis and decision-making. The land use topological relationship data is subjected to multi-scale spatial analysis, and the spatial characteristics of the land use area are deeply excavated through spatial analysis methods of different scales, such as based on neighborhoods, buffer zones, etc., which is helpful to understand the land use data from different angles and scales, discover more detailed and comprehensive spatial laws, and provide more effective reference for land use decision-making.

[0021] Preferably, the land use topological relationship data includes land use adjacency relationship data, land use adjacency relationship data, land use coverage relationship data and land use intersection relationship data, and step S132 is specifically as follows:

[0022] Performing adjacency processing according to land use image conversion data to obtain land use adjacency data;

[0023] Connectivity processing is performed based on land use image conversion data to obtain land use adjacency relationship data;

[0024] Carry out coverage relationship processing according to land use image conversion data to obtain land use coverage relationship data;

[0025] Cross-relationship processing is performed on the land use image conversion data to obtain land use cross-relationship data.

[0026] In the present invention, by performing adjacency relationship processing on land use image conversion data, the adjacency relationship between land use areas, that is, the relationship between adjacent or bordering areas, is identified, which helps to understand the spatial distribution pattern of land use areas and discover the spatial correlation between adjacent areas. Using land use image conversion data to perform connection relationship processing, the connection relationship between land use areas, that is, the relationship between areas connected by paths or linear features, is identified, which helps to discover the spatial connectivity between land use areas and understand the organizational structure of the land use network. Using land use image conversion data to perform covering relationship processing, the covering relationship between land use areas, that is, the relationship in which one area is completely or partially covered by another area, is identified, which helps to understand the spatial competition relationship and resource utilization between land use areas. Using land use image conversion data to perform intersection relationship processing, the intersection relationship between land use areas, that is, the intersection or overlapping relationship between different areas, is identified, which helps to discover spatial conflicts or interactive effects between land use areas, and provides a reference basis for resolving land use conflicts and optimizing land use layout.

[0027] Preferably, step S133 is specifically:

[0028] Performing data scale conversion on land use topological relationship data to obtain land use scale conversion data;

[0029] Performing scale matching processing on the land use scale conversion data to obtain land use scale matching data;

[0030] Multi-scale data fusion is performed on the land use scale matching data to obtain land use data.

[0031] In the present invention, by performing data scale conversion on land use topological relationship data, the scale of the original data is adjusted to adapt to different analysis requirements or processing methods, which helps to uniformly process and compare land use data at different scales, and improves the versatility and applicability of the data. On the basis of scale conversion, scale matching processing is performed on land use scale conversion data, so that data of different scales have consistency and matching, which helps to ensure the comparability and credibility of land use data at different scales. Based on scale-matched land use data, multi-scale data fusion is performed to integrate and merge data information at different scales to obtain more comprehensive and accurate land use data, which helps to make full use of information at different scales and improve the comprehensive utilization value and analysis ability of land use data.

[0032] Preferably, step S2 specifically includes:

[0033] Step S21: extracting basic land use features from the land use data to obtain basic land use feature data;

[0034] Step S22: performing cluster calculation on the basic characteristic data of land use to obtain cluster characteristic data of land use;

[0035] Step S23: Calculate the derived characteristics of the land use data and the land population data to obtain the land use derived characteristic data;

[0036] Step S24: performing time series analysis and spatial analysis on the land use data to obtain land use time series characteristic data and land use spatial characteristic data respectively;

[0037] Step S25: Integrate the basic land use characteristic data, the land use cluster characteristic data, the land use derived characteristic data, the land use temporal characteristic data and the land use spatial characteristic data to obtain land use characteristic data.

[0038] The present invention helps to understand the basic situation and internal laws of land use by extracting the basic characteristics and clustering characteristics of land use. Combined with the calculation of derived characteristics of land use, the correlation and influencing factors of land use data can be deeply explored, providing more comprehensive information support for land use decisions. Time series analysis and spatial analysis help to reveal the changing trend and spatial pattern of land use, and provide a scientific basis for land use planning and resource management. Based on the basic characteristic data of land use, clustering calculations are performed to cluster similar land use types or characteristics to obtain clustering characteristic data of land use, which helps to discover the internal structure and distribution law of land use data and provides a basis for the identification and analysis of land use patterns. Combined with land use data and land population data, derived characteristic calculations are performed to obtain derived characteristic data of land use, including information such as population density and land use intensity, which helps to deeply explore the internal correlation and influencing factors of land use data. Time series analysis and spatial analysis are performed on land use data to obtain time series characteristic data and spatial characteristic data of land use, respectively. Time series characteristic data can reflect the trend and law of land use change, and spatial characteristic data can reveal the spatial distribution and pattern of land use, providing an in-depth understanding of the dynamic changes and spatial layout of land use. Integrating basic land use characteristic data, land use clustering characteristic data, land use derived characteristic data, land use time series characteristic data and land use spatial characteristic data to obtain comprehensive land use characteristic data will help to uniformly manage and analyze characteristic information from different sources and types, providing comprehensive data support for land use decision-making.

[0039] Preferably, step S23 is specifically:

[0040] Calculate the land use population density based on the land use data and land population data to obtain the land use population density characteristic data;

[0041] Gridding the land use data to obtain land use grid data;

[0042] The spatial population calculation is performed on the land use grid data through the density kernel function to obtain the land use spatial population characteristic data;

[0043] Calculate population migration based on land use data to obtain land use population migration characteristic data;

[0044] The land use population density characteristic data, land use spatial population characteristic data and land use population migration characteristic data are integrated into land use derived characteristic data.

[0045] In this invention, by comprehensively considering land use and population data, we can have a deeper understanding of the population distribution and population mobility patterns in land use areas. Using characteristic data such as population density, spatial population and population migration, we can deeply explore the correlation between land use and population, and provide more accurate data support for urban planning and resource management. Integrating different types of land use characteristic data into derived characteristic data helps to deeply analyze the complex relationship between land use and population, and provide a scientific basis for urban development decisions.

[0046] Preferably, step S24 is specifically:

[0047] Step S241: performing time series segmentation on the land use data to obtain land use time series segmentation data;

[0048] Step S242: performing time series change detection on the land use time series segmentation data to obtain land use time series feature data;

[0049] Step S243: performing spatial object association analysis on the land use data to obtain land use spatial object association data;

[0050] Step S244: Perform spatial clustering analysis on the land use data and land use spatial object associated data to obtain land use spatial characteristic data.

[0051] In the present invention, by performing time series segmentation on land use data, the time series data is divided into different time series segments or time periods, and the land use time series segmentation data is obtained, which helps to split the long-term time series data into shorter time periods, so as to better perform time series analysis and change detection. Based on the time series segmentation data, time series change detection is performed, and the changes in land use in different time periods are analyzed to obtain the time series characteristic data of land use, which helps to identify the trend and pattern of land use change, and provide time-effective data support for land resource management and planning. Through spatial object association analysis, the spatial correlation and connection between land use data are analyzed to obtain land use spatial object association data, which helps to understand the spatial distribution characteristics and spatial relations of land use data, and provide data support from a spatial perspective for land use planning and decision-making. Based on land use data and spatial object association data, spatial clustering analysis is performed, similar land use areas or spatial objects are clustered, and land use spatial characteristic data is obtained, which helps to identify the pattern and clustering phenomenon of land use spatial distribution, and provides a reference basis for land use planning and spatial layout.

[0052] Preferably, step S244 is specifically:

[0053] Perform density spatial clustering on land use data and land use spatial object associated data to obtain preliminary land use spatial characteristic data;

[0054] The preliminary land use spatial characteristic data are subjected to density clustering scanning processing to obtain the land use spatial characteristic data.

[0055] In the present invention, through density spatial clustering processing, land use data and land use spatial object association data are combined to identify land use areas or spatial objects with similar density characteristics, and obtain preliminary land use spatial feature data, which is helpful to discover density distribution patterns and aggregation phenomena in land use data. Further, the preliminary land use spatial feature data is subjected to density clustering scanning processing, and by determining the density clustering scanning parameters of each area, areas with significant density clustering characteristics are identified to obtain land use spatial feature data, which is helpful to analyze the density distribution and spatial clustering characteristics of land use from a more refined perspective, and provide more accurate data support for land use planning and spatial layout. However, the existing technical means often adopt a single feature extraction method or a relatively rough feature extraction method, which can only process a small amount of land use features and is difficult to fully mine the potential information in the data. The present invention combines the advantages of density spatial clustering processing and density clustering scanning processing, overcomes the shortcomings of single clustering processing or feature processing, and reduces the problem of information loss in the processing process.

[0056] Preferably, step S3 specifically includes:

[0057] Identify the land boundaries and divide the land use data into plots to obtain the plot division data;

[0058] Performing land use classification processing on the plot division data to obtain land use classification data;

[0059] Obtaining land use optimization target data;

[0060] According to the land use optimization target data, the land use classification data is spatially optimized to obtain the land use spatial data.

[0061] In the present invention, by performing boundary identification and plot division on land use data, the plots are divided according to their spatial boundaries to obtain plot division data, which helps to divide the land into smaller units and provide a basis for subsequent land use classification and optimization processing. Based on the plot division data, land use classification processing is performed on each plot, and different plots are classified into corresponding land use types to obtain land use classification data. This helps to understand the distribution and type composition of land use and provides a basis for subsequent spatial optimization processing. Obtaining target data related to land use optimization, including but not limited to data on land resource utilization efficiency, economic benefits, environmental friendliness, etc., helps to clarify the goals and directions of land use optimization and provide guidance and basis for optimization processing. Based on the land use optimization target data, the land use classification data is spatially optimized, and the land use type and layout are adjusted to make it more in line with the optimization goal to obtain land use spatial data, which helps to improve the efficiency of land resource utilization, optimize the land use structure, and provide scientific support for urban development and land planning.

[0062] Preferably, the present application also provides a land use intelligent engine construction system, which is used to execute the land use intelligent engine construction method as described above, and the land use intelligent engine construction system includes:

[0063] The land use basic data collection module is used to obtain land use data and land population data;

[0064] The land use feature extraction module is used to extract land use features from land use data and land population data to obtain land use feature data;

[0065] The land use spatial data processing module is used to perform spatial data processing on the land use data to obtain the land use spatial data;

[0066] The land use engine construction module is used to construct the land use engine according to the land use characteristic data and the land use spatial data, and obtain the land use engine data to perform land use intelligent decision-making auxiliary operations.

[0067] The beneficial effects of the present invention are: obtaining and extracting characteristic information of land use data and land population data, making full use of multi-source data, including land use data and population data. Land use feature extraction makes it possible to analyze land use from multiple angles, not only to understand the basic situation of land use, but also to deeply explore the potential characteristics of land use, so as to fully understand the current situation and potential problems of land use. Spatial data processing makes it possible to consider the spatial distribution of land use, including factors such as the geographical location and spatial correlation of land use, so as to better grasp the regional characteristics and spatial pattern of land use. The land use engine construction integrates land use feature data and spatial data to form an intelligent decision support system. Through comprehensive analysis and modeling of land use, the system can provide targeted intelligent decision support, including decision support in land planning, resource allocation, environmental protection and other aspects. Using the results of land use engine construction, users can make decisions related to land use more quickly and accurately. The data results constructed by the engine fully consider information from multiple aspects, which can help users comprehensively evaluate various factors and improve the efficiency and accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0069] Figure 1 A flowchart showing a method for constructing a land use intelligent engine according to an embodiment of the present invention is provided;

[0070] Figure 2 A flowchart showing the steps of a land use basic data collection method according to an embodiment is shown;

[0071] Figure 3 A flow chart showing the steps of a method for generating land use data according to an embodiment is shown;

[0072] Figure 4 A flow chart showing the steps of a land use feature extraction method according to an embodiment is shown. DETAILED DESCRIPTION

[0073] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] See also Figures 1 to 4 , the present application provides a method for constructing a land use intelligent engine, comprising the following steps:

[0077] Step S1: Obtain land use data and land population data;

[0078] Specifically, land use data acquisition: use geographic information system (GIS) or databases of relevant government departments to obtain land use data, such as land use status map, land use planning map, etc. Land population data acquisition: obtain land population data, such as census data, population density data, etc. from information databases of government statistics departments, census data, health departments or other relevant departments.

[0079] Specifically, access relevant geospatial data services or map services through GIS software, such as ArcGIS Online, to obtain layer data of land use status map or land use planning map. Then, use the spatial analysis tools in GIS software, such as data query, spatial cross analysis and other functions, to extract the required land use data from the map. Access the data portal or open data interface of relevant government departments, such as the data query service of the National Bureau of Statistics, the demographic data service of local relevant departments, etc. Then, use the data query function to enter the required geographic area or range information to obtain the census data or population density data of the corresponding area.

[0080] Step S2: extracting land use characteristics from land use data and land population data to obtain land use characteristic data;

[0081] Specifically, land use feature extraction: using GIS software or professional data processing tools to extract features from land use data, such as land use type, land use area, land use distribution, etc. Land population data feature extraction: extracting relevant features such as population size, population density, population distribution, etc. based on land population data.

[0082] Specifically, the acquired land use data is imported into the GIS software to create a geographic information layer. Then, various features are extracted from the land use data using the spatial analysis and geographic processing functions provided by the GIS software, such as spatial query, area calculation, spatial statistical analysis, etc. For example, the distribution of various land use types can be determined through spatial query, the size of various land use areas can be determined through area calculation, and the spatial pattern of land use distribution can be determined through spatial statistical analysis.

[0083] Specifically, the acquired land population data is imported into data analysis and statistical software, such as the pandas library in Python, R language, etc. Then, the data processing and analysis functions provided by the data analysis software are used to extract the features of the land population data. For example, the population size and population density of each geographical area can be calculated through data aggregation and statistical functions, and the population distribution can be visualized.

[0084] Step S3: performing spatial data processing on the land use data to obtain land use spatial data;

[0085] Specifically, GIS software is used for spatial data processing, such as geographic coordinate conversion, map projection, spatial analysis, etc., to obtain the spatial characteristics of land use data. The processed land use data is visualized to generate a map or spatial image of land use spatial data for subsequent analysis and application.

[0086] Specifically, the acquired land use data is imported into the Python environment. Then, the GeoPandas library is used to read the data and perform geographic coordinate conversion to ensure the consistency and accuracy of the data. For example, the latitude and longitude coordinates in the original data are converted to the required projection coordinate system, such as the UTM projection coordinate system, for subsequent spatial analysis.

[0087] Open the land use data in the GIS software, select the appropriate projection method and perform projection processing. According to the spatial range of the data and the required accuracy, select the map projection method, such as equal longitude and latitude projection, UTM projection, etc. Then, convert the data into a map under the selected projection coordinate system and save it as a new geographic information layer.

[0088] In GIS software, spatial analysis tools are used to analyze land use data. For example, spatial queries can be performed to identify the distribution of land use types in a specific geographic area, buffer analysis can be used to determine the proximity of land use areas, or spatial interpolation can be performed to infer land use in unknown areas. Through these spatial analyses, the spatial characteristics and distribution patterns of land use data can be better understood.

[0089] Specifically, geographic coordinate conversion: Use the Geopandas library to read the original land use data, and then convert it according to the required geographic coordinate system. The to_crs() method can be used to achieve the conversion of geographic coordinates. Map projection: If map projection is required, you can use the Proj library in Python or related projection conversion tools to achieve it. These tools can project the geographic data to the specified map projection system based on the projection information. Spatial analysis: Use the Shapely library to create and analyze spatial geometric objects. Use the functions in the Shapely library to calculate the spatial characteristics of land use data, such as area, length, geometric relationships, etc. Through these spatial analyses, the spatial characteristics of land use data can be obtained.

[0090] Step S4: construct a land use engine based on the land use characteristic data and the land use spatial data to obtain land use engine data for assisting land use intelligent decision making.

[0091] Specifically, a land use engine model is constructed based on land use feature data and spatial data using machine learning algorithms or professional geographic information systems. The constructed land use engine model is used to assist in intelligent decision-making on land use, such as land planning, resource allocation, and environmental protection.

[0092] Specifically, the land use feature data and land use spatial data are organized into a format suitable for processing by machine learning algorithms. Feature data may include land use type, land use area, land use distribution, etc., and spatial data may include spatial distribution of land use, neighboring relationship, etc. Use deep learning frameworks such as TensorFlow or PyTorch to build a land use engine model on the training set. A CNN model can be used to extract the spatial features of land use data, and a RNN model can be combined to capture the temporal features of land use data. The input of the model can be a vector representation of land use feature data, and the output can be a classification result of land use or related decision indicators. Use annotated land use data sets for model training, and minimize the loss function by optimizing model parameters. During the training process, cross-validation and other techniques can be used to evaluate the performance and generalization ability of the model. Use the test set to verify the performance of the trained land use engine model. Evaluate the accuracy and reliability of the model by comparing the difference between the model's prediction results and the actual data. Use the constructed land use engine model to predict and assist in decision-making for new land use data. For example, assist in formulating land planning plans, resource allocation strategies, etc. based on the land use predicted by the model. At the same time, the model prediction results can be visualized by combining with tools such as geographic information system (GIS) to provide intuitive reference information for decision makers.

[0093] The present invention combines various information such as land use and population distribution by acquiring land use data and land population data, realizes comprehensive data analysis, and provides more reliable information support for land use decision-making. By performing feature extraction and spatial data processing on land use data and land population data, important feature information can be extracted from massive data, and the data can be spatially analyzed and processed, thereby improving the availability and effectiveness of the data. Based on land use feature data and spatial data, a land use engine is constructed, which can construct and optimize data models, thereby realizing intelligent analysis and decision-making assistance for land use. Through the construction of the land use engine, simulation prediction and intelligent decision-making assistance for land use can be realized, providing a scientific basis for decisions such as urban planning and land management, and improving the accuracy and efficiency of decisions. By comprehensively analyzing data such as land use and population distribution, decision makers can better understand the current status and future trends of land use, optimize resource allocation, rationally plan land use, and maximize economic, social and ecological benefits.

[0094] Preferably, step S1 specifically includes:

[0095] Step S11: collecting land use data and land population data through a land use database and land population data to obtain original land use data and original land population data;

[0096] Specifically, by applying to local governments or relevant departments, obtaining permission or data sharing agreements for land use databases, and then obtaining original land use data and land population data, such as land use planning, land use surveys, census data, population density data, etc.

[0097] Step S12: collecting land space images through the Internet or geographic information system to obtain land space image data;

[0098] Specifically, Internet map services, such as Google Earth, Baidu Maps, etc., are used to obtain land space image data, such as satellite images or aerial images, through interface operations or API interfaces.

[0099] Specifically, GIS software, such as ArcGIS, QGIS, etc., is used to obtain land spatial image data by accessing a GIS server or importing data files.

[0100] Step S13: Projecting the land space image data according to the original land use data to obtain land use data;

[0101] Specifically, GIS software is used to convert geographic coordinates and convert land space image data into a unified geographic coordinate system for subsequent analysis and processing. According to specific needs, a map projection method (such as Mercator projection, UTM projection, equidistant cylindrical projection, etc.) is selected to project the land space image data into the required map projection system. For example, the geographical range covered by the land space image data is determined, such as a longitude range of 100 degrees to 110 degrees and a latitude range of 30 degrees to 40 degrees. For the target area, a map projection system is selected, such as a UTM projection system, because the UTM projection is suitable for small-scale maps of local areas and has small projection deformation. The spherical projection method is used to convert geographic coordinates into projection coordinates. The spherical projection method is suitable for small-scale map projections and has small projection deformation. According to the location of the target area, the projection parameters of the UTM projection system are set. For example, determine the projection belt number, determine the central meridian, etc.

[0102] Step S14: performing association processing on the land space image data according to the original land population data to obtain land population data.

[0103] Specifically, GIS software or related data processing tools are used to match the original land population data with the land spatial image data to establish the correlation between land use data and population data. Through spatial analysis methods such as spatial interpolation and spatial statistics, the land spatial image data and land population data are analyzed for correlation, thereby obtaining land population data with a high degree of correlation.

[0104] In the present invention, the land use database and land population data are collected to obtain the original land use data and land population data, realizing the collection and integration of information such as land use and population distribution, and providing basic data support. The land space image is collected by using the Internet or geographic information system to obtain the land space image data, providing information on the current land use status and landform characteristics. The land space image data is projected and associated with the original land population data to obtain the association result of land use data and land population data, which helps to associate geographic space data with land use data and population data, and improves the accuracy and availability of the data.

[0105] Preferably, step S13 is specifically:

[0106] Step S131: performing geographic coordinate conversion on the land space image data according to the original land use data to obtain land use image conversion data;

[0107] Specifically, GIS software (such as ArcGIS) is used to import the original land use data and land space image data. A projection coordinate system, such as WGS 84 (latitude and longitude) or UTM (Universal Transverse Mercator) is selected in the GIS software to convert the land space image data into a unified geographic coordinate system.

[0108] Specifically, the geographic coordinate information in the original land use data is read and a projection method (such as spherical projection) is used to convert the geographic coordinates into plane coordinates.

[0109] Step S132: performing topological relationship analysis based on the land use image conversion data to obtain land use topological relationship data;

[0110] Specifically, in GIS software, topological analysis tools, such as the topological toolset in ArcGIS, are used to perform topological relationship analysis on land use image conversion data. Topological relationship analysis includes topological relationships between geometric objects such as points, lines, and surfaces, such as adjacency and intersection, to obtain land use topological relationship data.

[0111] Specifically, according to the land use image conversion data, the spatial geometric objects in the Shapely library are used to represent each land use area, and then the topological relationship analysis is performed, such as judging the intersection and inclusion relationship between areas.

[0112] Step S133: Perform multi-scale spatial analysis on the land use topological relationship data to obtain land use data.

[0113] Specifically, use professional geographic information system software, such as ArcGIS or QGIS, to import land use topological relationship data. Apply multi-scale spatial analysis methods, such as multi-scale spatial statistical analysis or multi-scale spatial interpolation analysis, in GIS software to process land use topological relationship data to obtain multi-scale spatial analysis results. Analyze multi-scale spatial data to obtain spatial feature information of land use data at different scales, and generate corresponding multi-scale spatial analysis results.

[0114] Specifically, based on the land use topological relationship data, multi-scale spatial analysis, such as spatial autocorrelation analysis and spatial cluster analysis, is performed using libraries such as GeoPandas or PySAL to reveal the spatial characteristics and changing patterns of land use patterns at different scales. Spatial autocorrelation analysis aims to reveal spatial correlation patterns, that is, whether there is a spatial correlation between the attribute values ​​of a plot and the attribute values ​​of its surrounding plots. Spatial cluster analysis is used to identify clusters of plots with similar land use patterns.

[0115] Spatial autocorrelation analysis: Obtain geospatial data, such as land use data. The data includes the location information (geometry) of each plot or geographic unit and the corresponding attribute values ​​(such as land use type). Use an appropriate spatial weight matrix to describe the spatial relationship between geographic units. Commonly used weight matrices include adjacency weight matrix and distance weight matrix. The adjacency weight matrix indicates whether the geographic units are adjacent or connected, while the distance weight matrix indicates the distance between the geographic units. The spatial autocorrelation statistics used include Moran's I index, Geary's C index, etc. Taking Moran's I as an example, it is a widely used spatial autocorrelation index used to measure the degree of spatial aggregation. The calculation process is to calculate the correlation between the attribute value of each geographic unit and the attribute value of its neighboring geographic units, and summarize the results into an index value. According to the calculated spatial autocorrelation index, it can be judged whether the attribute values ​​of the geographic units show spatial aggregation. An index close to 1 indicates positive spatial autocorrelation, that is, similar values ​​tend to cluster together; close to -1 indicates negative spatial autocorrelation, that is, similar values ​​tend to disperse; close to 0 indicates random distribution in space.

[0116] Spatial cluster analysis: Obtain geospatial data, such as land use data. The data includes the location information (geometry) of each plot or geographic unit and the corresponding attribute values ​​(such as land use type). Select a similarity measure to calculate the similarity between geospatial units, including Euclidean distance, Manhattan distance, Mahalanobis distance, etc. Select a clustering algorithm to cluster the geospatial units, including K-means clustering, DBSCAN, hierarchical clustering, etc. Cluster the geospatial units based on the output of the clustering algorithm. Each cluster represents a group of plots with similar land use patterns. By interpreting and analyzing the clustering results, clusters of plots with similar land use patterns are identified.

[0117] In the present invention, the original land use data and land space image data are converted into geographic coordinates, and the image data is mapped to the geographic space coordinate system, so as to ensure the spatial consistency and accuracy of the land use data and the image data, and improve the reliability and accuracy of the subsequent analysis. The land use image conversion data is used to perform topological relationship analysis, and the spatial relationship between the land use areas, such as adjacent and overlapping, is analyzed to obtain the topological relationship data of land use, which is helpful to identify the spatial connection and interaction between the land use areas, and provides important information for the subsequent spatial analysis and decision-making. The land use topological relationship data is subjected to multi-scale spatial analysis, and the spatial characteristics of the land use area are deeply excavated through spatial analysis methods of different scales, such as based on neighborhoods, buffer zones, etc., which is helpful to understand the land use data from different angles and scales, discover more detailed and comprehensive spatial laws, and provide more effective reference for land use decision-making.

[0118] Preferably, the land use topological relationship data includes land use adjacency relationship data, land use adjacency relationship data, land use coverage relationship data and land use intersection relationship data, and step S132 is specifically as follows:

[0119] Performing adjacency processing according to land use image conversion data to obtain land use adjacency data;

[0120] Specifically, spatial analysis tools in GIS, such as proximity analysis tools, are used to identify adjacent land units in the land use image and determine the adjacency relationship between them. Based on the adjacency analysis results, land use adjacency relationship data is generated to record the relationship information between adjacent land units.

[0121] Specifically, edge detection algorithms are used to identify boundary information in land use images.

[0122] Connectivity processing is performed based on land use image conversion data to obtain land use adjacency relationship data;

[0123] Specifically, the connection analysis tools in GIS, such as the connection tool, are used to identify the interconnected or connected land units in the land use image and determine the connection relationship between them. Based on the connection analysis results, land use connection relationship data are generated to record the relationship information between the interconnected or connected land units.

[0124] Specifically, the connected region labeling algorithm is used to identify the connectivity between adjacent plots in the land use image.

[0125] Carry out coverage relationship processing according to land use image conversion data to obtain land use coverage relationship data;

[0126] Specifically, spatial overlay tools in GIS, such as overlay tools, are used to analyze the coverage relationship between different land types in the land use image. Based on the overlay analysis results, land use and coverage relationship data are generated to record the coverage relationship information between different land types.

[0127] Specifically, a pixel matching algorithm is used to identify the overlap between different plots in the land use image.

[0128] Cross-relationship processing is performed on the land use image conversion data to obtain land use cross-relationship data.

[0129] Specifically, spatial analysis tools in GIS, such as intersection analysis tools, are used to identify intersecting land units in land use images and determine the intersection relationship between them. Based on the intersection analysis results, land use intersection relationship data is generated to record the relationship information between intersecting land units.

[0130] Specifically, the intersection detection algorithm is used to identify the intersections between different plots in the land use image.

[0131] In the present invention, by performing adjacency relationship processing on land use image conversion data, the adjacency relationship between land use areas, that is, the relationship between adjacent or bordering areas, is identified, which helps to understand the spatial distribution pattern of land use areas and discover the spatial correlation between adjacent areas. Using land use image conversion data to perform connection relationship processing, the connection relationship between land use areas, that is, the relationship between areas connected by paths or linear features, is identified, which helps to discover the spatial connectivity between land use areas and understand the organizational structure of the land use network. Using land use image conversion data to perform covering relationship processing, the covering relationship between land use areas, that is, the relationship in which one area is completely or partially covered by another area, is identified, which helps to understand the spatial competition relationship and resource utilization between land use areas. Using land use image conversion data to perform intersection relationship processing, the intersection relationship between land use areas, that is, the intersection or overlapping relationship between different areas, is identified, which helps to discover spatial conflicts or interactive effects between land use areas, and provides a reference basis for resolving land use conflicts and optimizing land use layout.

[0132] Preferably, step S133 is specifically:

[0133] Performing data scale conversion on land use topological relationship data to obtain land use scale conversion data;

[0134] Specifically, a data scale conversion method is selected, such as spatial resolution adjustment or data downsampling, to convert the land use topological relationship data to the required target scale. The data scale conversion method is applied to process the land use topological relationship data and generate land use scale conversion data.

[0135] Performing scale matching processing on the land use scale conversion data to obtain land use scale matching data;

[0136] Specifically, import land use scale conversion data and other related data, such as terrain data or land use planning data, into GIS software. Use spatial analysis tools in GIS, such as scale matching tools, to match data of different scales to ensure that they are spatially aligned and matched. Perform scale matching to adjust and match data of different scales for subsequent data fusion analysis.

[0137] Multi-scale data fusion is performed on the land use scale matching data to obtain land use data.

[0138] Specifically, load the matched land use scale conversion data and other related data into the GIS software. Use data fusion technology in GIS, such as overlay analysis or weighted fusion, to fuse data of different scales. Perform multi-scale data fusion analysis to integrate data information of each scale to obtain more comprehensive and accurate land use data.

[0139] In the present invention, by performing data scale conversion on land use topological relationship data, the scale of the original data is adjusted to adapt to different analysis requirements or processing methods, which helps to uniformly process and compare land use data at different scales, and improves the versatility and applicability of the data. On the basis of scale conversion, scale matching processing is performed on land use scale conversion data, so that data of different scales have consistency and matching, which helps to ensure the comparability and credibility of land use data at different scales. Based on scale-matched land use data, multi-scale data fusion is performed to integrate and merge data information at different scales to obtain more comprehensive and accurate land use data, which helps to make full use of information at different scales and improve the comprehensive utilization value and analysis ability of land use data.

[0140] Preferably, step S2 specifically includes:

[0141] Step S21: extracting basic land use features from the land use data to obtain basic land use feature data;

[0142] Specifically, basic features are extracted from land use data, such as land use type, land use area, land ownership, etc. GIS tools and geostatistical methods are used to analyze and process the extracted features to generate basic land use feature data.

[0143] Step S22: performing cluster calculation on the basic characteristic data of land use to obtain cluster characteristic data of land use;

[0144] Specifically, based on the basic characteristic data of land use, a clustering algorithm, such as K-means clustering or DBSCAN, is used to perform clustering calculations on the land use data. The parameters of the clustering algorithm, such as the number of clusters or the distance threshold, are adjusted to obtain clustering results. The clustering results are analyzed to obtain the characteristics and distribution of each cluster cluster, and the land use clustering characteristic data is generated.

[0145] Step S23: Calculate the derived characteristics of the land use data and the land population data to obtain the land use derived characteristic data;

[0146] Specifically, derived characteristics are calculated based on land use data and land population data, such as correlation indicators between population density and land use type, and diversity indicators of land use types.

[0147] Specifically, the correlation index between population density and land use type is calculated: the average population density of each land use type is calculated, that is, the number of people in this type of land divided by the area of ​​this type of land. Statistical methods (such as the Pearson correlation coefficient) are used to calculate the correlation between population density and each land use type.

[0148]

[0149] r is the correlation coefficient data between population density and land use type, n is the sample size data, x is the population density data, and y is the land use type proportion data.

[0150] Calculate the diversity index of land use types: Indicators such as the Shannon Diversity Index can be used to measure the diversity of different land use types. The calculation method includes first calculating the proportion of each land use type, and then using the formula to calculate the diversity index.

[0151]

[0152] H′ is the Shannon diversity index data of land use type, s is the number data of land use type, i is the ordinal data of land use type, p i is the proportion data of the i-th land use type.

[0153] Step S24: performing time series analysis and spatial analysis on the land use data to obtain land use time series characteristic data and land use spatial characteristic data respectively;

[0154] Specifically, the land use data is segmented in time series to obtain time series segmentation data. Time series analysis methods, such as time series analysis or trend analysis, are used to analyze the land use time series data to obtain land use time series feature data. Spatial object association analysis is performed on the land use data to obtain land use spatial object association data. Spatial analysis methods, such as spatial statistical analysis or spatial interpolation analysis, are used to analyze the land use spatial data to obtain land use spatial feature data.

[0155] Step S25: Integrate the basic land use characteristic data, the land use cluster characteristic data, the land use derived characteristic data, the land use temporal characteristic data and the land use spatial characteristic data to obtain land use characteristic data.

[0156] Specifically, data integration techniques, such as data merging or association operations, are used to integrate various data sets into a comprehensive land use feature data set to support subsequent land use intelligent decision-making assistance operations.

[0157] The present invention helps to understand the basic situation and internal laws of land use by extracting the basic characteristics and clustering characteristics of land use. Combined with the calculation of derived characteristics of land use, the correlation and influencing factors of land use data can be deeply explored, providing more comprehensive information support for land use decisions. Time series analysis and spatial analysis help to reveal the changing trend and spatial pattern of land use, and provide a scientific basis for land use planning and resource management. Based on the basic characteristic data of land use, clustering calculations are performed to cluster similar land use types or characteristics to obtain clustering characteristic data of land use, which helps to discover the internal structure and distribution law of land use data and provides a basis for the identification and analysis of land use patterns. Combined with land use data and land population data, derived characteristic calculations are performed to obtain derived characteristic data of land use, including information such as population density and land use intensity, which helps to deeply explore the internal correlation and influencing factors of land use data. Time series analysis and spatial analysis are performed on land use data to obtain time series characteristic data and spatial characteristic data of land use, respectively. Time series characteristic data can reflect the trend and law of land use change, and spatial characteristic data can reveal the spatial distribution and pattern of land use, providing an in-depth understanding of the dynamic changes and spatial layout of land use. Integrating basic land use characteristic data, land use clustering characteristic data, land use derived characteristic data, land use time series characteristic data and land use spatial characteristic data to obtain comprehensive land use characteristic data will help to uniformly manage and analyze characteristic information from different sources and types, providing comprehensive data support for land use decision-making.

[0158] Preferably, step S23 is specifically:

[0159] Calculate the land use population density based on the land use data and land population data to obtain the land use population density characteristic data;

[0160] Specifically, population data is spatially associated with land use data according to geographic regions, for example, using spatial overlay operations. The population density of each land use region, that is, the number of people per unit area, is calculated. Based on the calculation results, land use population density feature data is generated.

[0161] Gridding the land use data to obtain land use grid data;

[0162] Specifically, the land use area is divided into grids of equal size. The land use data in each grid is counted and summarized, for example, the distribution of land use types in each grid is calculated. Based on the statistical results, land use grid data is generated.

[0163] The spatial population calculation is performed on the land use grid data through the density kernel function to obtain the land use spatial population characteristic data;

[0164] Specifically, the land use grid data is spatially associated with the population data to determine the population in each grid. The population data is spatially smoothed using a density kernel function, such as a Gaussian kernel function or a uniform kernel function, to eliminate spatial volatility. Based on the calculation results of the kernel function, the land use spatial population characteristic data is generated.

[0165] Calculate population migration based on land use data to obtain land use population migration characteristic data;

[0166] Specifically, historical population data is used to analyze population migration in different time periods, such as the number and direction of people moving in and out. Spatial statistical analysis is performed on migration data to determine population migration trends and patterns in different regions. Based on the analysis results, land use population migration characteristic data is generated.

[0167] The land use population density characteristic data, land use spatial population characteristic data and land use population migration characteristic data are integrated into land use derived characteristic data.

[0168] Specifically, data integration techniques, such as data merging or association operations, are used to integrate the individual feature datasets into a comprehensive land use derived feature dataset.

[0169] In this invention, by comprehensively considering land use and population data, we can have a deeper understanding of the population distribution and population mobility patterns in land use areas. Using characteristic data such as population density, spatial population and population migration, we can deeply explore the correlation between land use and population, and provide more accurate data support for urban planning and resource management. Integrating different types of land use characteristic data into derived characteristic data helps to deeply analyze the complex relationship between land use and population, and provide a scientific basis for urban development decisions.

[0170] Preferably, step S24 is specifically:

[0171] Step S241: performing time series segmentation on the land use data to obtain land use time series segmentation data;

[0172] Specifically, the continuous land use data is segmented into different time series segments according to time using the time series analysis method. The time series segmentation can be performed using a sliding window or a fixed time interval method to ensure that the length of each time series segment is consistent. Each time series segment is identified and encoded for subsequent time series change detection and analysis. The land use time series segmentation data is generated, and the start and end time of each time series segment is recorded.

[0173] Step S242: performing time series change detection on the land use time series segmentation data to obtain land use time series feature data;

[0174] Specifically, a change detection algorithm, such as a pixel-based change detection method or an object-based change detection method, is used to detect land use changes between adjacent time series segments. The type and extent of land use changes are analyzed, such as newly added, reduced, or converted land use types. The characteristics of land use time series changes, such as the frequency, magnitude, and trend of the changes, are extracted. Time series feature data of land use are generated to record the change information of each time series segment.

[0175] Step S243: performing spatial object association analysis on the land use data to obtain land use spatial object association data;

[0176] Specifically, spatial analysis methods, such as spatial connection analysis or spatial association analysis, are used to analyze the association relationship between spatial objects in land use data. The degree of mutual influence and connection relationship between spatial objects are determined based on the spatial attributes of land use data. The characteristics of spatial object association, such as proximity, distance, and regularity of spatial distribution, are extracted. Land use spatial object association data are generated to record the relationship and characteristics between various spatial objects.

[0177] Step S244: Perform spatial clustering analysis on the land use data and land use spatial object associated data to obtain land use spatial characteristic data.

[0178] Specifically, a spatial clustering algorithm, such as density-based clustering algorithm (DBSCAN), hierarchical clustering algorithm (HAC) or grid-based clustering algorithm, is used to cluster land use data. Similar spatial objects are aggregated into the same category according to the spatial characteristics in the land use spatial object association data. The parameters of the clustering algorithm are adjusted to obtain the optimal clustering results. The land use spatial feature data is generated to record the characteristics and attribute information of each cluster.

[0179] In the present invention, by performing time series segmentation on land use data, the time series data is divided into different time series segments or time periods, and the land use time series segmentation data is obtained, which helps to split the long-term time series data into shorter time periods, so as to better perform time series analysis and change detection. Based on the time series segmentation data, time series change detection is performed, and the changes in land use in different time periods are analyzed to obtain the time series characteristic data of land use, which helps to identify the trend and pattern of land use change, and provide time-effective data support for land resource management and planning. Through spatial object association analysis, the spatial correlation and connection between land use data are analyzed to obtain land use spatial object association data, which helps to understand the spatial distribution characteristics and spatial relations of land use data, and provide data support from a spatial perspective for land use planning and decision-making. Based on land use data and spatial object association data, spatial clustering analysis is performed, similar land use areas or spatial objects are clustered, and land use spatial characteristic data is obtained, which helps to identify the pattern and clustering phenomenon of land use spatial distribution, and provides a reference basis for land use planning and spatial layout.

[0180] Preferably, step S244 is specifically:

[0181] Perform density spatial clustering on land use data and land use spatial object associated data to obtain preliminary land use spatial characteristic data;

[0182] Specifically, density-based clustering algorithms, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise) or OPTICS (Ordering Points To Identify the Clustering Structure), are used to cluster land use data and associated spatial object data. In the DBSCAN algorithm, the minimum number of samples and the neighborhood radius of the cluster are set, and the density around each point determines whether it belongs to a core object, a boundary point, or a noise point. Based on the clustering results obtained by the DBSCAN algorithm, the spatial objects are divided into different clusters to reflect the degree of aggregation and distribution of the spatial characteristics of land use. As for the OPTICS algorithm, it is similar to DBSCAN, but it can discover clusters of different densities and scales, and the clustering results of the data are more comprehensive.

[0183] The preliminary land use spatial characteristic data are subjected to density clustering scanning processing to obtain the land use spatial characteristic data.

[0184] Specifically, for the initially obtained land use spatial feature data, a density clustering scanning algorithm, such as DENCLUE (DENsity-based CLUstEring) or the density scanning version of DBSCAN, is used to further refine the clustering results. The DENCLUE algorithm can perform local and global density estimation on the data set and identify a finer clustering structure to improve the accuracy and robustness of clustering. The algorithm parameters, such as the bandwidth parameter or the density threshold, are adjusted to achieve the best clustering effect. Through the density clustering scanning process, more refined land use spatial feature data is obtained, making the clustering results more representative and interpretable.

[0185] In the present invention, through density spatial clustering processing, land use data and land use spatial object association data are combined to identify land use areas or spatial objects with similar density characteristics, and obtain preliminary land use spatial feature data, which is helpful to discover density distribution patterns and aggregation phenomena in land use data. Further, the preliminary land use spatial feature data is subjected to density clustering scanning processing, and by determining the density clustering scanning parameters of each area, areas with significant density clustering characteristics are identified to obtain land use spatial feature data, which is helpful to analyze the density distribution and spatial clustering characteristics of land use from a more refined perspective, and provide more accurate data support for land use planning and spatial layout. However, the existing technical means often adopt a single feature extraction method or a relatively rough feature extraction method, which can only process a small amount of land use features and is difficult to fully mine the potential information in the data. The present invention combines the advantages of density spatial clustering processing and density clustering scanning processing, overcomes the shortcomings of single clustering processing or feature processing, and reduces the problem of information loss in the processing process.

[0186] Preferably, step S3 is specifically:

[0187] Identify the land boundaries and divide the land use data into plots to obtain the plot division data;

[0188] Specifically, remote sensing images or geographic information system (GIS) technology are used to perform image segmentation or object extraction on land use data to identify land boundaries and divide the land into different plots. Based on image processing algorithms, such as edge detection methods (such as Canny operator, Sobel operator) or watershed algorithms, the land use data is identified and segmented to generate plot division data. According to the spatial characteristics and land attributes of land use data, the land is divided into plots with relative continuity and similar characteristics, providing basic data for subsequent classification processing.

[0189] Performing land use classification processing on the plot division data to obtain land use classification data;

[0190] Specifically, machine learning algorithms such as support vector machine (SVM), random forest, convolutional neural network (CNN), etc. are used to classify the land use of the plot division data. Based on the attributes of the objects and the characteristics of land use, the classification model is trained to distinguish different land use types, such as farmland, forest land, urban construction land, etc. The land use classification is carried out by using the features such as the spectral information, texture features and spatial relationship of the objects, and the plot division data is classified into different land use types.

[0191] Obtaining land use optimization target data;

[0192] Specifically, through expert knowledge or using historical data and market demand, we can determine the optimization goals of land use, such as maximizing farmland output, minimizing ecological damage, maximizing the benefits of urban land use, etc. We can collect indicators and data on land resource utilization, environmental protection, economic development, etc. as target data for land use optimization, and provide a basis for subsequent spatial optimization processing.

[0193] According to the land use optimization target data, the land use classification data is spatially optimized to obtain the land use spatial data.

[0194] Specifically, based on the land use optimization target data and land use classification data, spatial analysis and optimization algorithms are used to optimize land use space. Spatial planning models, genetic algorithms, simulated annealing algorithms and other optimization algorithms are used to adjust and optimize the land use classification results to achieve the optimal land use configuration. Combined with land use types, land use goals and spatial constraints, optimized land use spatial data are generated to provide a scientific basis and reference plan for land use decision-making.

[0195] In the present invention, by performing boundary identification and plot division on land use data, the plots are divided according to their spatial boundaries to obtain plot division data, which helps to divide the land into smaller units and provide a basis for subsequent land use classification and optimization processing. Based on the plot division data, land use classification processing is performed on each plot, and different plots are classified into corresponding land use types to obtain land use classification data. This helps to understand the distribution and type composition of land use and provides a basis for subsequent spatial optimization processing. Obtaining target data related to land use optimization, including but not limited to data on land resource utilization efficiency, economic benefits, environmental friendliness, etc., helps to clarify the goals and directions of land use optimization and provide guidance and basis for optimization processing. Based on the land use optimization target data, the land use classification data is spatially optimized, and the land use type and layout are adjusted to make it more in line with the optimization goal to obtain land use spatial data, which helps to improve the efficiency of land resource utilization, optimize the land use structure, and provide scientific support for urban development and land planning.

[0196] Preferably, the present application also provides a land use intelligent engine construction system, which is used to execute the land use intelligent engine construction method as described above, and the land use intelligent engine construction system includes:

[0197] The land use basic data collection module is used to obtain land use data and land population data;

[0198] The land use feature extraction module is used to extract land use features from land use data and land population data to obtain land use feature data;

[0199] The land use spatial data processing module is used to perform spatial data processing on the land use data to obtain the land use spatial data;

[0200] The land use engine construction module is used to construct the land use engine according to the land use characteristic data and the land use spatial data, and obtain the land use engine data to perform land use intelligent decision-making auxiliary operations.

[0201] The beneficial effects of the present invention are: obtaining and extracting characteristic information of land use data and land population data, making full use of multi-source data, including land use data and population data. Land use feature extraction makes it possible to analyze land use from multiple angles, not only to understand the basic situation of land use, but also to deeply explore the potential characteristics of land use, so as to fully understand the current situation and potential problems of land use. Spatial data processing makes it possible to consider the spatial distribution of land use, including factors such as the geographical location and spatial correlation of land use, so as to better grasp the regional characteristics and spatial pattern of land use. The land use engine construction integrates land use feature data and spatial data to form an intelligent decision support system. Through comprehensive analysis and modeling of land use, the system can provide targeted intelligent decision support, including decision support in land planning, resource allocation, environmental protection and other aspects. Using the results of land use engine construction, users can make decisions related to land use more quickly and accurately. The data results constructed by the engine fully consider information from multiple aspects, which can help users comprehensively evaluate various factors and improve the efficiency and accuracy of decision-making.

[0202] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0203] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a land use intelligent engine, characterized in that: The following steps are involved: Step S1: Obtain land use data and land population data; Step S2: extracting land use characteristics from land use data and land population data to obtain land use characteristic data; Step S3: performing spatial data processing on the land use data to obtain land use spatial data; Step S4: constructing a land use engine according to the land use characteristic data and the land use spatial data to obtain land use engine data for assisting land use intelligent decision making; Wherein step S2 is specifically: Step S21: extracting basic land use features from the land use data to obtain basic land use feature data; Step S22: performing cluster calculation on the basic characteristic data of land use to obtain cluster characteristic data of land use; Step S23: Calculate the derived characteristics of the land use data and the land population data to obtain the land use derived characteristic data; Step S24: performing time series analysis and spatial analysis on the land use data to obtain land use time series characteristic data and land use spatial characteristic data respectively; Step S25: integrating the basic land use characteristic data, the land use cluster characteristic data, the land use derived characteristic data, the land use temporal characteristic data and the land use spatial characteristic data to obtain land use characteristic data; Wherein step S23 is specifically as follows: Calculate the land use population density based on the land use data and land population data to obtain the land use population density characteristic data; Gridding the land use data to obtain land use grid data; The spatial population calculation is performed on the land use grid data through the density kernel function to obtain the land use spatial population characteristic data; Calculate population migration based on land use data to obtain land use population migration characteristic data; Integrate land use population density characteristic data, land use spatial population characteristic data and land use population migration characteristic data into land use derived characteristic data; Wherein step S24 is specifically as follows: Step S241: performing time series segmentation on the land use data to obtain land use time series segmentation data; Step S242: performing time series change detection on the land use time series segmentation data to obtain land use time series feature data; Step S243: performing spatial object association analysis on the land use data to obtain land use spatial object association data; Step S244: performing spatial cluster analysis on the land use data and the land use spatial object associated data to obtain land use spatial characteristic data; The specific steps of step S244 are as follows: Perform density spatial clustering on land use data and land use spatial object associated data to obtain preliminary land use spatial characteristic data; The preliminary land use spatial characteristic data are subjected to density clustering scanning processing to obtain the land use spatial characteristic data.

2. The method according to claim 1, characterized in that Step S1 is specifically as follows: Step S11: collecting land use data and land population data through a land use database and land population data to obtain original land use data and original land population data; Step S12: collecting land space images through the Internet or geographic information system to obtain land space image data; Step S13: Projecting the land space image data according to the original land use data to obtain land use data; Step S14: performing association processing on the land space image data according to the original land population data to obtain land population data.

3. The method according to claim 2, characterized in that Step S13 is specifically as follows: Step S131: performing geographic coordinate conversion on the land space image data according to the original land use data to obtain land use image conversion data; Step S132: performing topological relationship analysis based on the land use image conversion data to obtain land use topological relationship data; Step S133: Perform multi-scale spatial analysis on the land use topological relationship data to obtain land use data.

4. The method according to claim 3, characterized in that The land use topological relationship data includes land use adjacency relationship data, land use connection relationship data, land use coverage relationship data and land use intersection relationship data. Step S132 is specifically as follows: Performing adjacency processing according to land use image conversion data to obtain land use adjacency data; Perform connection relationship processing according to land use image conversion data to obtain land use connection relationship data; Carry out coverage relationship processing according to land use image conversion data to obtain land use coverage relationship data; Cross-relationship processing is performed on the land use image conversion data to obtain land use cross-relationship data.

5. The method according to claim 3, characterized in that: Step S133 is specifically as follows: Performing data scale conversion on land use topological relationship data to obtain land use scale conversion data; Performing scale matching processing on the land use scale conversion data to obtain land use scale matching data; Multi-scale data fusion is performed on the land use scale matching data to obtain land use data.

6. The method according to claim 1, characterized in that Step S3 is specifically as follows: Identify the land boundaries and divide the land use data into plots to obtain the plot division data; Performing land use classification processing on the plot division data to obtain land use classification data; Obtaining land use optimization target data; According to the land use optimization target data, the land use classification data is spatially optimized to obtain the land use spatial data.

7. A system for constructing a land use intelligent engine, characterized in that: The method for constructing a land use intelligent engine according to claim 1 is used to execute the method, wherein the construction system of the land use intelligent engine comprises: The land use basic data collection module is used to obtain land use data and land population data; The land use feature extraction module is used to extract land use features from land use data and land population data to obtain land use feature data; The land use spatial data processing module is used to perform spatial data processing on the land use data to obtain the land use spatial data; The land use engine construction module is used to construct the land use engine according to the land use characteristic data and the land use spatial data, and obtain the land use engine data to perform land use intelligent decision-making auxiliary operations.

Images