Big data-based national space planning data intelligent analysis method

Abstract

The application discloses a land space planning data intelligent analysis method based on big data, relates to the technical field of land space planning, and comprises the following steps: collecting multi-source data and performing quality screening to form a standardized data set. Space element extraction rules are set based on specific planning targets, and key space elements are mined from the standardized data according to the rules. A big data analysis model is constructed, key elements are inputted to obtain a space development tendency index through calculation, and a preliminary planning scheme is generated accordingly. Then, the scheme is checked for compliance and evaluation data is generated, and the scheme is adjusted accordingly. Finally, spatial efficiency deduction calculation is performed on the adjusted scheme, the scheme is optimized according to the deduction result data, and the final planning scheme is outputted. The method improves the accuracy of data mining through target-driven element extraction, and enhances the forward-looking and scientific nature of the planning scheme through dynamic efficiency simulation.

Description

Technical Field

[0001] This invention belongs to the field of land and space planning technology, specifically a method for intelligent analysis of land and space planning data based on big data. Background Technology

[0002] In the field of territorial spatial planning, existing technologies generally rely on multi-source data aggregation and standardized processing as a foundation. However, in the identification and extraction of key spatial elements, existing methods primarily depend on pre-set general screening criteria or the experience and judgment of planners. This method of element extraction lacks a flexible and direct logical connection with the specific objectives and policy orientations of particular planning projects. The process is often static and passive, making it difficult to dynamically and accurately locate the spatial entities, structures, or patterns most relevant to the core intent of the current plan from massive amounts of standardized data, resulting in the data value not being fully realized.

[0003] In terms of generating and optimizing planning schemes, existing technical processes typically stop at the compliance review of preliminary schemes. This review mainly relies on static comparisons based on current regulations and standards, lacking dynamic simulations and quantitative predictions of the spatial development processes, interactions, and long-term comprehensive effects that may occur after the scheme is implemented. Subsequent adjustments to the scheme are mostly based on compliance conclusions and qualitative analysis, lacking timely data feedback from future scenario simulations to support optimization decisions. This makes it difficult for the final scheme generation process to form a closed-loop, self-iterably optimizing intelligent system.

[0004] A method is needed to address how to intelligently extract key spatial elements based on dynamic planning objectives, and how to drive continuous optimization of planning schemes based on forward-looking spatial performance simulation data. Summary of the Invention

[0005] This invention aims to solve at least one of the technical problems existing in the prior art;

[0006] To this end, the present invention proposes a data intelligence analysis method for land and space planning based on big data, including:

[0007] Collect basic land and space data from multiple sources, and perform quality screening on the basic land and space data from these multiple sources to generate a standardized set of land and space data.

[0008] Based on the planning objectives, spatial element extraction rules are set, and element mining is performed on the standardized land and space data set according to the spatial element extraction rules to extract the key spatial element set.

[0009] A big data analysis model for territorial spatial planning is constructed. The set of key spatial elements is input into the big data analysis model for territorial spatial planning, and a set of spatial development tendency indicators is obtained by calculation.

[0010] A preliminary planning scheme is generated based on the aforementioned set of spatial development tendency indicators;

[0011] A compliance verification calculation is performed on the preliminary planning scheme, and compliance evaluation data is generated based on the results of the compliance verification calculation.

[0012] Based on the compliance evaluation data, the planning elements of the preliminary planning scheme are adjusted to form the adjusted planning scheme;

[0013] Spatial efficiency simulation calculations are performed on the adjusted planning scheme to generate simulation result data. Based on the simulation result data, the adjusted planning scheme is optimized to output the final land spatial planning scheme.

[0014] Furthermore, the process involves aggregating multi-source land and space infrastructure data, performing quality screening on this multi-source data, and generating a standardized land and space data set, including:

[0015] Acquire multi-source basic land space data from surveying and mapping data, remote sensing data, socio-economic statistics data, and geographic national conditions monitoring data;

[0016] The multi-source land spatial basic data are subjected to operations such as spatial benchmark unification, data format conversion, attribute field alignment, and outlier detection.

[0017] Data integrity is supplemented and logical consistency is restored on the basic land and space data that has passed the outlier detection, and the standardized land and space data set is generated.

[0018] Furthermore, spatial element extraction rules are established based on the planning objectives, and element mining is performed on the standardized land and space data set according to the spatial element extraction rules to extract a set of key spatial elements, including:

[0019] Define spatial element types related to planning objectives, and configure element identification features and extraction condition thresholds for each spatial element type to form spatial element extraction rules;

[0020] The standardized land and space data set is imported into a spatial data mining engine, which performs traversal search and feature matching based on the spatial element extraction rules.

[0021] Data objects that meet the aforementioned feature recognition characteristics and extraction condition thresholds are clustered and labeled to form the set of key spatial features.

[0022] Furthermore, a big data analysis model for territorial spatial planning is constructed. The set of key spatial elements is input into the big data analysis model for territorial spatial planning, and the resulting set of spatial development trend indicators includes:

[0023] Build a big data analysis model for land spatial planning that includes trend analysis, correlation analysis, and constraint analysis functions;

[0024] Using the set of key spatial elements as input, the trend analysis function calculates the spatial development rate and direction, the correlation analysis function calculates the spatial coupling strength between elements, and the constraint analysis function identifies the limiting factors of development.

[0025] By aggregating the analysis results of the spatial development rate and direction, the spatial coupling strength between the elements, and the limiting factors of development, a set of spatial development tendency indicators containing development potential value, conflict risk value, and carrying pressure value is quantitatively calculated and output.

[0026] Furthermore, generating a preliminary planning scheme based on the aforementioned set of spatial development tendency indicators includes:

[0027] Priority development areas are delineated based on development potential values ​​in the aforementioned set of spatial development tendency indicators; coordination and control areas are delineated based on conflict risk values; and optimized protection areas are delineated based on carrying capacity pressure values.

[0028] Based on the land use classification standards of the national land spatial planning, construction and development uses are allocated in the priority development area, mixed-use uses are allocated in the coordinated control area, and ecological conservation uses are allocated in the optimized protection area, thus forming a preliminary spatial layout plan;

[0029] Configure planning indicators for the preliminary spatial layout scheme to generate a preliminary planning scheme that includes spatial boundaries, land use, and planning indicators.

[0030] Furthermore, performing compliance verification calculations on the preliminary planning scheme and generating compliance evaluation data based on the results of the compliance verification calculations includes:

[0031] Establish a compliance verification rule base that includes constraints from higher-level planning, technical specifications, and policy and regulatory requirements;

[0032] The preliminary planning scheme is compared and spatially overlaid with the clauses in the compliance verification rule base item by item;

[0033] Record the conforming, non-conforming, and borderline conforming items found in the comparison and overlay analysis, and quantitatively assess the degree of deviation of the non-conforming items to generate compliance evaluation data that includes a conformity list, a problem list, and deviation assessment values.

[0034] Furthermore, based on the compliance evaluation data, the planning elements of the preliminary planning scheme are adjusted to form the adjusted planning scheme, which includes:

[0035] Based on the issue list in the compliance evaluation data, identify the planning elements in the preliminary planning scheme that need to be adjusted;

[0036] For each issue, the direction and allowable adjustment range of the elements are generated according to the corresponding compliance verification rules;

[0037] Within the allowable adjustment range, the planning elements that need to be adjusted may undergo boundary correction, nature change, or indicator optimization.

[0038] After adjusting all issues, verify the conformity of the adjusted planning scheme with the compliance verification rule base to form the adjusted planning scheme.

[0039] Furthermore, spatial performance simulation calculations are performed on the adjusted planning scheme to generate simulation result data. Based on the simulation result data, the adjusted planning scheme is optimized to output the final land spatial planning scheme, including:

[0040] Establish a spatial performance evaluation target system that includes economic, social, and environmental benefits;

[0041] Using spatial simulation technology, the spatial development process of the adjusted planning scheme within the preset planning period is deduced;

[0042] Quantitatively calculate the benefit values ​​of the spatial development process under the spatial performance evaluation target system, and generate extrapolation result data including economic benefit value, social benefit value and environmental benefit value;

[0043] The balance of various benefit values ​​in the simulation results data is analyzed, and the key parameters in the adjusted planning scheme are iteratively optimized until the preset comprehensive performance requirements are met, and the final land space planning scheme is output.

[0044] Furthermore, the unification of spatial benchmarks for the aforementioned multi-source land spatial basic data includes:

[0045] Identify the coordinate system and projection method used by each of the multi-source land spatial data;

[0046] Transform all data to a preset unified spatial reference coordinate system;

[0047] Verify the spatial location accuracy of the converted data.

[0048] Furthermore, the association analysis function calculates the spatial coupling strength between elements, including:

[0049] Calculate the proximity of different key spatial elements in their spatial distribution;

[0050] Analyze the correlation between the changes in quantity and structure of different key spatial elements;

[0051] Combining the proximity and the correlation, the spatial coupling strength value, representing the degree of interdependence and influence between elements, is calculated using the coupling strength model.

[0052] Compared with the prior art, the beneficial effects of the present invention are:

[0053] By transforming specific planning objectives into calculable and executable spatial element extraction rules, and applying these rules to targeted mining of standardized land spatial data sets, the automatic identification and extraction of key spatial elements is achieved. This technology directly binds data filtering logic to planning intent, replacing traditional element identification methods that rely on fixed parameters or subjective experience. This enables the efficient and accurate separation of spatial entities, attributes, and relationships closely related to specific development orientations, constraints, or policy priorities from complex, multi-dimensional datasets, improving the accuracy and intelligence of information processing in the initial stage of planning analysis.

[0054] Based on the generated adjusted planning scheme, a spatial performance simulation and calculation model is introduced to dynamically simulate and predict the spatial processes, interactions, and long-term comprehensive impacts that may be triggered after the scheme's implementation. The scheme is then iteratively optimized based on the generated quantitative simulation results. This technology embeds a forward-looking simulation and feedback mechanism into the planning decision-making process, changing the previous optimization model that mainly relied on static rule compliance checks. This allows the adjustment of the scheme to be based on scientific predictions of future states, rather than merely inductions from historical patterns or the current situation, thereby enhancing the forward-looking nature, adaptability, and reliability of the planning scheme and the decision-making process. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating the steps of the intelligent analysis method for land spatial planning data based on big data as described in this invention.

[0056] Figure 2 A flowchart for the collection and standardization of multi-source land spatial basic data;

[0057] Figure 3 A flowchart for extracting key spatial elements;

[0058] Figure 4 Box-line map showing the distribution of the three core indicators of spatial units in territorial spatial planning;

[0059] Figure 5 The curves showing the changes in key parameters and overall effectiveness of the land spatial planning scheme during iterative optimization. Detailed Implementation

[0060] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] See Figure 1 This process involves collecting basic land and space data from various sources, screening the quality of this multi-source data, generating a standardized land and space data set, formulating spatial element extraction rules based on pre-set planning objectives, and mining key spatial elements from the standardized dataset based on these rules. A specialized big data analysis model for land and space planning is then constructed. The key spatial element set is input into this model for computation, resulting in a set of spatial development trend indicators. A preliminary planning scheme is generated based on these indicators, and compliance verification calculations are performed on this preliminary scheme. Compliance evaluation data is generated based on the calculation results, and adjustments are made to the planning elements in the preliminary scheme based on the compliance evaluation data to form an adjusted planning scheme. Spatial effectiveness extrapolation calculations are performed on the adjusted scheme to generate extrapolation result data, and the scheme is optimized based on this result data, ultimately outputting the finalized land and space planning scheme.

[0062] See Figure 2 In one embodiment of the present invention, multi-source land spatial data is collected and quality-screened to generate a standardized land spatial data set. This is achieved through the following steps: acquiring multi-source land spatial data from surveying and mapping data, remote sensing data, socio-economic statistical data, and geographic national condition monitoring data. In specific implementation, surveying and mapping data includes topographic maps and control point coordinates; remote sensing data includes multispectral satellite imagery; socio-economic statistical data includes tables of population distribution and industrial output; and geographic national condition monitoring data includes land cover classification patches. These data are stored in different formats and spatial references. For example, surveying and mapping data uses an independent city coordinate system; remote sensing data uses the WGS84 geographic coordinate system; socio-economic statistical data is in tabular format without spatial coordinates; and geographic national condition monitoring data uses the National Geodetic Coordinate System 2000. Data comparison shows significant differences in coordinate systems, file formats, and attribute structures, requiring operations such as spatial benchmark unification, data format conversion, attribute field alignment, and outlier detection.

[0063] In specific implementation, unifying the spatial reference for the multi-source land spatial basic data includes identifying the coordinate system and projection method used by each of the multi-source land spatial basic data. In some embodiments, the coordinate system is identified by reading data metadata or file header information. For example, surveying data is identified as "City_Local_CS", remote sensing data as "EPSG:4326", and geographic national condition monitoring data as "CGCS2000_Gauss_Kruger". All data are then converted to a preset unified spatial reference coordinate system. The coordinate system is defined as "CGCS2000_3_Degree_GK_Zone_38". Batch conversion is performed using a coordinate transformation tool. A data comparison example shows that before conversion, the coordinates of a point in the survey data were (50000, 30000) meters, and in the remote sensing data, they were (116.5°E, 40.2°N). After conversion, in the unified spatial reference coordinate system, all coordinates are (3850000, 500000) meters. Spatial location accuracy is verified on the converted data. This verification is achieved by calculating the conversion residuals. One possible verification formula is as follows:

[0064]

[0065] in: Indicates the average positional deviation. Indicates the number of checkpoints. and This represents the x and y coordinates of the checkpoint after the transformation. and Represents the x and y coordinates of the reference point, when The verification is passed when the value is less than a preset threshold, such as 0.5 meters.

[0066] In some embodiments, data format conversion is performed on the multi-source land spatial data to unify vector data into Shapefile format, raster data into GeoTIFF format, and tabular data into CSV format. Attribute field alignment operations map attribute names and data types from different data sources to standard fields. For example, the "Class" field of remote sensing data and the "LandCover" field of geographic national condition monitoring data are aligned to the standard field "Surface Type". Outlier detection operations apply statistical methods to numerical attribute fields to identify outliers. In specific implementations, for the population density field, the mean and standard deviation of all records are calculated, and outliers exceeding three times the standard deviation of the mean are identified. Records within the area were marked as anomalies. Data comparison showed that before anomaly detection, the population density of a certain area was recorded as 5000 people / square kilometer. After detection, it was corrected to 500 people / square kilometer based on the context. Data integrity completion and logical consistency repair were performed on the basic land spatial data that passed the anomaly detection. It can be understood that data integrity completion uses spatial interpolation or the mean of neighboring records to fill missing attribute values. Logical consistency repair checks and corrects geometric topological errors, such as eliminating overlapping or gaps in surface features, to generate the standardized land spatial data set. The standardized land spatial data set is stored in a spatial database and contains a unified coordinate reference, format, and attribute structure for subsequent feature mining.

[0067] Optionally, after batch conversion, the spatial benchmark unification operation performs a visual overlay check. This can be understood as loading the converted data layer through GIS software and observing whether the boundaries of the same land feature, such as a river, overlap in different data sources. Data comparison and overlay display show that the boundary deviation was as high as 10 meters before conversion, and the deviation was reduced to within 1 meter after conversion. Optionally, in addition to statistical methods, outlier detection can also combine domain knowledge to set fixed thresholds. For example, records with an altitude greater than 9000 meters or less than -500 meters are judged as outliers. In specific implementation, for missing land type codes, data integrity completion assigns values ​​based on the codes of adjacent map patches. Logical consistency repair uses graphics processing algorithms to automatically correct geometric errors. The generated standardized land spatial dataset serves as the input basis for the entire analysis process.

[0068] See Figure 3In one embodiment of the present invention, spatial element extraction rules are set based on planning objectives, and element mining is performed on a standardized set of land and space data according to the spatial element extraction rules. This is achieved through the following steps: defining spatial element types related to the planning objectives and configuring element identification features and extraction condition thresholds for each spatial element type to form spatial element extraction rules. In some embodiments, the planning objective is to identify regional ecological security patterns, and the defined spatial element types include "ecological source areas" and "ecological corridors." The element identification features configured for the "ecological source area" spatial element type are high vegetation coverage and low population density. The specific extraction thresholds for the interference level include a normalized vegetation index (NVI) value greater than 0.6, a distance from the boundary of the built-up area greater than 1000 meters, and a continuous area of ​​map patches greater than 1 square kilometer. The feature identification characteristic configured for the spatial element type of "ecological corridor" is a potential low-resistance path connecting the ecological source area. The extraction thresholds include a land surface type of forest or water and a slope of less than 15 degrees. Data comparison shows that the value range of the "NVI" field varies in different data sources. After standardization, the value of this field in the dataset is uniformly normalized to the range of [-1,1], so that the threshold of 0.6 has a consistent physical meaning.

[0069] In practice, a standardized set of territorial spatial data is imported into a spatial data mining engine. The spatial data mining engine performs traversal search and feature matching based on spatial element extraction rules. In some embodiments, the spatial data mining engine loads a data layer containing normalized vegetation index (NZVI) rasters, land use type vectors, and digital elevation models. For the extraction of "ecological source areas," the engine traverses each raster cell, calculates its NZVI value and determines whether it is greater than 0.6. At the same time, it queries the land use type corresponding to its spatial location and the distance from the built-up area. Data comparison examples show that before the traversal search, there are 1 million cells in the study area. After feature matching, 50,000 cells meet the conditions of a vegetation index greater than 0.6 and a distance greater than 1,000 meters. The spatial data mining engine further aggregates the continuously distributed cells, filters out patches with an area greater than 1 square kilometer, and finally matches 15 candidate objects that meet all the extraction condition thresholds for "ecological source areas."

[0070] Optionally, the spatial data mining engine employs multi-condition overlay analysis during feature matching. For the identification of "ecological corridors," the engine first generates an initial resistance surface based on land use type and slope conditions. The resistance surface is assigned a value of 1 for forest land, 2 for water area, 5 for grassland, 10 for cultivated land, and 100 for construction land. The resistance value increases by 1 for every 1 degree increase in slope. The engine then runs a minimum cumulative resistance model. In practice, the minimum cumulative resistance model is calculated starting from the identified ecological source pixels. The spatial data mining engine traverses and calculates the cumulative resistance cost from each pixel to the nearest ecological source, generating a cumulative resistance surface. Based on the spatial element extraction rules, low-resistance channels with cumulative resistance values ​​less than a preset threshold and spatially connecting two or more ecological source areas are marked as potential ecological corridors. Data comparison shows that directly identifying "corridors" based on land use classification will result in fragmented line segments, while after traversing and searching based on the minimum cumulative resistance model by the spatial data mining engine, a continuous and meandering corridor network is obtained, and the number of candidate corridors is integrated from hundreds of discrete line segments into dozens of main channels.

[0071] Data objects that meet the feature identification characteristics and extraction threshold are clustered and labeled to form a key spatial feature set. In specific implementation, for the identified candidate "ecological source areas" patches, a density-based spatial clustering algorithm is used for aggregation, merging neighboring patches with a spatial distance of less than 200 meters into one ecological source area feature. The formula used for the clustering operation is as follows:

[0072]

[0073] in: This indicates the spatial aggregation degree between patch a and patch b. and These represent the number of pixels contained in patch a and patch b, respectively. Let represent the Euclidean distance between the i-th pixel in patch a and the j-th pixel in patch b. This represents the preset aggregation distance threshold. This is an indicator function that takes the value 1 when the condition is true and 0 otherwise. It can be understood that when... When the calculated result is greater than 0.5, the two candidate patches are merged. After merging, their geometric centers and total areas are recalculated. Data comparison shows that there were 15 candidate ecological source patches before clustering. After the above clustering and merging operations, 8 key ecological source spatial elements are finally labeled. The spatial data mining engine assigns a unique identifier and attributes to each final element, including element type, area, average vegetation index, etc. All "ecological source areas" and "ecological corridors" together constitute a set of key spatial elements related to the ecological security pattern planning objectives. Optionally, the traversal search of the spatial data mining engine can be configured as an iterative process, adjusting the threshold based on the previous round of matching results for fine-grained searching.

[0074] In one embodiment of the present invention, a land spatial planning big data analysis model is constructed and a set of key spatial elements is input into the model for computation. This is achieved through the following steps: A land spatial planning big data analysis model including trend analysis, correlation analysis, and constraint analysis functions is built. In specific implementation, the land spatial planning big data analysis model is implemented as a software module. The trend analysis module loads time-series spatial data, the correlation analysis module integrates spatial statistics and correlation calculation algorithms, and the constraint analysis module has a built-in rule engine and spatial query tool. The set of key spatial elements is used as input. The set of key spatial elements includes residential land elements, industrial land elements, transportation node elements, and ecological protection zone elements extracted from historical data. Data comparison shows that the input set of key spatial elements contains 120 residential land parcels and 45 industrial land parcels. The map features 80 points for the map parcels and transportation nodes, and 25 areas for the ecological protection zone. The spatial development rate and direction are calculated using the trend analysis function. In some embodiments, the trend analysis function is based on five consecutive years of land use change data to calculate the expansion or contraction rate of each spatial element type. For residential land elements, the distance and directional angle of their geometric center movement between adjacent years are calculated. The spatial development rate is expressed as an annual average area change percentage, and the spatial development direction is expressed as the dominant expansion azimuth angle. In the example scenario, the spatial development rate of residential land elements in the eastern region is 8.5% per year, and the spatial development direction is 15 degrees east of south. The spatial development rate of industrial land elements in the northwest region is 5.2% per year, and the spatial development direction is due north. The data comparison shows that there are differences in the spatial development rate and direction of different element types, and the expansion rate of residential land elements is higher than that of industrial land elements.

[0075] The spatial coupling strength between elements is calculated using the correlation analysis function. This calculation includes determining the proximity of different key spatial elements in their spatial distribution and analyzing the correlation between these key spatial elements in terms of quantity and structural changes. In practice, the spatial proximity of residential land elements and transportation node elements is calculated using the average nearest neighbor distance metric. The average distance from the geometric center of a residential land element patch to the nearest transportation node element is 500 meters, while the average distance from the geometric center of an industrial land element patch to the nearest transportation node element is 1200 meters. Data comparison shows that the proximity between residential land elements and transportation node elements is higher than that between industrial land elements and transportation node elements. The correlation between different key spatial elements in terms of quantity and structural changes is analyzed. For the annual change rate of residential land element area and the annual change rate of industrial land element area, the Pearson correlation coefficient is calculated. In the example scenario, the correlation coefficient is 0.78, indicating a positive correlation between the two in terms of quantity changes. Combining proximity and correlation, the spatial coupling strength value, representing the degree of interdependence and influence between elements, is calculated using the coupling strength model. One possible implementation formula for the coupling strength model is:

[0076]

[0077] in: This represents the spatial coupling strength between feature type x and feature type y. This represents the average spatial proximity distance between feature type x and feature type y. This represents the correlation coefficient between element type x and element type y in terms of quantity changes. , , These are model parameters used to adjust the weights of distance decay and correlation. In practice, the parameters are set as follows: , , Calculate residential land use elements and transportation node elements rice, Substituting into the formula, we get Calculate the industrial land use elements and transportation node elements. rice, Substituting into the formula, we get Data comparison shows that the spatial coupling strength between residential land and transportation nodes is higher than that between industrial land and transportation nodes.

[0078] The constraint analysis function identifies limiting factors for development. In some embodiments, the constraint analysis function identifies spatial development constraints based on topographic data, ecological protection red line data, and infrastructure coverage data. For each planning unit, the constraint analysis function calculates the average slope, whether it is located within the ecological protection red line, and the distance to the nearest sewage treatment plant. Areas with an average slope greater than 25 degrees, located within the ecological protection red line, and more than 5 kilometers away from the sewage treatment plant are marked as high-restriction areas. In the example scenario, the northwest area has an average slope of 30 degrees and is located within the ecological protection red line, and is identified as a limiting factor for development. Data comparison shows that the eastern area has fewer limiting factors while the northwest area has more. The analysis results of spatial development rate and direction, spatial coupling strength between elements, and limiting factors are aggregated to quantitatively calculate and output a set of spatial development tendency indicators including development potential value, conflict risk value, and carrying capacity pressure value. It can be understood that the development potential value is calculated by comprehensively considering the spatial development rate, spatial coupling strength, and the reverse scoring of limiting factors, while the conflict risk value... Based on the intersection and overlap of spatial expansion directions of different element types and the calculation of conflicts with restricted areas, the carrying capacity pressure value is calculated based on the ratio of current development intensity to resource and environmental thresholds. In specific implementation, for each 1-square-kilometer grid unit, the development potential value is calculated through a weighted summation model, with inputs including the standardized value of the spatial development rate of the unit, the average value of the relevant spatial coupling intensity, and the inverse index of the restrictive factor. The conflict risk value is calculated through an overlay analysis model, with inputs including the buffer zone overlay area of ​​different element types expansion directions and the area overlapping with the ecological red line. The carrying capacity pressure value is calculated through a ratio model, with inputs including the ratio of current population density to water resource carrying capacity and the ratio of current construction land ratio to land carrying capacity limit. The output set of spatial development tendency indicators is stored in the form of a grid layer. Each grid contains three values: development potential value, conflict risk value, and carrying capacity pressure value. Data comparison shows that the eastern region has a higher development potential value, a medium conflict risk value, and a lower carrying capacity pressure value, while the northwestern region has a lower development potential value, a higher conflict risk value, and a higher carrying capacity pressure value. Optionally, the trend analysis function can incorporate more time-point data to improve the accuracy of rate calculations. Similarly, the correlation analysis function can be extended to include correlations with structural changes such as changes in shape indices. Optionally, the constraint analysis function can dynamically update the limiting factors identified to reflect policy changes.

[0079] In one embodiment of the present invention, a preliminary planning scheme is generated based on a set of spatial development tendency indicators. This set is stored in a grid format, with each grid cell containing three values: development potential, conflict risk, and carrying capacity pressure. An example scenario is selected: a study area containing 100 regular spatial cells. Data comparison shows significant differences in indicator values ​​among different spatial cells. Priority development areas are delineated based on the development potential values ​​in the spatial development tendency indicator set, with the rule being that spatial cells with a development potential value greater than 0.7 are included in priority development areas. Coordination and control areas are delineated based on the conflict risk values, with the rule being that spatial cells with a conflict risk value greater than 0.6 are included in coordination and control areas. Optimized protection areas are delineated based on the carrying capacity pressure values, with the rule being that spatial cells with a carrying capacity pressure value greater than 0.8 are included in optimization and protection areas. In some embodiments, spatial units are classified into optimized protection areas using spatial analysis tools of geographic information system software. Each grid unit is classified according to the aforementioned threshold conditions, and the classification results form a spatial distribution map of priority development areas, coordinated control areas, and optimized protection areas. Data comparison shows that there are 30 spatial units with a development potential value greater than 0.7, 25 spatial units with a conflict risk value greater than 0.6, and 20 spatial units with a carrying capacity pressure value greater than 0.8. Some spatial units meet multiple conditions simultaneously. The processing rule is to prioritize the carrying capacity pressure value condition, followed by the conflict risk value condition, and finally the development potential value condition. If a spatial unit has a carrying capacity pressure value greater than 0.8, it is directly classified into the optimized protection area without further consideration of other conditions.

[0080] Based on the land use classification standards of the territorial spatial planning, construction and development uses are allocated within priority development areas, including residential land, public management and public service facilities land, and commercial service facilities land. In the coordinated control areas, mixed-use uses are allocated, including agricultural production and ecological leisure mixed-use land, and urban construction and ecological protection mixed-use land. In the optimized protection areas, ecological conservation uses are allocated, including forest land and water areas. This forms a preliminary spatial layout plan. In specific implementation, the allocation is carried out according to the land use classification standard codes of the territorial spatial planning. Spatial units within priority development areas are assigned the default major category code of urban construction land, and then subdivided into intermediate categories based on location and surrounding conditions. For example, central area units are allocated as commercial service facilities land, while peripheral area units are allocated as residential land. Spatial units within the coordinated control areas are allocated according to the principles of dominant function and compatibility. Assigning composite land use codes, such as assigning a composite land use code for agricultural production and ecological leisure to areas that combine farmland and park functions, and strictly assigning ecological land use codes such as forest land or water area to spatial units within the optimized protection area, configuring planning indicators for the preliminary spatial layout scheme, including the total construction land area, green space and square area, and permanent population size, generating a preliminary planning scheme containing spatial boundaries, land use nature, and planning indicators. The preliminary planning scheme is expressed in the form of vector layers and attribute tables. The spatial boundary of each spatial unit is converted from raster to polygon. The land use nature is stored in the "land use code" field of the attribute table. The planning indicators are summarized in the scheme summary table. Data comparison shows that the total construction land area configured in the preliminary planning scheme is 50 square kilometers, of which the priority development area contributes 40 square kilometers, the coordinated control area contributes 10 square kilometers, and there is no construction land in the optimized protection area (see Table 1).

[0081] Table 1: Spatial Unit Data Table of Preliminary Planning Scheme

[0082] Space unit numbering Region type Land use code Development potential value Conflict risk value Bearing pressure value A01 Priority development areas R2 0.85 0.45 0.30 B05 Coordinated control area E2 / G1 0.60 0.75 0.55 C12 Optimize protected areas E1 0.20 0.40 0.92 A15 Priority development areas B1 0.78 0.50 0.35 B22 Coordinated control area A9 / G2 0.55 0.68 0.60

[0083] To ensure compliance verification of the preliminary planning scheme, a compliance verification rule base is established, encompassing constraints from higher-level planning, technical specifications, and policy and regulatory requirements. This rule base is stored in a structured database table format, with each rule including a rule number, rule content, constraint type, applicable spatial scope, and threshold parameters. The preliminary planning scheme is then compared item by item with the clauses in the compliance verification rule base, and spatial overlay analysis is performed. Item-by-item comparison targets planning indicators, such as comparing the ecological protection red line area calculated from the preliminary planning scheme with the threshold of "not less than 100 square kilometers" in the rule base. Spatial overlay analysis targets spatial layout, such as overlaying the construction land area layer of the preliminary planning scheme with the permanent basic farmland protection area layer to analyze whether spatial overlap exists.

[0084] Record the conforming, non-conforming, and borderline conforming items found in the comparison and overlay analysis, and quantitatively assess the deviation degree of non-conforming items to generate compliance evaluation data including a conformity list, a problem list, and deviation assessment values. In some embodiments, the comparison found that the ecological protection red line area in the preliminary planning scheme is 98 square kilometers, which does not comply with the constraints of the higher-level plan, with a deviation of 2 square kilometers. The overlay analysis found that the construction land area of ​​3 spatial units in the preliminary planning scheme overlaps with the permanent basic farmland, with an overlapping area of ​​0.5 square kilometers, which does not comply with policy and regulatory requirements. The deviation assessment value is calculated based on the deviation amount. For area-based indicators, the deviation assessment value is:

[0085]

[0086] in: This indicates the deviation assessment value. This represents the threshold required by the rule. This represents the actual value in the preliminary planning scheme; in the example, it is the deviation assessment value of the ecological protection red line area. The compliance list records items such as "12 square meters of green space per capita, in compliance with technical specifications," while the issue list records items such as "insufficient area of ​​ecological protection red line" and "occupation of permanent basic farmland," along with specific spatial locations and deviation assessment values. Compliance evaluation data is output in report form. Optionally, spatial overlay analysis is performed using the overlay and intersection tools of a geographic information system.

[0087] See Figure 4In the data feature analysis stage of territorial spatial planning, the distribution characteristics of the three core indicators of spatial units—development potential, conflict risk, and carrying capacity—are quantitatively and visually represented using box plots. Specifically, using 100 regular spatial units as a research sample, the standardized values ​​of the three indicators are constructed into a discrete data distribution set. The boxes, whiskers, and outlier points of the box plot respectively map the quartile intervals, ranges, and extreme discrete values ​​of the indicators. The dispersion and central tendency of the indicator distribution were quantitatively analyzed using box plot topology: the upper edge of the box for bearing pressure value exceeded the 0.8 threshold, and the median was significantly higher than the other two indicators. Combined with the extension range of the whiskers, it can be seen that the high-value area of ​​this indicator has a high concentration, and there are low-value outliers below 0.3, which matches the highest degree of matching with the threshold for delineating optimized protection areas (0.8). The median of the box for conflict risk value is about 0.6, and the upper quartile does not exceed 0.7, corresponding to the threshold for delineating coordinated control areas (0.6). The lower whisker extends to 0.2, showing that the indicator distribution span is large. The upper quartile of the box for development potential value is close to 0.8, and the median is about 0.68, forming a critical distribution characteristic with the threshold for delineating priority development areas (0.7), and there are extreme low-value outliers below 0.1. The topological comparison of the box plots of the three indicators clearly presents the differentiated characteristics of spatial development trends, providing direct data distribution basis for subsequent threshold-based spatial area classification, priority determination, and preliminary planning scheme preparation.

[0088] In one embodiment of the present invention, the compliance evaluation data problem list includes two items: "insufficient area of ​​ecological protection red line" and "occupation of permanent basic farmland". The corresponding deviation evaluation values ​​are 0.02 and 0.005, respectively. Regarding the problem of "insufficient area of ​​ecological protection red line", two map patches with spatial unit numbers A15 and B22 in the preliminary planning scheme are located. Their current land use nature is commercial service facility land and agricultural production and ecological leisure composite land, respectively, but neither is included in the ecological protection red line range. Regarding the problem of "occupation of permanent basic farmland", three map patches with spatial unit numbers A01, B05 and C12 in the preliminary planning scheme are located. Their land use range has spatial overlap with the permanent basic farmland protection zone layer, with overlap areas of 0.2, 0.2 and 0.1 square kilometers, respectively. Data comparison shows that the ecological protection red line area in the preliminary planning scheme before adjustment is 98 square kilometers, and the area occupied by permanent basic farmland is 0.5 square kilometers.

[0089] For each issue, the direction and allowable adjustment range of the element are generated according to the corresponding compliance verification rules. In some embodiments, corresponding to the higher-level planning constraint that "the area of ​​the ecological protection red line shall not be less than 100 square kilometers", the generated element adjustment direction is "to change some non-ecological land in the preliminary planning scheme to ecological conservation land to increase the area of ​​the ecological protection red line", and the allowable adjustment range is "to increase the area of ​​the ecological protection red line by at least 2 square kilometers, and the newly added ecological land should be selected first from non-red line areas with higher current ecological value". Corresponding to the policy and regulatory requirement that "it is strictly forbidden to occupy permanent basic farmland", the generated element adjustment direction is "to adjust the boundary or nature of construction land or composite land that overlaps with permanent basic farmland in the preliminary planning scheme to eliminate the overlap", and the allowable adjustment range is "the overlapping area must be reduced to zero, and the adjustment can be achieved by boundary shrinkage or changing the land use nature to permanent basic farmland". In specific implementation, the allowable adjustment range is determined by calculating the difference between the threshold of the rule clause in the compliance verification rule base and the current value of the preliminary planning scheme.

[0090] Within the permissible adjustment range, boundary corrections, nature changes, or indicator optimizations are made for planning elements requiring adjustment. Regarding the issue of "insufficient ecological protection red line area," within the permissible adjustment range, spatial unit A15, adjacent to existing forest land and with low development potential, is selected, and its land use is changed from commercial service facilities land to forest land. The ecological function portion of spatial unit B22 is selected, and its composite land use is adjusted from agricultural production to ecological recreation, without changing the total area but enhancing its ecological attributes. After the nature change, the preliminary calculation shows that the ecological protection red line area increases by 2.2 square kilometers. Data comparison shows that the total ecological protection red line area reaches 100.2 square kilometers after the change, meeting the constraint of not less than 100 square kilometers. Regarding the issue of "occupying permanent basic farmland," within the permissible adjustment range, the boundary of spatial unit A01 is corrected, and the 0.2 square kilometer area overlapping with permanent basic farmland is removed from the construction land boundary. The area of ​​the adjusted A01 unit is reduced. The area of ​​spatial unit B05 is also adjusted. The land use of the Yuan project was changed from a mixed agricultural and ecological recreation area to permanent basic farmland, covering an area of ​​0.2 square kilometers that overlapped with permanent basic farmland. The boundary of spatial unit C12 was also modified; since it is ecological conservation land within an optimized protection area, its boundary was reduced by 0.1 square kilometers to avoid permanent basic farmland. After these adjustments, the area occupied by the preliminary planning scheme and permanent basic farmland was reduced to zero. After completing all the adjustments, the revised planning scheme was verified to conform to the compliance verification rule base, resulting in the revised planning scheme. The verification process involved comparing the revised scheme with the compliance verification rule base item by item and performing spatial overlay analysis. Once it was confirmed that the ecological protection red line area met the requirements and did not occupy permanent basic farmland, the revised planning scheme was confirmed. Data comparison showed that the total construction land area of ​​the revised planning scheme decreased from 50 square kilometers to 49.7 square kilometers, while the ecological protection red line area increased from 98 square kilometers to 100.2 square kilometers.

[0091] The operation of performing spatial performance simulation calculations on the adjusted planning scheme is as follows: A spatial performance evaluation target system is established, encompassing economic, social, and environmental benefits. In specific implementation, economic benefit targets include GDP and land transfer revenue; social benefit targets include public service facility coverage and job-housing balance index; and environmental benefit targets include carbon sequestration and surface water quality compliance rate. The spatial performance evaluation target system assigns weights to each target and sets benchmark values. Using spatial simulation technology, the spatial development process of the adjusted planning scheme within the preset planning period is simulated. In some embodiments, the preset planning period is 10 years. The model simulates the spatial simulation of intelligent agents by inputting the adjusted planning scheme's land use layout, infrastructure planning, and socio-economic forecast parameters. The model simulates the dynamic process of population distribution, industrial layout, traffic flow, and land use changes over the next ten years. The spatial simulation technology calculates the state changes of each spatial unit year by year and records key indicators. Data comparison shows that the construction land area in the starting year (year 0) is 49.7 square kilometers, which increases to 52.1 square kilometers in year 5 and reaches 54.0 square kilometers in year 10. The simulation process shows that development mainly occurs in priority development areas.

[0092] The quantitative calculation of various benefit values ​​of the spatial development process under the spatial efficiency evaluation target system generates projection results data including economic, social, and environmental benefit values. In specific implementation, the economic benefit value is calculated by summing the output of each industrial sector at the end of the simulation period; the social benefit value is obtained by calculating and normalizing indicators such as the proportion of the population served by public service facilities and the average commuting time at the end of the simulation period; and the environmental benefit value is obtained by cumulatively calculating the change in carbon sink during the simulation period and the proportion of water quality compliance area calculated based on the water quality model. The projection results data are presented in the form of numerical tables. It can be understood that an intermediate calculation formula for quantifying comprehensive benefits is as follows:

[0093]

[0094] in: The comprehensive evaluation value representing spatial effectiveness. This represents the economic benefit value at the end of the simulation period. This represents the social benefit value at the end of the simulation period. This represents the environmental benefit value at the end of the simulation period. , , These are the preset lower limit benchmark values ​​for each benefit. , , These are the preset upper limit expected values ​​for each benefit. , , In this example, the weighting coefficients are set to correspond to the economic, social, and environmental benefits. , , The formula is used internally to calculate the normalized contribution of each benefit and is not directly used as the final output. The generated simulation results show that the economic benefit value at the end of the simulation period (year 10) is 12 billion yuan, the social benefit value is 0.75, and the environmental benefit value is 0.68.

[0095] The analysis examines the balance of various benefit values ​​in the simulation results. Iterative optimization of key parameters in the adjusted planning scheme is performed until the preset comprehensive performance requirements are met, resulting in the final land spatial planning scheme. In some embodiments, the analysis reveals that the social benefit value of 0.75 in the first round of simulation results is lower than the preset target of 0.80, while the economic benefit value of 12 billion yuan is higher than the preset target of 11 billion yuan, indicating an imbalance between benefits. Key parameters include the proportion of public facility land and the upper limit of development intensity within the priority development area. The adjusted planning scheme is optimized by lowering the upper limit of development intensity for unit A01 (commercial service facility land) within the priority development area from a plot ratio of 3.0 to 2.8, and changing the land use of 0.1 square kilometers within this unit from commercial service facility land to public management and public service facility land. Using the optimized scheme parameters, spatial simulation and benefit value quantification are re-executed. Optionally, the iterative optimization process is performed automatically until the comprehensive evaluation value of spatial performance is achieved. With all benefit values ​​exceeding the preset threshold of 0.80 and not lower than 90% of their respective preset targets, after two rounds of iterative optimization, the projection results show an economic benefit value of 11.5 billion yuan, a social benefit value of 0.80, an environmental benefit value of 0.70, and a comprehensive evaluation value of [missing value]. The value is 0.82, which meets the preset comprehensive efficiency requirements. The final output of this round of optimization is the final land space planning scheme. Data comparison shows that compared with the adjusted planning scheme, the area of ​​public facilities land in the final land space planning scheme has increased by 0.5 square kilometers, and the average plot ratio of commercial service facilities land has decreased.

[0096] See Figure 5In the key parameter adjustment and comprehensive performance evaluation system for the iterative optimization of territorial spatial planning schemes, the coupling relationship between parameter changes and performance improvement can be interpreted through dual-axis quantitative analysis. Specifically, the left vertical axis represents the numerical changes in planning parameters such as the upper limit of commercial land floor area ratio and the increase in public facility land area, while the right vertical axis corresponds to the quantitative results of the comprehensive spatial performance score. In the initial scheme stage, the upper limit of commercial land floor area ratio was set at 3.0, the increase in public facility land area was 0 km², and the comprehensive performance score was 0.75. In the first round of optimization, by lowering the upper limit of commercial land floor area ratio to 2.9 and increasing public facility land area by 0.2 km², the comprehensive performance score improved to 0.80. In the second round of optimization, the upper limit of commercial land floor area ratio was further reduced to 2.8, while the increase in public facility land area was increased to 0.5 km², ultimately achieving a comprehensive performance score of 0.82, meeting the preset threshold requirements. The inherent logic of parameter adjustment follows an iterative path of "benefit balance - efficiency improvement": by appropriately reducing the intensity of commercial development (maximum floor area ratio), incremental land resources are released for public facilities, thereby achieving a dynamic balance between economic and social benefits, ultimately driving a step-by-step improvement in the comprehensive efficiency score. In this process, the magnitude of parameter adjustment and the magnitude of efficiency improvement show a significant positive correlation, verifying the effectiveness of the planning methodology of "refined control of key parameters - systematic optimization of spatial efficiency."

[0097] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A data-driven intelligent analysis method for land and space planning based on big data, characterized in that: The method includes: Collect basic land and space data from multiple sources, and perform quality screening on the basic land and space data from these multiple sources to generate a standardized set of land and space data. Based on the planning objectives, spatial element extraction rules are established, and element mining is performed on the standardized land and space data set according to the spatial element extraction rules to extract a key spatial element set. This includes: defining spatial element types related to the planning objectives, configuring element identification features and extraction condition thresholds for each spatial element type to form spatial element extraction rules; importing the standardized land and space data set into a spatial data mining engine, which performs traversal search and feature matching according to the spatial element extraction rules; and clustering and labeling data objects that meet the element identification features and extraction condition thresholds to form the key spatial element set. A big data analysis model for territorial spatial planning is constructed. The key spatial element set is input into the model to calculate a set of spatial development tendency indicators. This includes: building a big data analysis model for territorial spatial planning that incorporates trend analysis, correlation analysis, and constraint analysis functions; using the key spatial element set as input, the trend analysis function calculates the spatial development rate and direction, the correlation analysis function calculates the spatial coupling strength between elements, and the constraint analysis function identifies limiting factors for development; aggregating the analysis results of the spatial development rate and direction, the spatial coupling strength between elements, and the limiting factors for development, and quantitatively calculating and outputting a set of spatial development tendency indicators that includes development potential values, conflict risk values, and carrying capacity pressure values. A preliminary planning scheme is generated based on the aforementioned set of spatial development tendency indicators; A compliance verification calculation is performed on the preliminary planning scheme, and compliance evaluation data is generated based on the results of the compliance verification calculation. Based on the compliance evaluation data, the planning elements of the preliminary planning scheme are adjusted to form the adjusted planning scheme; Spatial efficiency simulation calculations are performed on the adjusted planning scheme to generate simulation result data. Based on the simulation result data, the adjusted planning scheme is optimized to output the final land spatial planning scheme.

2. The intelligent analysis method for land spatial planning data based on big data as described in claim 1, characterized in that, The process involves collecting multi-source basic land spatial data, performing quality screening on the multi-source basic land spatial data, and generating a standardized land spatial data set, including: Acquire multi-source basic land space data from surveying and mapping data, remote sensing data, socio-economic statistics data, and geographic national conditions monitoring data; The multi-source land spatial basic data are subjected to operations such as spatial benchmark unification, data format conversion, attribute field alignment, and outlier detection. Data integrity is supplemented and logical consistency is restored on the basic land and space data that has passed the outlier detection, and the standardized land and space data set is generated.

3. The intelligent analysis method for land spatial planning data based on big data as described in claim 2, characterized in that, The preliminary planning scheme generated based on the aforementioned set of spatial development tendency indicators includes: Priority development areas are delineated based on development potential values ​​in the aforementioned set of spatial development tendency indicators; coordination and control areas are delineated based on conflict risk values; and optimized protection areas are delineated based on carrying capacity pressure values. Based on the land use classification standards of the national land spatial planning, construction and development uses are allocated in the priority development area, mixed-use uses are allocated in the coordinated control area, and ecological conservation uses are allocated in the optimized protection area, thus forming a preliminary spatial layout plan; Configure planning indicators for the preliminary spatial layout scheme to generate a preliminary planning scheme that includes spatial boundaries, land use, and planning indicators.

4. The intelligent analysis method for land spatial planning data based on big data as described in claim 3, characterized in that, Performing compliance verification calculations on the preliminary planning scheme and generating compliance evaluation data based on the results of the compliance verification calculations includes: Establish a compliance verification rule base that includes constraints from higher-level planning, technical specifications, and policy and regulatory requirements; The preliminary planning scheme is compared and spatially overlaid with the clauses in the compliance verification rule base item by item; Record the conforming, non-conforming, and borderline conforming items found in the comparison and overlay analysis, and quantitatively assess the degree of deviation of the non-conforming items to generate compliance evaluation data that includes a conformity list, a problem list, and deviation assessment values.

5. The intelligent analysis method for land spatial planning data based on big data as described in claim 4, characterized in that, Based on the compliance evaluation data, the planning elements of the preliminary planning scheme are adjusted to form the adjusted planning scheme, which includes: Based on the issue list in the compliance evaluation data, identify the planning elements in the preliminary planning scheme that need to be adjusted; For each issue, the direction and allowable adjustment range of the elements are generated according to the corresponding compliance verification rules; Within the allowable adjustment range, the planning elements that need to be adjusted may undergo boundary correction, nature change, or indicator optimization. After adjusting all issues, verify the conformity of the adjusted planning scheme with the compliance verification rule base to form the adjusted planning scheme.

6. The intelligent analysis method for land spatial planning data based on big data as described in claim 5, characterized in that, Spatial efficiency simulation calculations are performed on the adjusted planning scheme to generate simulation result data. Based on the simulation result data, the adjusted planning scheme is optimized, and the final land spatial planning scheme is output, including: Establish a spatial performance evaluation target system that includes economic, social, and environmental benefits; Using spatial simulation technology, the spatial development process of the adjusted planning scheme within the preset planning period is deduced; Quantitatively calculate the benefit values ​​of the spatial development process under the spatial performance evaluation target system, and generate extrapolation result data including economic benefit value, social benefit value and environmental benefit value; The balance of various benefit values ​​in the simulation results data is analyzed, and the key parameters in the adjusted planning scheme are iteratively optimized until the preset comprehensive performance requirements are met, and the final land space planning scheme is output.

7. The intelligent analysis method for land spatial planning data based on big data as described in claim 6, characterized in that, Performing spatial benchmark unification on the aforementioned multi-source land spatial basic data includes: Identify the coordinate system and projection method used by each of the multi-source land spatial data; Transform all data to a preset unified spatial reference coordinate system; Verify the spatial location accuracy of the converted data.

8. The intelligent analysis method for land spatial planning data based on big data as described in claim 7, characterized in that, The correlation analysis function calculates the spatial coupling strength between elements, including: Calculate the proximity of different key spatial elements in their spatial distribution; Analyze the correlation between the changes in quantity and structure of different key spatial elements; Combining the proximity and the correlation, the spatial coupling strength value, representing the degree of interdependence and influence between elements, is calculated using the coupling strength model.

Images