High-value industrial land identification method and system based on land economic value

Abstract

The invention discloses a high-value industrial land identification method and system based on land economic value, the high-value industrial land identification method comprises the following steps: obtaining map data and industrial land data of a research area, the map data comprising a plurality of industrial map spots; performing data assignment on the plurality of industrial map spots by using the industrial land data to obtain a plurality of target analysis units; obtaining a high-value industrial land identification index system, wherein the high-value industrial land identification index system comprises a plurality of identification indexes and weight values of the identification indexes; calculating a comprehensive score of each target analysis unit based on the index data of each target analysis unit and the weight value of each identification index; the industrial data of the target analysis unit is index data; and determining a high-value industrial land identification result of the target analysis unit based on the comprehensive score of the target analysis unit.

Description

Technical Field

[0001] The present invention relates to a data processing method, and in particular to a method and system for identifying high-value industrial land based on the economic value of the land. Background Art

[0002] With the rapid development of my country's economy and the acceleration of urbanization, industrial land, as an important material basis for urban development, has a great significance for promoting regional economic development and improving the efficiency of land resource utilization. However, the problem of extensive use of industrial land has seriously restricted the healthy development of cities for a long time.

[0003] To this end, it is of great significance to identify high-value industrial land and identify industrial land with high economic value and development potential to promote intensive use of industrial space. Summary of the invention

[0004] In order to overcome the above technical defects, the present invention provides a method and system for identifying high-value industrial land based on the economic value of the land.

[0005] In order to solve the above problems, the present invention is implemented according to the following technical solutions:

[0006] In a first aspect, the present invention provides a method for identifying high-value industrial land based on the economic value of the land, comprising the following steps:

[0007] Acquire map data and industrial land data of a study area, wherein the map data includes a plurality of industrial land spots;

[0008] Use industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units;

[0009] Obtaining a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes;

[0010] Based on the index data of each target analysis unit and the weight value of each identification index, the comprehensive score of each target analysis unit is calculated; the industrial land data of the target analysis unit is the index data;

[0011] Based on the comprehensive score of the target analysis unit, the high-value industrial land identification result of the target analysis unit is determined.

[0012] In combination with the first aspect, the present invention further provides a first specific implementation of the first aspect, specifically, the high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to a plurality of index layers;

[0013] The target layer includes a land use intensity index system and an economic benefit index system;

[0014] The indicator layers of the land use intensity indicator system include benchmark land price, rental unit price, volume ratio, building density, building coefficient, construction completion and land operation entity;

[0015] The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

[0016] In combination with the first aspect, the present invention further provides a second specific implementation of the first aspect, specifically, based on the indicator data of each target analysis unit and the weight value of each identification indicator, calculating the comprehensive score of each target analysis unit, specifically including:

[0017] Standardizing the indicator data to obtain the indicator value of each indicator layer;

[0018] Based on the indicator value and weight value of the indicator layer, calculate the target layer score of each target analysis unit;

[0019] The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer;

[0020] Calculate the composite score of each target analysis unit;

[0021] The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

[0022] In combination with the first aspect, the present invention further provides a third specific implementation of the first aspect, specifically, using industrial land data to assign data to multiple industrial map spots to obtain multiple target analysis units, specifically including:

[0023] Process the industrial land data in a unified coordinate system to generate surface data;

[0024] Using the surface data, the surface attribute data is assigned to the industrial map patches to obtain the target analysis unit and its index data.

[0025] In combination with the first aspect, the present invention further provides a fourth specific implementation of the first aspect. Specifically, the unified coordinate system processing is: using ArcGIS's Spatial Adjustment to perform parameterized adjustment to map coordinates of map data.

[0026] In combination with the first aspect, the present invention also provides a fifth specific implementation scheme of the first aspect. Specifically, the high-value industrial land identification results include first-level high-value industrial land, second-level high-value industrial land, third-level high value, first-level inefficiency industrial land, second-level inefficiency industrial land and third-level inefficiency industrial land.

[0027] In a second aspect, the present invention further provides a high-value industrial land identification system based on the economic value of the land, comprising:

[0028] A first acquisition module, which is used to acquire map data and industrial land data of a research area, wherein the map data includes a plurality of industrial land spots;

[0029] A matching module, which is used to use the industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units;

[0030] A second acquisition module is used to acquire a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes;

[0031] A calculation module, which is used to calculate the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator; the industrial land data of the target analysis unit is the indicator data;

[0032] An identification module is used to determine the high-value industrial land identification result of the target analysis unit based on the comprehensive score of the target analysis unit.

[0033] In combination with the second aspect, the present invention further provides a first specific implementation of the second aspect, specifically, the high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to a plurality of index layers;

[0034] The target layer includes a land use intensity index system and an economic benefit index system;

[0035] The indicator layers of the land use intensity indicator system include benchmark land price, rental unit price, volume ratio, building density, building coefficient, construction completion and land operation entity;

[0036] The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

[0037] In combination with the second aspect, the present invention further provides a second specific implementation of the second aspect, specifically, the calculation module calculates the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator, specifically including:

[0038] Standardizing the indicator data to obtain the indicator value of each indicator layer;

[0039] Based on the indicator value and weight value of the indicator layer, calculate the target layer score of each target analysis unit;

[0040] The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer;

[0041] Calculate the composite score of each target analysis unit;

[0042] The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

[0043] In combination with the second aspect, the present invention further provides a third specific implementation of the second aspect, specifically, the matching module uses industrial land data to assign data to multiple industrial map spots to obtain multiple target analysis units, specifically including:

[0044] Process the industrial land data in a unified coordinate system to generate surface data;

[0045] Using the surface data, the surface attribute data is assigned to the industrial map patches to obtain the target analysis unit and its index data.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention provides a method for identifying high-value industrial land based on the economic value of land, comprising the following steps: obtaining map data and industrial land data of a study area, wherein the map data includes a plurality of industrial map patches; using the industrial land data to assign data to the plurality of industrial map patches to obtain a plurality of target analysis units; obtaining a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes; based on the index data of each target analysis unit and the weight values ​​of each identification index, calculating the comprehensive score of each target analysis unit; the industrial land data of the target analysis unit is the index data; and based on the comprehensive score of the target analysis unit, determining the high-value industrial land identification result of the target analysis unit.

[0048] The present invention provides a new scientific identification tool. The high-value industrial land identification method uses industrial land data to assign data to multiple industrial land spots, calculates the comprehensive score of each target analysis unit based on the high-value industrial land identification index system, and identifies high-value industrial land. The present invention can systematically identify high-value industrial land, provide a scientific basis for the rational allocation and optimization of land resources, and better plan industrial land. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The specific embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings, wherein:

[0050] Figure 1 It is a flow chart of a method for identifying high-value industrial land based on the economic value of the land of the present invention; DETAILED DESCRIPTION

[0051] The following specifically illustrates the implementation mode of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and cannot be understood as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0052] With the rapid development of my country's economy and the acceleration of urbanization, industrial land, as an important material basis for urban development, has a great significance for promoting regional economic development and improving the efficiency of land resource utilization. However, the problem of extensive use of industrial land has seriously restricted the healthy development of cities for a long time.

[0053] Therefore, it is of great significance to identify high-value industrial land and identify industrial land with high economic value and development potential to promote intensive use of industrial space. Therefore, it is necessary to provide a high-value industrial land identification technology.

[0054] For this purpose, refer to Figure 1 The embodiment of the present invention provides a flow chart of a method for identifying high-value industrial land based on the economic value of the land. The present invention can systematically identify high-value industrial land, provide a scientific basis for the rational allocation and optimization of land resources, and better plan industrial land.

[0055] The present invention provides a method for identifying high-value industrial land based on the economic value of the land. The method can be performed by a system for identifying high-value industrial land based on the economic value of the land. The system can be implemented in the form of hardware and / or software, and the system can be configured in a computer. Figure 1 As shown, the method includes:

[0056] S100: Acquire map data and industrial land data of a study area, wherein the map data includes a plurality of industrial land spots.

[0057] S200: Use industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units.

[0058] S300: Acquire a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes.

[0059] S400: Calculate the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator; the industrial land data of the target analysis unit is the indicator data.

[0060] S500: Based on the comprehensive score of the target analysis unit, determine the high-value industrial land identification result of the target analysis unit.

[0061] The present invention provides a new scientific identification tool. The high-value industrial land identification method uses industrial land data to assign data to multiple industrial map patches, calculates the comprehensive score of each target analysis unit based on the high-value industrial land identification index system, and identifies high-value industrial land. Specifically, this embodiment provides a detailed description of each step.

[0062] S100: Acquire map data and industrial land data of a study area, wherein the map data includes a plurality of industrial land spots.

[0063] In the present invention, obtaining map data and industrial land data of the study area is the basis for identifying high-value industrial land. These data provide detailed information such as spatial location, land attributes, and enterprise data.

[0064] In specific implementation, data sources can be obtained through channels such as government planning departments, land management departments, and geographic information system (GIS) databases to obtain map data and industrial land data in the study area. In terms of data integration, GIS software is used to integrate map data and industrial land data to ensure data consistency and accuracy. If necessary, data can be cleaned, formatted, and standardized for subsequent analysis.

[0065] Specifically, the details of the industrial land data are described below. The industrial land data of the present invention is used as indicator data of the target analysis unit.

[0066] In a specific implementation, the present invention also provides a method for obtaining industrial map patches. Specifically, the map data is obtained by the following method:

[0067] S110: Acquire remote sensing image data and POI data of the study area.

[0068] In the present invention, the remote sensing data is Landsat8 images, which can be obtained through the geospatial data cloud website, covering the entire study area. The Landsat8 satellite's land imager (Operational Land Image, OLI) includes a total of nine bands, including eight multispectral bands with a resolution of 30 meters and one panchromatic band with a resolution of 15 meters.

[0069] In specific implementation, POI data mainly refers to geographic information points that are closely related to life, including shopping services, accommodation services, science and humanities, scenic spots, public transportation service facilities, etc., and each main type also includes multiple subcategories.

[0070] The POI data of the present invention specifically refers to POI data whose land use type is industrial land. Industrial land belongs to a type of land use, and its main category is industrial development zone, and its subcategories are industrial zone, development zone, science and technology park, characteristic area, etc. Preferably, POI data needs to be preprocessed, including POI data cleaning and POI data reclassification. The POI data cleaning includes removing duplicate data, eliminating data with missing information (removing duplicate and erroneous data), and coordinate conversion (ensuring consistency with remote sensing image data). The PO data reclassification is to filter out the POI data classified as industrial land and output it for use.

[0071] S120: Calculate land use identification features based on remote sensing image data.

[0072] In the specific implementation, the seven bands of the remote sensing image data of the study area obtained by preprocessing are exported in turn based on ENVI5.3 software. Each band has a certain pixel value in its grid with a resolution of 30m. The exported 7-band TIFF files are visualized in ArcGIS software, and the 7-band TIFF files are converted into shp files through the raster to surface tool to obtain 30m*30m grid pixel values ​​of different bands. Through the spatial connection method, multiple 30m*30m grid pixel values ​​are used as 100m*100m grid land use identification features based on remote sensing image data, and 100m*100m grid is a research unit.

[0073] S130: Calculate land use identification features based on POI data.

[0074] The preprocessed POI data is connected to the 100m*100m grid space to obtain the POI data of each research unit. For each research unit, the POI relative density feature is constructed, and the calculation formula is:

[0075]

[0076]

[0077] In the formula, i represents the type of POI; n ij represents the number of POIs of the i-th type in unit j; Ni represents the total number of POIs of the i-th type; f ij represents the frequency density of the number of POIs of the i-th type in the research unit j and the total number of POIs of all types in the unit j; F i represents the frequency density of the total amount of POIs of the i-th type and the total amount of POIs of all types; C ij It represents the percentage of the frequency density of the i-th type of POI in the research unit j to the frequency density of the i-th type of POI within the research scope, that is, the relative density of POI.

[0078] S140: Based on the land use identification features of remote sensing image data and the land use identification features based on POI data, the GBDT model is used to identify and classify urban land use functions and output map data.

[0079] In the present invention, GBDT (Gradient Boosting Decision Trees) is an ensemble learning algorithm that makes predictions by building multiple decision trees, and each new tree attempts to correct the errors of the previous tree. GBDT performs well in both classification and regression problems, especially when dealing with nonlinear data and feature interactions.

[0080] (1) Feature Engineering: Features are extracted from remote sensing image data and POI data to form a feature matrix. Preferably, the features are normalized to eliminate the dimensional effects between different features.

[0081] In one example, for each learning example, band pixel values ​​are extracted from remote sensing image data, which reflect the spectral characteristics of different objects. The statistical features of each band, such as mean, median, standard deviation, etc., are calculated as part of the feature vector. The remote sensing image band pixel values ​​and POI relative density values ​​are combined into a feature matrix, where each row represents a sample and each column represents a feature.

[0082] (2) Preparation of training data set: The feature matrix and land use function type labels are combined to form a training data set.

[0083] In specific implementations, land use function type labels include industrial land, commercial areas, residential areas, water sources, forest land, etc.

[0084] Specifically, 30% of the grids are randomly selected as learning samples, and the land use data of the learning samples are used as machine learning labels for supervised classification learning. During the training process, the machine classification model is established by mining the relationship between the pixel values ​​of the remote sensing image bands of each lot, the relative density values ​​of the business POI types, and the land use properties within the land.

[0085] (3) Model parameter tuning: Adjust the parameters of the GBDT model, such as learning rate, number of trees, tree depth, etc., to optimize model performance.

[0086] In the specific implementation, the basic parameters of the GBDT model are determined, such as the learning rate (e.g., 0.1), the number of trees (e.g., 100), and the depth of the tree (e.g., 6). The grid search method is used to systematically traverse multiple parameter combinations to find the optimal parameter settings. K-fold cross validation (e.g., 5-fold) is applied to evaluate the performance of different parameter combinations.

[0087] (4) Land use function identification and classification: Apply the trained GBDT model to the feature matrix of the entire study area to classify land use functions. Output the classification results and generate map data of the study area.

[0088] The trained GBDT model is applied to the feature matrix of the entire study area to classify land use functions. The classification results are output and the classification results representing industrial land are integrated with the spatial location information to generate map data of the study area.

[0089] 200: Use industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units.

[0090] In this step, the image spots are converted into target analysis units containing economic value information through data assignment, providing a basis for subsequent comprehensive score calculation. In a specific implementation, step S300 assigns industrial land data to several target analysis units, specifically including the following steps:

[0091] S210: Process the industrial land data in a unified coordinate system to generate surface data.

[0092] In a specific implementation, the unified coordinate system processing is specifically: using ArcGIS's SpatialAdajustment to perform parameterized adjustment to the map coordinates of the map data, with an accuracy that meets research needs.

[0093] The ArcGIS Spatial Adjustment tool allows parameter adjustment of industrial land data to ensure that all data is converted to the map coordinate system of the map data. This step ensures that the accuracy of the data meets the research needs, thereby providing an accurate spatial reference for subsequent analysis. In ArcGIS, the "Define Projection" tool can be used to define the coordinate system of the data to ensure that all data is in the same coordinate system for accurate spatial analysis.

[0094] S220: Using the surface data, assigning surface attribute data to the target analysis unit to obtain unit data of the target analysis unit.

[0095] In the specific implementation, the identify tool is used to superimpose the surface data into the target analysis unit to realize the surface attribute data assignment. The industrial land data includes a lot of data content, which needs to be converted into surface data, and then associated with the target analysis unit to become the indicator data of the target analysis unit.

[0096] In ArcGIS, the “Identify” tool can be used to overlay the polygonal data onto the target analysis unit. This tool can help identify the attributes in the polygonal data and assign them to the target analysis unit to achieve the assignment of polygonal attribute data. The various data contained in the industrial land data needs to be converted into polygonal data and associated with the target analysis unit so that the comprehensive score can be calculated in the subsequent steps. This can be achieved through the “Join” or “Spatial Join” tools in ArcGIS to combine the attribute data with the spatial location information.

[0097] S300: Acquire a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes.

[0098] In a specific implementation, the high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to several index layers;

[0099] The target layer includes a land use intensity index system and an economic benefit index system;

[0100] The indicator layers of the land use intensity indicator system include benchmark land price, rental unit price, volume ratio, building density, building coefficient, construction completion and land operation entity;

[0101] The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

[0102] In another preferred implementation, the target layer also includes a road traffic indicator system and an industrial development indicator system.

[0103] The road traffic indicator system includes:

[0104] In the specific implementation, the weight value of the identification index can be obtained by the analytic hierarchy process. The analytic hierarchy process (AHP) is a commonly used decision analysis method, which determines the weight value of the identification index by constructing a judgment matrix and combining expert scoring. This method is suitable for solving complex decision-making problems with multiple objectives and multiple criteria, and can convert the subjective judgment of the decision maker into a numerical value that can be quantified.

[0105] In a specific implementation, the identification indicator needs to calculate the CR value and pass the test to meet the analysis requirements, as follows:

[0106] in, When CI is less than 0.1, the judgment matrix can accept consistency, otherwise it needs to be modified. When n ≥ 3, in order to eliminate the influence of CI on the order, it is necessary to introduce the average random consistency index RI of the judgment matrix, taking CR = CI / RI, and perform consistency test on the constructed judgment matrix.

[0107] It is generally believed that when CR < 0.1, the judgment matrix passes the consistency test, otherwise it does not have satisfactory consistency. Using the weighted combination of hierarchical single sorting, the weight of the previous layer is calculated to obtain the weight value of each single indicator in the evaluation system.

[0108] In calculating the weight values ​​of the identification indicators, the AHP method is implemented through the following steps:

[0109] 1. Establish a hierarchical model: decompose the decision-making problem into the target layer and the indicator layer to form a hierarchical structure model.

[0110] 2. Construct a pairwise comparison matrix: Compare the factors of the target layer in pairs, construct a pairwise comparison matrix, and fill in the matrix elements. In this process, a 1-9 scale is usually used to quantify the relative importance of the factors.

[0111] 3. Calculate the weight vector and perform consistency check: Calculate the maximum eigenvalue and the corresponding eigenvector of the pairwise comparison matrix and perform consistency check. If the consistency ratio CR is less than 0.1, the consistency of the matrix is ​​considered acceptable, otherwise the judgment matrix needs to be readjusted.

[0112] 4. Hierarchical total sorting and consistency check: Calculate the combined weight vector of the lowest layer for the target and perform a combined consistency check. If the check is passed, a decision can be made based on it.

[0113] 5. Result analysis: Based on the calculated weight values, sort and analyze each identification indicator to determine their relative importance.

[0114] The advantage of the AHP method is that it can combine the subjective judgment of decision makers with objective data, and is suitable for decision-making problems with incomplete or difficult to quantify data information. In addition, the calculation process of the AHP method is relatively simple, easy to understand and operate, allowing decision makers to quickly analyze and make decisions on complex problems.

[0115] In the specific implementation, the identification indicators, weight values, and data sources of the high-value industrial land identification indicator system are as follows:

[0116] Table 1 High-value industrial land identification index system

[0117]

[0118]

[0119]

[0120] In specific implementation, the higher the benchmark land price, the more costs need to be paid, the lower the willingness of enterprises to participate in investment, which is not conducive to the development of industrial land. The benchmark land price is calculated by the following formula:

[0121]

[0122] In the formula, S represents the benchmark land price of the current target analysis unit, Si represents the benchmark land price of a certain plot of land in the target analysis unit, Mi represents the area of ​​the plot of land, M represents the area of ​​the current target analysis unit, and n represents the number of plots in the current target analysis unit.

[0123] In specific implementation, the building coefficient reflects the project's use of land in plane, and can measure the intensity and rationality of land use. Building coefficient = (building area + structure area + open-air storage area) ÷ project area × 100%.

[0124] In the specific implementation, land operators are divided into four categories: idle, fully leased, partially leased, and continuously operating through Baidu Street View database and field surveys, based on the business conditions of the enterprises and the stability of land use, and are assigned standardized values ​​of 0, 4, 6, and 10 respectively.

[0125] In specific implementation, data sources can be obtained through government planning departments, land management departments, geographic information system (GIS) databases, field surveys and other channels to obtain map data and industrial land data of the study area.

[0126] S400: Calculate the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator; the industrial land data of the target analysis unit is the indicator data.

[0127] In a specific implementation, based on the indicator data of each target analysis unit and the weight value of each identification indicator, the comprehensive score of each target analysis unit is calculated and obtained in the following manner:

[0128] S410: performing standardization processing on the indicator data to obtain an indicator value of each indicator layer;

[0129] In a specific implementation, the standardization method includes minimum-maximum standardization, Z-score standardization, etc. In the present invention, the minimum-maximum standardization is used to convert the indicator data into a value between 0 and 1, and the formula is:

[0130] Among them, x is the indicator data of the evaluation indicator, xmin is the minimum value of the evaluation indicator, and xmax is the maximum value of the evaluation indicator.

[0131] S420: Calculating the target layer score of each target analysis unit based on the indicator value and weight value of the indicator layer;

[0132] The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer;

[0133] S430: Calculate the comprehensive score of each target analysis unit;

[0134] The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

[0135] S500: Based on the comprehensive score of the target analysis unit, determine the high-value industrial land identification result of the target analysis unit.

[0136] In a specific implementation, the high-value industrial land identification results include first-level high-value industrial land, second-level high-value industrial land, third-level high value, first-level inefficient industrial land, second-level inefficient industrial land and third-level inefficient industrial land.

[0137] In one example, the correspondence between the comprehensive score and the high-value industrial land identification result is as follows:

[0138]

[0139]

[0140] The present invention also provides a high-value industrial land identification system based on the economic value of the land, which is used to execute the above-mentioned high-value industrial land identification method. The high-value industrial land identification system includes:

[0141] A first acquisition module, which is used to acquire map data and industrial land data of a research area, wherein the map data includes a plurality of industrial land spots;

[0142] A matching module, which is used to use the industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units;

[0143] A second acquisition module is used to acquire a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes;

[0144] A calculation module, which is used to calculate the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator; the industrial land data of the target analysis unit is the indicator data;

[0145] An identification module is used to determine the high-value industrial land identification result of the target analysis unit based on the comprehensive score of the target analysis unit.

[0146] Preferably, the high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to several index layers;

[0147] The target layer includes a land use intensity index system and an economic benefit index system;

[0148] The indicator layers of the land use intensity indicator system include benchmark land price, volume ratio, building density, building coefficient, construction completion and land use subject;

[0149] The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

[0150] Preferably, the calculation module calculates the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator, specifically including:

[0151] Standardizing the indicator data to obtain the indicator value of each indicator layer;

[0152] Based on the indicator value and weight value of the indicator layer, calculate the target layer score of each target analysis unit;

[0153] The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer;

[0154] Calculate the composite score of each target analysis unit;

[0155] The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

[0156] Specifically, the matching module uses the industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units, specifically including:

[0157] Process the industrial land data in a unified coordinate system to generate surface data;

[0158] Using the surface data, the surface attribute data is assigned to the industrial map patches to obtain the target analysis unit and its index data.

[0159] For other structures of the method and system for identifying high-value industrial land based on the economic value of the land described in this embodiment, refer to the prior art.

[0160] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Therefore, any modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A method for identifying high-value industrial land based on the economic value of the land, characterized in that: The steps include: Acquire map data and industrial land data of a study area, wherein the map data includes a plurality of industrial land spots; Use industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units; Obtaining a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes; Based on the indicator data of each target analysis unit and the weight value of each identification indicator, the comprehensive score of each target analysis unit is calculated; The industrial land data of the target analysis unit is index data; Based on the comprehensive score of the target analysis unit, the high-value industrial land identification result of the target analysis unit is determined.

2. A method for identifying high-value industrial land based on the economic value of land according to claim 1, characterized in that: The high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to several index layers; The target layer includes a land use intensity index system and an economic benefit index system; The indicator layers of the land use intensity indicator system include benchmark land price, rental unit price, volume ratio, building density, building coefficient, construction completion and land operation entity; The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

3. A method for identifying high-value industrial land based on the economic value of land according to claim 2, characterized in that: Based on the indicator data of each target analysis unit and the weight value of each identification indicator, the comprehensive score of each target analysis unit is calculated, including: Standardizing the indicator data to obtain the indicator value of each indicator layer; Based on the indicator value and weight value of the indicator layer, calculate the target layer score of each target analysis unit; The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer; Calculate the composite score of each target analysis unit; The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

4. The method for identifying high-value industrial land based on the economic value of the land according to claim 1, characterized in that: Use industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units, including: Process the industrial land data in a unified coordinate system to generate surface data; Using the surface data, the surface attribute data is assigned to the industrial map patches to obtain the target analysis unit and its index data.

5. A method for identifying high-value industrial land based on the economic value of land according to claim 4, characterized in that: The unified coordinate system processing specifically includes: using ArcGIS Spatial Adjustment to perform parameterized adjustment to map coordinates of map data.

6. A method for identifying high-value industrial land based on the economic value of land according to claim 1, characterized in that: The high-value industrial land identification results include first-level high-value industrial land, second-level high-value industrial land, third-level high value, first-level low-efficiency industrial land, second-level low-efficiency industrial land and third-level low-efficiency industrial land.

7. A high-value industrial land identification system based on the economic value of the land, characterized in that: include: A first acquisition module, which is used to acquire map data and industrial land data of a research area, wherein the map data includes a plurality of industrial land spots; A matching module, which is used to use the industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units; A second acquisition module is used to acquire a high-value industrial land identification index system, wherein the high-value industrial land identification index system includes a plurality of identification indexes and weight values ​​of the identification indexes; A calculation module, which is used to calculate the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator; The industrial land data of the target analysis unit is index data; An identification module is used to determine the high-value industrial land identification result of the target analysis unit based on the comprehensive score of the target analysis unit.

8. A high-value industrial land identification system based on the economic value of land according to claim 7, characterized in that: The high-value industrial land identification index system includes a target layer and an index layer; one target layer corresponds to several index layers; The target layer includes a land use intensity index system and an economic benefit index system; The indicator layers of the land use intensity indicator system include benchmark land price, rental unit price, volume ratio, building density, building coefficient, construction completion and land operation entity; The indicator layers of the economic benefit indicator system include fixed asset investment intensity, per capita output value, per capita tax revenue, per capita employment number, electricity consumption per 10,000 yuan of output value, water consumption per 10,000 yuan of output value and total assets.

9. A high-value industrial land identification system based on the economic value of land according to claim 8, characterized in that: The calculation module calculates the comprehensive score of each target analysis unit based on the indicator data of each target analysis unit and the weight value of each identification indicator, specifically including: Standardizing the indicator data to obtain the indicator value of each indicator layer; Based on the indicator value and weight value of the indicator layer, calculate the target layer score of each target analysis unit; The calculation formula of the target layer score is: In the formula, S i is the i-th target layer score of the target analysis unit; P ij is the index value of the jth index layer of the i-th target layer of the target analysis unit; W j is the weight value of the jth indicator layer, and n represents the total number of indicators in the indicator layer; Calculate the composite score of each target analysis unit; The formula for calculating the comprehensive score is: In the formula, S is the comprehensive score of the target analysis unit; S i is the target layer score of the i-th target layer in the target analysis unit; W i is the weight value of the i-th target layer, and n represents the total number of indicators of the target layer.

10. A high-value industrial land identification system based on the economic value of land according to claim 7, characterized in that: The matching module uses the industrial land data to assign data to multiple industrial land spots to obtain multiple target analysis units, specifically including: Process the industrial land data in a unified coordinate system to generate surface data; Using the surface data, the surface attribute data is assigned to the industrial map patches to obtain the target analysis unit and its index data.

Images