Industrial land modulus interval calculation method based on space matching

Abstract

The invention relates to an industrial land modulus interval calculation method based on space matching. The method comprises the following steps: acquiring industrial land data; the industrial land data comprises multiple pieces of enterprise data; each piece of enterprise data comprises an ellipsoid floor area and various operation data; according to the ellipsoid occupied area of each enterprise, obtaining screened industrial land data; constructing a multiple linear regression equation according to the screened industrial land data; calculating to obtain an optimal coefficient combination according to a multiple linear regression equation and the screened industrial land data; according to the optimal coefficient combination, the multiple linear regression equation and the screened industrial land data, a modulus interval is obtained through calculation. The method has the characteristics of comprehensive evaluation and high accuracy.

Description

Technical Field

[0001] This invention relates to the field of industrial land technology, and in particular to a method for calculating the modular interval of industrial land based on spatial matching. Background Technology

[0002] With the increasing demand for refined management of industrial land, scientifically formulating industry land use standards has become crucial for improving the efficiency of land resource allocation. Therefore, calculating the industrial land use modulus can use numerical methods to measure multiple practical factors, and then use the numerical comparison results to assist subsequent decision-making.

[0003] In existing technologies, methods for calculating industrial land use moduloes largely rely on macro-statistics or empirical estimations. These methods are mostly based on administrative divisions or sampling surveys, lacking precise spatial correspondence between enterprises and land use, making it difficult to reflect actual land use characteristics and resulting in a weak data foundation. They fail to systematically consider the differences in technological processes and production organization among different industrial sectors, leading to discrepancies between the calculated moduloes and the actual land use needs of each industry, and insufficient consideration of industry characteristics. Traditional methods often employ simple arithmetic averages or empirical coefficients, lacking quantitative analysis of spatial distribution characteristics and multiple influencing factors, resulting in limited accuracy of the modulo standard and a lack of scientific rigor. In summary, existing methods for calculating industrial land use moduloes are rather one-sided and have low accuracy.

[0004] Existing technology discloses a method and system for managing investment promotion in industrial parks. This method includes: obtaining a popularity attraction index based on the browsing time of client companies; determining the attraction influence level based on the popularity attraction index and the number of rental / sale transactions; obtaining a rental / sale difficulty index based on the rental / sale transaction status; determining the rental / sale difficulty based on the attraction influence level, the popularity attraction index, and the rental / sale difficulty index; determining the matching degree between client companies and commercial spaces based on the industry type, company size, and the attributes of the commercial spaces rented / sold; obtaining an introduction promotion index based on the company size and industry type; determining the introduction intensity based on the introduction promotion index, rental / sale difficulty, and matching degree; and adjusting the preferential strategies for each client company that did not successfully rent / sell. This method primarily focuses on numerical calculations for industrial park investment promotion and does not address industrial land use. Summary of the Invention

[0005] This invention addresses the shortcomings of existing methods for calculating the modular interval of industrial land use, which are often one-sided and have low accuracy. It provides a spatial matching-based method for calculating the modular interval of industrial land use. This method features comprehensive evaluation and high accuracy.

[0006] A method for calculating the modular interval of industrial land use based on spatial matching, comprising: S1: Obtain industrial land data; the industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data; S2: Based on the ellipsoidal area of ​​each enterprise, obtain the filtered industrial land data; S3: Construct a multiple linear regression equation based on the screened industrial land data; S4: Based on the multiple linear regression equation and the screened industrial land data, the optimal coefficient combination is calculated; S5: Based on the optimal coefficient combination, the multiple linear regression equation, and the screened industrial land data, the modulus interval is calculated.

[0007] Further, in step S2, the filtered industrial land data is obtained, including: S201: Calculate the upper and lower quantiles based on the ellipsoidal area of ​​all enterprises; S202: Calculate the interquartile range based on the upper quantile and the lower quantile; S203: The upper boundary and the lower boundary are calculated based on the upper quantile, the lower quantile, and the interquartile range; S204: Based on the upper boundary and the lower boundary, the ellipsoidal land area of ​​all enterprises is filtered to obtain the filtered industrial land data.

[0008] Further, in step S4, the optimal combination of coefficients is calculated, including: S401: Based on the multiple linear regression equation and the screened industrial land data, calculate the regression coefficients of multiple linear regression equations, and use them as the first set of regression coefficients. S402: Select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the first coefficient combination; S403: Determine whether the first coefficient combination meets the first preset condition; if it meets the first preset condition, proceed to step S405; if it does not meet the first preset condition, proceed to step S404. S404: Remove the first coefficient combination from the first regression coefficient group; select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the new first coefficient combination; execute step S403; S405: Use the first coefficient combination as the optimal coefficient combination.

[0009] Furthermore, the formula for calculating the regression coefficient set is as follows:

[0010] This represents the regression coefficient matrix of industry g. This represents the operating data matrix for industry g. Represents the ellipsoidal area matrix of industry g; , Represents the regression coefficient of industry g's operating data n; , This represents the nth operating data point of company i in industry g; , This represents the ellipsoidal area occupied by company i in industry g.

[0011] Furthermore, the formula for the sum of squared residuals is as follows:

[0012] This represents the sum of squared residuals for industry g. This represents the predicted ellipsoidal area of ​​company i in industry g. This represents the ellipsoidal area occupied by company i in industry g.

[0013] Furthermore, the multiple linear regression equation is as follows:

[0014] This represents the predicted ellipsoidal area occupied by company i in industry g, where i represents the company number and g represents the industry number. This represents the regression constant term of industry g. This represents the regression coefficient of industry g's operating data n, where n represents the data index. This represents the random error of company i in industry g. This represents the nth operating data point of company i in industry g.

[0015] Further, in step S5, the modulus interval is calculated, including:

[0016]

[0017] This represents the lower boundary of the modulus interval for industry g and enterprise i. This represents the upper boundary of the modulus interval for industry g and enterprise i. Describing the degrees of freedom as The 0.05 quantile of the t-distribution, Indicates the regression standard error. This represents the operating data matrix for industry g. A vector representing the operational data of company i in industry g; .

[0018] A method for calculating industrial land use data, comprising: S01: Obtain multiple enterprise latitude and longitude data groups and corresponding enterprise verification data; S02: Project the latitude and longitude data of the multiple enterprises onto an ellipsoid using the Gauss-Kruger projection method to obtain the projected ellipsoid for each enterprise. S03: Calculate the area of ​​the projected ellipsoid corresponding to each enterprise to obtain the area occupied by the first ellipsoid corresponding to each enterprise; S04: Divide the area of ​​the first ellipsoid corresponding to each enterprise into overlapping sections to obtain the area of ​​the second ellipsoid corresponding to each enterprise. S05: Based on the area of ​​the first ellipsoid corresponding to each enterprise and the verification data corresponding to each enterprise, spatial association filtering is performed to obtain the enterprise group after spatial association filtering; S06: Obtain the various business data corresponding to each enterprise in the enterprise group filtered by spatial association; take the second ellipsoidal land area corresponding to each enterprise in the enterprise group filtered by spatial association and the various business data corresponding to each enterprise in the enterprise group filtered by spatial association as industrial land data.

[0019] A project site selection method, comprising: S001: Obtain the ellipsoidal area of ​​multiple candidate plots; S002: Based on the ellipsoidal area of ​​each candidate plot and the modulus range, multiple candidate plots are selected after screening. S003: Select multiple candidate sites after screening as the project site selection results.

[0020] A system for calculating the modular interval of industrial land use based on spatial matching, comprising: Data acquisition module: Acquires industrial land data; the industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data; Data filtering module: Based on the ellipsoidal land area of ​​each enterprise, the filtered industrial land data is obtained; Regression equation construction module: Constructs a multiple linear regression equation based on the screened industrial land data; Coefficient calculation module: Calculates the optimal coefficient combination based on the multiple linear regression equation and the screened industrial land data; Modulus Interval Calculation Module: Based on the optimal coefficient combination, multiple linear regression equation, and screened industrial land data, the modulus interval is calculated.

[0021] Compared with the prior art, the beneficial effects of the present invention are: This invention utilizes a multiple linear regression equation to establish a quantifiable and verifiable modulus calculation model, avoiding subjective experience interference and ensuring the objectivity and consistency of the results. The multiple linear regression equation considers multiple operational data simultaneously, fully reflecting the relationship between land use characteristics and enterprise needs, thus resulting in higher accuracy and more comprehensive evaluation of the modulus range. This, in turn, enables project site selection to meet the needs of enterprises in specific industries.

[0022] This invention also links enterprise latitude and longitude data with enterprise verification data through an industrial land data calculation method, and uses the ellipsoidal land area for area calculation, which reduces data errors and makes the accuracy of the modulus interval calculation higher. Attached Figure Description

[0023] Figure 1 The flowchart shows a method for calculating the modular interval of industrial land use based on spatial matching, as provided in Example 1.

[0024] Figure 2 The flowchart for obtaining the filtered industrial land data provided in Example 1.

[0025] Figure 3 The flowchart for calculating the optimal coefficient combination provided in Example 1.

[0026] Figure 4 This is a flowchart of an industrial land use data calculation method provided in Example 2.

[0027] Figure 5 This is a schematic diagram of overlapping and dividing the area of ​​the ellipsoid provided in Example 2.

[0028] Figure 6 This is a schematic diagram illustrating the matching of the enterprise's spatial location with the ellipsoidal area provided in Example 2.

[0029] Figure 7 This is a schematic diagram of removing data where the matching point is located on the boundary in the matching process, as provided in Example 2.

[0030] Figure 8 This is a flowchart of a project site selection method provided in Example 3. Detailed Implementation

[0031] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent. To better illustrate this embodiment, some parts in the accompanying drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions; It will be understood by those skilled in the art that certain well-known structures and their descriptions may be omitted in the accompanying drawings.

[0032] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0033] Example 1 like Figure 1 As shown, a method for calculating the modular interval of industrial land use based on spatial matching includes: S1: Obtain industrial land data; the industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data; S2: Based on the ellipsoidal area of ​​each enterprise, obtain the filtered industrial land data; S3: Construct a multiple linear regression equation based on the screened industrial land data; S4: Based on the multiple linear regression equation and the screened industrial land data, the optimal coefficient combination is calculated; S5: Based on the optimal coefficient combination, the multiple linear regression equation, and the screened industrial land data, the modulus interval is calculated.

[0034] In one specific embodiment, operating data includes enterprise revenue, taxes, number of employees, and production capacity.

[0035] It should be noted that using an ellipsoidal area allows the area calculation of this scheme to closely match the curvature of the Earth, thereby reducing errors.

[0036] It should be noted that steps S1 to S5 only calculate the modulus range for data from the same industry. However, steps S1 to S5 can be repeated to process data from different industries, thereby obtaining modulus ranges for multiple industries.

[0037] Furthermore, such as Figure 2 As shown, in step S2, the filtered industrial land data is obtained, including: S201: Calculate the upper and lower quantiles based on the ellipsoidal area of ​​all enterprises; S202: Calculate the interquartile range based on the upper quantile and the lower quantile; S203: The upper boundary and the lower boundary are calculated based on the upper quantile, the lower quantile, and the interquartile range; S204: Based on the upper boundary and the lower boundary, the ellipsoidal land area of ​​all enterprises is filtered to obtain the filtered industrial land data.

[0038] It should be noted that the IQR quartile method in step S2 can be used to remove area outliers.

[0039]

[0040]

[0041] Ellipsoids with a floor area greater than the upper boundary or less than the lower boundary will be excluded.

[0042] The ellipsoidal area can be sorted in ascending order, and the upper quantile can be obtained using the following formula. lower quantile Interquartile Range (IQR). n represents the total number of firms.

[0043]

[0044]

[0045]

[0046] Furthermore, such as Figure 3 As shown, in step S4, the optimal coefficient combination is calculated, including: S401: Based on the multiple linear regression equation and the screened industrial land data, calculate the regression coefficients of multiple linear regression equations, and use them as the first set of regression coefficients. S402: Select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the first coefficient combination; S403: Determine whether the first coefficient combination meets the first preset condition; if it meets the first preset condition, proceed to step S405; if it does not meet the first preset condition, proceed to step S404. S404: Remove the first coefficient combination from the first regression coefficient group; select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the new first coefficient combination; execute step S403; S405: Use the first coefficient combination as the optimal coefficient combination.

[0047] In one specific embodiment, the first preset condition is as follows:

[0048]

[0049]

[0050] Used to determine whether the estimated regression coefficients are significant. The results indicate that they are statistically significant and in line with expectations. For the industry g No. j Estimates of the regression coefficients, for The standard error, For the industry g Dependent variable mean n g For the industry g Sample size The adjusted coefficient of determination, if A value greater than 0.7 indicates that the model fits well and can explain most of the variation in the dependent variable. If the above... and If two parameters do not meet expectations, insignificant independent variables need to be investigated and eliminated. The abnormal values ​​present in the model are then used to iteratively calculate and refit the equation to generate new regression coefficient estimates before performing model statistics calculations.

[0051] Furthermore, the formula for calculating the regression coefficient set is as follows:

[0052] This represents the regression coefficient matrix of industry g. This represents the operating data matrix for industry g. Represents the ellipsoidal area matrix of industry g; , Represents the regression coefficient of industry g's operating data n; , This represents the nth operating data point of company i in industry g; , This represents the ellipsoidal area occupied by company i in industry g.

[0053] Furthermore, the formula for the sum of squared residuals is as follows:

[0054] This represents the sum of squared residuals for industry g. This represents the predicted ellipsoidal area of ​​company i in industry g. This represents the ellipsoidal area occupied by company i in industry g.

[0055] Furthermore, the multiple linear regression equation is as follows:

[0056] This represents the predicted ellipsoidal area occupied by company i in industry g, where i represents the company number and g represents the industry number. This represents the regression constant term of industry g. This represents the regression coefficient of industry g's operating data n, where n represents the data index. This represents the random error of company i in industry g. This represents the nth operating data point of company i in industry g.

[0057] Further, in step S5, the modulus interval is calculated, including:

[0058]

[0059] This represents the lower boundary of the modulus interval for industry g and enterprise i. This represents the upper boundary of the modulus interval for industry g and enterprise i. Describing the degrees of freedom as The 0.05 quantile of the t-distribution, Indicates the regression standard error. This represents the operating data matrix for industry g. A vector representing the operational data of company i in industry g; .

[0060] A system for calculating the modular interval of industrial land use based on spatial matching, comprising: Data acquisition module: Acquires industrial land data; the industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data; Data filtering module: Based on the ellipsoidal land area of ​​each enterprise, the filtered industrial land data is obtained; Regression equation construction module: Constructs a multiple linear regression equation based on the screened industrial land data; Coefficient calculation module: Calculates the optimal coefficient combination based on the multiple linear regression equation and the screened industrial land data; Modulus Interval Calculation Module: Based on the optimal coefficient combination, multiple linear regression equation, and screened industrial land data, the modulus interval is calculated.

[0061] Example 2: Based on the spatial matching-based industrial land modular interval calculation method described in Example 1, this example uses the same spatial matching-based industrial land modular interval calculation method as Example 1.

[0062] like Figure 4 As shown, a method for calculating industrial land use data includes: S01: Obtain multiple enterprise latitude and longitude data groups and corresponding enterprise verification data; S02: Project the latitude and longitude data of the multiple enterprises onto an ellipsoid using the Gauss-Kruger projection method to obtain the projected ellipsoid for each enterprise. S03: Calculate the area of ​​the projected ellipsoid corresponding to each enterprise to obtain the area occupied by the first ellipsoid corresponding to each enterprise; S04: Divide the area of ​​the first ellipsoid corresponding to each enterprise into overlapping sections to obtain the area of ​​the second ellipsoid corresponding to each enterprise. S05: Based on the area of ​​the first ellipsoid corresponding to each enterprise and the verification data corresponding to each enterprise, spatial association filtering is performed to obtain the enterprise group after spatial association filtering; S06: Obtain the various business data corresponding to each enterprise in the enterprise group filtered by spatial association; take the second ellipsoidal land area corresponding to each enterprise in the enterprise group filtered by spatial association and the various business data corresponding to each enterprise in the enterprise group filtered by spatial association as industrial land data.

[0063] In one specific embodiment, the formula for the Gauss-Kruger projection in step S2 is as follows:

[0064] a For the semi-major axis of the ellipsoid, b For the minor semi-axis of the ellipsoid, e It is the eccentricity of the ellipsoid. B Latitude L Longitude dB latitude B a tiny increment, dL Indicates longitude L a tiny increment, S Let be the area of ​​the ellipsoid.

[0065] The latitude and longitude data sets first form a closed polygon, which is then projected onto an ellipsoid using the projection formula described above.

[0066] In one specific embodiment, in step S04, as follows: Figure 5 As shown, if multiple enterprises occupy the same ellipsoidal area at the same time, the ellipsoidal area is divided according to ownership data and road network data, so that one ellipsoidal area corresponds to one enterprise.

[0067] In one specific embodiment, step S5, spatial association filtering mainly consists of two steps: Step a: Match the spatial location of the enterprise in the verification data with the area of ​​the ellipsoid; like Figure 6 As shown, let the enterprise point big data be the target dataset. T={t 1 ,t 2 ...t m } , including attribute set A T ={a T1 , aT2 ...a Tm } Each target element t i Corresponding spatial geometric objects G(t i ) Let the industrial land data be the join dataset. J={j 1 , j 2 ...j k } , including attribute set A J ={a J1 ,a J2 ...a Jmp } Each connecting element j l Corresponding spatial geometric objects G(j l ) .

[0068] For each target element t i and connecting elements j l Through spatial predicates R Determine whether the two satisfy a spatial relationship. Spatial relationship R Using intersecting ( Intersects The method, namely G(t) i )∩G(j l )≠Ø, as detailed below:

[0069] Each target element t i Only one is associated with R Connection elements j l The mapping relationship is constructed as follows:

[0070]

[0071] In the formula, φ(t i ,j l ) For the filtering function, output elements o i =( t iAttributes j l (attributes), final output O The binding result of the union of attribute sets and spatial relationships is as follows:

[0072] In the formula, A T (t i ) is t i The original properties, A * J (t i ) It is the connection attribute after association, and the output result after connection is "Enterprise-Industrial Land Preliminary Matching Result".

[0073] Step b: Based on the above matching results, remove data where the matching point is located on the boundary.

[0074] like Figure 7 As shown, based on the preliminary matching results, the geometric overlap check method is used to calculate the distance of the shortest line segment between a certain enterprise point and the corresponding industrial land. D (i.e., the shortest distance), where the coordinates of the enterprise point are ( x 0 ,y 0), the coordinates of the two endpoints of the shortest line segment between the enterprise point and the corresponding industrial land ( x 1 ,y 1) and ( x 2 ,y 2) Based on the spatial relationship between points and line segments, there are two cases: Case 1: If the point lies within the perpendicular shadow of the line segment, then the shortest distance is the perpendicular distance from the point to the line segment.

[0075] Case 2: If the point is outside the perpendicular shadow of the line segment, the shortest distance is the straight-line distance from the point to the nearest endpoint of the line segment. If the perpendicular shadow is close to (…), then the shortest distance is the straight-line distance from the point to the nearest endpoint of the line segment. x 1 ,y 1) and ( x 2 ,y 2), the corresponding distance calculations are as follows:

[0076]

[0077] The shortest distance calculated above D Set tolerance θ dIs 0.05, for differential statistics D ≤0 (the point is within the plane, belonging to normal matching), 0 < D ≤ θ d (near the boundary, conforming to the connection rule), D > tolerance (the point is outside the plane, belonging to abnormal mismatch), count the number of cases in three categories, and then calculate the abnormal mismatch rate:

[0078] In the formula, Is the number of associated pairs with a distance exceeding the spatial connection tolerance; Is the total number of matching associated pairs. If ≤3% is qualified. If >3% is unqualified, and it is necessary to check each abnormal associated pair one by one. After verification, retain the successfully matched records as the enterprise group screened by spatial association.

[0079] Embodiment 3: Based on the method for calculating the industrial land modulus interval based on spatial matching described in Embodiment 1, that is, this embodiment adopts the same method for calculating the industrial land modulus interval based on spatial matching as Embodiment 1.

[0080] Such as Figure 8 Shown, a project site selection method includes: S001: Obtain the ellipsoidal floor area of multiple candidate plots; S002: According to the ellipsoidal floor area of each candidate plot and the modulus interval, screen to obtain multiple screened candidate plots; S003: Use multiple screened candidate plots as the project site selection result.

[0081] For various industries, the present invention analyzes as follows: Sports goods manufacturing: The spatial unit modulus is between 1.3 - 3 hectares, with an average of about 2.08 hectares and a variance of 0.49. The land use modulus is mainly related to the enterprise scale. Under the same scale, the unit modulus gap of different products is small, and the land use scale difference is small.

[0082] The candidate plots are the following four.

[0083] Plot 1: The plot is located in the Tangheng area of Daya Bay, and the plot area is about 10 hectares.

[0084] Plot 2: The plot is located in the Shiwan area of Boluo County, and the plot area is about 5 hectares. Plot 3: The plot is located in the Qiuchang area of Huiyang District, and the plot area is about 2 hectares.

[0085] Plot 4: The plot is located in the Liling area of Zhongkai, and the plot area is about 0.5 hectares.

[0086] After modular comparison, Plot 3 meets the requirements for manufacturing sporting goods.

[0087] The same or similar labels correspond to the same or similar parts; The terms used to describe positional relationships in the accompanying drawings are for illustrative purposes only and should not be construed as limiting this patent. Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for calculating the modular interval of industrial land use based on spatial matching, characterized in that, include: S1: Obtain industrial land data; the industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data; S2: Based on the ellipsoidal area of ​​each enterprise, obtain the filtered industrial land data; S3: Construct a multiple linear regression equation based on the screened industrial land data; S4: Based on the multiple linear regression equation and the screened industrial land data, the optimal coefficient combination is calculated; S5: Based on the optimal coefficient combination, the multiple linear regression equation, and the screened industrial land data, the modulus interval is calculated.

2. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 1, characterized in that, In step S2, the filtered industrial land data is obtained, including: S201: Calculate the upper and lower quantiles based on the ellipsoidal area of ​​all enterprises; S202: Calculate the interquartile range based on the upper quantile and the lower quantile; S203: The upper boundary and the lower boundary are calculated based on the upper quantile, the lower quantile, and the interquartile range; S204: Based on the upper boundary and the lower boundary, the ellipsoidal land area of ​​all enterprises is filtered to obtain the filtered industrial land data.

3. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 1, characterized in that, In step S4, the optimal combination of coefficients is calculated, including: S401: Based on the multiple linear regression equation and the screened industrial land data, calculate the regression coefficients of multiple linear regression equations, and use them as the first set of regression coefficients. S402: Select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the first coefficient combination; S403: Determine whether the first coefficient combination meets the first preset condition; if it meets the first preset condition, proceed to step S405; if it does not meet the first preset condition, proceed to step S404. S404: Remove the first coefficient combination from the first regression coefficient group; select the regression coefficient combination with the smallest sum of squared residuals in the first regression coefficient group as the new first coefficient combination; execute step S403; S405: Use the first coefficient combination as the optimal coefficient combination.

4. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 3, characterized in that, The formula for calculating the regression coefficient group is as follows: This represents the regression coefficient matrix of industry g. This represents the operating data matrix for industry g. Represents the ellipsoidal area matrix of industry g; , Represents the regression coefficient of industry g's operating data n; , This represents the nth operating data point of company i in industry g; , This represents the ellipsoidal area occupied by company i in industry g.

5. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 3, characterized in that, The formula for the sum of squared residuals is as follows: This represents the sum of squared residuals for industry g. This represents the predicted ellipsoidal area of ​​company i in industry g. This represents the ellipsoidal area occupied by company i in industry g. Let i represent the total number of companies in industry g, i represent the company number, and g represent the industry number.

6. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 1 or 5, characterized in that, The multiple linear regression equation is as follows: This represents the predicted ellipsoidal area occupied by company i in industry g, where i represents the company number and g represents the industry number. This represents the regression constant term of industry g. This represents the regression coefficient of industry g's operating data n, where n represents the data index. This represents the random error of company i in industry g. This represents the nth operating data point of company i in industry g.

7. The method for calculating the modular interval of industrial land use based on spatial matching according to claim 6, characterized in that, In step S5, the modulus interval is calculated, including: This represents the lower boundary of the modulus interval for industry g and enterprise i. This represents the upper boundary of the modulus interval for industry g and enterprise i. Describing the degrees of freedom as The 0.05 quantile of the t-distribution, Indicates the regression standard error. This represents the operating data matrix for industry g. A vector representing the operational data of company i in industry g; .

8. A method for calculating industrial land use data, applied to the modular interval calculation method according to any one of claims 1 to 7, characterized in that, include: S01: Obtain multiple enterprise latitude and longitude data groups and corresponding enterprise verification data; S02: Project the latitude and longitude data of the multiple enterprises onto an ellipsoid using the Gauss-Kruger projection method to obtain the projected ellipsoid for each enterprise. S03: Calculate the area of ​​the projected ellipsoid corresponding to each enterprise to obtain the area occupied by the first ellipsoid corresponding to each enterprise; S04: Divide the area of ​​the first ellipsoid corresponding to each enterprise into overlapping sections to obtain the area of ​​the second ellipsoid corresponding to each enterprise. S05: Based on the area of ​​the first ellipsoid corresponding to each enterprise and the verification data corresponding to each enterprise, spatial association filtering is performed to obtain the enterprise group after spatial association filtering; S06: Obtain multiple operational data for each enterprise in the enterprise group filtered by spatial association; The land area of ​​the second ellipsoid corresponding to each enterprise in the enterprise group filtered by spatial correlation, and the various operating data corresponding to each enterprise in the enterprise group filtered by spatial correlation, are used as industrial land data.

9. A project site selection method, characterized in that, include: S001: Obtain the ellipsoidal area of ​​multiple candidate plots; S002: Based on the ellipsoidal area of ​​each candidate plot and the modulus range described in any one of claims 1 to 7, multiple candidate plots are selected; S003: Select multiple candidate sites after screening as the project site selection results.

10. A spatial matching-based industrial land use modulus interval calculation system, applied to the calculation method described in any one of claims 1 to 7, characterized in that, include: Data acquisition module: Acquires industrial land use data; The industrial land data includes data on multiple enterprises; each enterprise's data includes the ellipsoidal land area and various operational data. Data filtering module: Based on the ellipsoidal land area of ​​each enterprise, the filtered industrial land data is obtained; Regression equation construction module: Constructs a multiple linear regression equation based on the screened industrial land data; Coefficient calculation module: Calculates the optimal coefficient combination based on the multiple linear regression equation and the screened industrial land data; Modulus Interval Calculation Module: Based on the optimal coefficient combination, multiple linear regression equation, and screened industrial land data, the modulus interval is calculated.

Images