Method and system for predicting distribution trend of non-batch construction-first production construction project, and medium

Abstract

The invention discloses a method and a system for predicting the distribution trend of non-batch construction-first production and construction projects, and a medium. The method comprises the following steps: acquiring data of non-batch construction-first production and construction projects affirmed and investigated in the current year; obtaining the number of production construction projects which are not firstly constructed in batches; establishing at least one driving factor according to the acquired driving indexes of the illegal behaviors in the research area in the last year; measuring the independent explanatory force q of the driving factors on the quantity distribution of the production construction projects, and identifying whether interaction enhancement exists among different driving factors or not; selecting a plurality of construction hierarchical structure models from the driving factors, and constructing a UVPI calculation formula; and calculating the UVPI of the current year, and if the significant correlation exists, constructing the UVPI of the next year by using the driving factor data of the current year, and predicting the easy-to-occur area of the production construction project which is not firstly constructed in batches in the next year. According to the method, the distribution rule of the areas where the non-batch construction-first production construction projects are likely to occur can be determined, and a decision basis is provided for preventing and investigating the non-batch construction-first production construction projects.

Description

Technical Field

[0001] The present invention relates to the fields of soil and water conservation and smart water conservancy, and in particular to a method, system and medium for predicting the distribution trend of production and construction projects that have been built without approval. Background Art

[0002] It is clarified that soil and water conservation credit evaluation refers to the Ministry of Water Resources evaluating the credit status of soil and water conservation related units in accordance with relevant laws and regulations and soil and water conservation credit information, in accordance with the prescribed indicators, methods and procedures, determining the credit level and making it public, for soil and water conservation supervision and management, reference by relevant departments and public supervision. Among them, soil and water conservation administrative supervision and administrative penalty information are the main evaluation indicators of soil and water conservation credit, which stipulates the relevant problems of soil and water conservation dishonesty and deducts the corresponding points according to the nature and level of the problems. Production and construction projects that are carried out without submitting soil and water conservation plans for approval in accordance with the requirements of the Soil and Water Conservation Law (construction without approval) are one of the main illegal and irregular behaviors.

[0003] my country has been carrying out remote sensing information-based supervision of illegal and irregular behaviors in production and construction projects for many years, and has carried out on-site review, identification and investigation of suspected unapproved production and construction projects through remote sensing through an integrated air-space-ground approach. According to statistics, more than 1 million projects are started or under construction nationwide each year. It is difficult to meet the construction needs of smart water conservation in the new era by only investigating and handling unapproved production and construction projects through human-computer interaction and on-site verification. Therefore, there is an urgent need for a distribution trend prediction method for unapproved production and construction projects to clarify the distribution patterns of areas prone to unapproved production and construction projects, and provide a decision-making basis for preventing and investigating unapproved production and construction projects. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and medium for predicting the distribution trend of production and construction projects that have been built without approval, so as to solve the problems such as low efficiency and high investment cost that currently exist in the situation where production and construction projects that have been built without approval can only rely on global remote sensing supervision, and to support the construction of a smart credit evaluation system for soil and water conservation.

[0005] In a first aspect, the present invention provides a method for predicting the distribution trend of production and construction projects that have been built without approval, comprising the following steps:

[0006] Step 1: Obtain data on production and construction projects that were investigated and dealt with without approval in the current year in the study area;

[0007] Step 2: spatially match and link the statistical data of the production and construction projects that have been investigated and punished without approval in the study area this year obtained in step 1 with the city-level administrative division surface vectors in the study area, and summarize them to obtain the number of production and construction projects that have been investigated and punished without approval in each city-level administrative district in the study area this year;

[0008] Step 3: Obtain the driving indicators that potentially drive the illegal and irregular behavior of building production and construction projects without approval in each city-level administrative district in the study area in the previous year, wherein the driving indicators include population indicators and economic indicators, and establish at least one driving factor based on the obtained driving indicators;

[0009] Step 4: Use the factor detector module in the geographic detector to measure the independent explanatory power q of the driving factors in step 3 on the number of production and construction projects that were investigated and punished without approval in the study area in the annual municipal administrative districts obtained in step 2, and use the interaction detector module in the geographic detector to identify whether there is an interactive enhancement effect between different driving factors;

[0010] Step 5: According to the independent explanatory power q obtained in step 4 and the driving factors with interactive enhancement effects identified by the interaction detector, several driving factors in step 3 are selected to construct a hierarchical model. Starting from the second layer of the hierarchical model, for the driving factors of the same layer that belong to each driving factor of the previous layer, a judgment matrix is ​​constructed until the bottom layer. After calculating the single sorting weight vector and the total sorting weight vector and performing consistency tests respectively, the weight of each driving factor is obtained, and finally the calculation formula of the Unauthorized Construction Projects Vulnerability Predictive Index (UVPI) is constructed based on this;

[0011] Step 6, calculate the UVPI of the susceptibility prediction index of production and construction projects that have been built without approval for each municipal administrative district in the study area this year according to the calculation formula of UVPI constructed in step 5, and verify the correlation with the actual data of the results of production and construction projects that have been built without approval this year using the Pearson test. If there is a significant correlation between the UVPI of this year and the actual data, the UVPI of the next year is constructed based on the driving factor data of this year to predict the areas prone to production and construction projects that have been built without approval next year, and divide the susceptibility degree into large, relatively large, medium, relatively small, and small according to the natural breakpoint method, and intuitively represent it in the form of a map.

[0012] Furthermore, step 1 obtains the data of production and construction projects that have been identified and investigated without approval in the study area this year, specifically including: obtaining the interactive data in the supervision and management subsystem of the national soil and water conservation information management system, and the results data obtained from the annual soil and water conservation information management work of production and construction projects organized and carried out by provincial-level administrative regions in accordance with the requirements of the "Technical Regulations on Informatization Supervision of Soil and Water Conservation for Production and Construction Projects (Implementation)" compiled and issued by the Ministry of Water Resources.

[0013] Furthermore, the data of production and construction projects that have been identified and investigated for construction without approval in the study area this year in step 1 is a kind of POI data, including latitude and longitude spatial information and attribute information, and the attribute information includes identification code, project name, construction unit, contact person, contact number, project category, disturbance change type, completion status, road section, investigation and punishment status, and investigation and punishment time.

[0014] Furthermore, step 2 specifically includes: according to the spatial position relationship, the attribute table information of the POI data of the production and construction projects that have been identified and investigated without approval and are located within a certain city-level administrative district surface vector is summarized, and the summarized attribute table information is assigned to the city-level administrative district surface vector, wherein each row of data in the city-level administrative district surface vector represents the relevant attribute information of a production and construction project that has been built without approval.

[0015] Furthermore, the population indicators in step 3 include registered population (Household Population, HP), permanent population (Population of Permanent Residents, PPR), and the economic indicators include corporation units (CU), units of scale, qualification or above (QAU), gross domestic product (GDP), primary industry (PI), secondary industry (SI), tertiary industry (TI), value added of private economy (VPE), growth rate of infrastructure investment (II), growth rate of industrial investment in fixed assets (IIFA), growth rate of investment in reconstruction and technological transformation (RTT), investment in real estate development (IRD), growth rate of investment in fixed assets (IFA), growth rate of private fixed asset investment (Growth Rate of of Non-governmental Investment of Fixed Assets (NFA).

[0016] Furthermore, the geographic detector in step 4 is used to detect spatial heterogeneity and reveal the driving force behind it. Spatial heterogeneity means that the same geographical phenomenon shows similarity in the same sub-region, but its distribution in different sub-regions is different.

[0017] Furthermore, the factor detector module is used to detect the spatial heterogeneity of the identification and investigation of production projects that have been built before approval and reveal its interaction with the driving factor described in step 3, as well as the strength, direction, linearity or nonlinearity of the interaction; the factor detector uses the q value to measure the extent to which the driving factor explains the spatial heterogeneity of attribute Y (i.e., identification and investigation of production projects that have been built before approval), and its expression is: where \(h = 1,\cdots,L\), and \(L\) is the number of categories of driving factors; \(N_h\) h and \(N\) are the number of units in layer \(h\) and the whole area, respectively; and \(\sigma_h^2\) 2 are the variances of the \(Y\) values in layer \(h\) and the whole area, respectively. The value range of \(q\) is \([0,1]\). The larger the value, the stronger the explanatory power of the driving factor \(X\) for \(Y\), and vice versa. At the same time, for each corresponding \(q\) value, there is a corresponding significance test \(p\) value. If the \(p\) value is less than \(0.05\), it indicates a significant difference. If \(P\) is less than \(0.01\), the difference is extremely significant. That is, the smaller the \(p\) value, the higher the reliability of the inference that a certain driving factor \(X\) has an impact on the \(Y\) value.

[0018] Furthermore, the interaction detector module, based on the function of the factor detector module, further identifies the influence of the interaction between different driving factors. By calculating the value of \(q(x_1\cap x_2)\) to judge whether the combined effect of driving factors \(x_1\) and \(\sigma_2\) on the dependent variable \(Y\) is enhanced or weakened. After comparing the value of \(q(x_1\cap x_2)\) with the values of \(q(x_1)\) and \(q(x_2)\), the relationship of its influence on \(Y\) can be divided into the following 5 types: non - linear weakening, \(q(x_1\cap x_2)<\min[q(x_1),q(x_2)]\); single - linear weakening, \(\min[q(x_1),q(x_2)]<q(x_1\cap x_2)<\max[q(x_1),q(x_2)]\); double - linear weakening, \(q(x_1\cap x_2)>\max[q(x_1),q(x_2)]\); independent of each other, \(q(x_1\cap x_2)=q(x_1)+q(x_2)\); non - linear enhancement, \(q(x_1\cap x_2)>q(x_1)+q(x_2)\).

[0019] Furthermore, the hierarchical structure model in step 5 is constructed based on the analytic hierarchy process. The analytic hierarchy process is a hierarchical weight decision - making analysis method. According to the mutual - related influence and subordination relationship between each driving factor and the identified and investigated unapproved production projects started before approval, it forms a multi - level analysis structure model, and thereby determines the relative importance weights of each driving factor with respect to reflecting the susceptibility of unapproved production and construction projects started before approval.

[0020] Furthermore, the Pearson test in step 6 measures the correlation between two variables by calculating the Pearson correlation coefficient. The correlation coefficient is obtained by dividing the covariance by the standard deviations of the two variables. The formula is as follows:

[0021]

[0022] where \(n\) is the sample size, \(E(X)\), \(\sigma_X\) x are the sample mean and sample standard deviation of the \(X\) i sample, respectively.

[0023] Furthermore, the natural breakpoint method described in step 6 is a statistical method for grading and classifying according to the statistical distribution law of numerical values, which maximizes the difference between classes. Any statistical series has some natural turning points and characteristic points, which can be used to divide the research objects into groups with similar properties. The present invention adopts the natural breakpoint method to determine the natural characteristic points of the susceptibility index of production and construction projects that have been built before approval in each municipal administrative district in the study area, and thereby realizes the grading and classification of the predicted susceptibility of production and construction projects that have been built before approval in each municipal administrative district in the study area.

[0024] Another aspect of the present invention provides a distribution trend prediction system for production and construction projects that are built without approval, comprising: a computer-readable storage medium and a processor;

[0025] The computer-readable storage medium is used to store executable instructions;

[0026] The processor is used to read the executable instructions stored in the computer-readable storage medium to execute the method for predicting the distribution trend of production and construction projects that have been built without approval as described in the first aspect.

[0027] On the other hand, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting distribution trends of production and construction projects that have been built without approval as described in the first aspect.

[0028] The beneficial effects of the present invention are:

[0029] The present invention proposes to conduct qualitative and quantitative analysis on the distribution trend of unapproved construction projects in this year through the driving factors of the previous year based on geographic detectors and hierarchical analysis method, and construct an unauthorized construction projects vulnerability prediction index (UVPI) for predicting the distribution trend of unapproved construction projects in the region. The index is based on the quantitative study of the interactive relationship between the identification and investigation of production and construction projects and regional population, social, economic and other driving factors, taking into account subjective and objective evaluation and analysis methods, and predicting the spatial trend of the prone areas of unapproved construction projects, which has a high reference value for the "precision guidance" of illegal and irregular production and construction project units. The present invention calculates the UVPI index through the driving factors of this year, predicts the areas where unapproved construction projects are likely to occur in the next year, and carries out targeted key supervision. In a feasible embodiment, compared with the full coverage human-computer interactive supervision method, this technology reasonably allocates human resources and time through targeted key supervision, and on the premise of ensuring accuracy, the overall efficiency is improved by about 20%, which improves the pertinence, scientificity, accuracy and timeliness of soil and water conservation supervision of production and construction projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic flow chart of a method for predicting distribution trends of production and construction projects that are built without approval according to an embodiment of the present invention;

[0031] Figure 2 This is a schematic diagram of the data of the information-based supervision results of soil and water loss in the annual production and construction projects in the study area of ​​Hubei Province according to an embodiment of the present invention;

[0032] Figure 3 This is a diagram of the interactive detection results of driving factors in the previous year in the Hubei Province study area according to an embodiment of the present invention;

[0033] Figure 4 It is a judgment matrix diagram of driving factors of the previous year in the Hubei Province study area according to an embodiment of the present invention;

[0034] Figure 5 Schematic diagram of the UVPI forecast index for the susceptibility of production and construction projects to be built without approval in the next year, which is constructed based on the driving factors of the Hubei study area in this year in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] See also Figure 1 The embodiment of the present invention provides a method for predicting the distribution trend of production and construction projects that have been built without approval, taking the Hubei Province research area as an example, and further illustrating the method, including the following steps:

[0037] Step 1: Obtain the results data of the information-based supervision of soil and water conservation in Hubei Province's production and construction projects in 2021. Among them, the information-based supervision of soil and water loss in Hubei Province's production and construction projects in 2021 is mainly divided into three phases, which are: the annual issuance of the Ministry of Water Resources, the first phase in Hubei Province, and the second phase in Hubei Province. Based on the results of the three phases of information-based supervision, the annual information-based supervision results of soil and water loss in Hubei Province's production and construction projects are summarized. The results are as follows: Figure 2 As shown in the figure, a total of 3565 POI point information data were obtained. After data cleaning and data standardization, 1718 POI point information data of production and construction projects that were investigated and dealt with without approval were finally obtained. The vector field of the standardized data is shown in Table 1.

[0038] Table 1

[0039]

[0040] Step 2: Spatial matching is performed between the results data of the production and construction projects identified and investigated without approval in Hubei Province in 2021 in step 1 and the surface vectors of 17 municipal-level administrative divisions in Hubei Province, and the attribute table information of the POI data of the production and construction projects identified and investigated without approval located within the surface vectors of each municipal-level administrative division is summarized, and the summarized attribute table information is assigned to the corresponding municipal-level administrative division surface vector, to obtain the summary data of various attributes of the production and construction projects identified and investigated without approval in each municipal-level administrative division in the study area. The summary attributes of the production and construction projects identified and investigated without approval in the municipal-level administrative divisions of Hubei Province in 2021 are shown in Table 2;

[0041] Table 2

[0042]

[0043] Step 3: Obtain the economic, population and other relevant indicators of each city-level administrative region in Hubei Province in 2020 (i.e., the year before the corresponding year of the data on the results of the identification and investigation of production and construction projects that were built without approval), including: Household Population (HP), Permanent Residents (PPR), Corporation Units (CU), Unit of Scale, Qualification or Above (QAU), Gross Domestic Product (GDP), Primary Industry (PI), Secondary Industry (SI), Tertiary Industry (TI), Value Added of Private Economy (VPE), Growth Rate of Infrastructure Investment (II), Growth Rate of Industrial Investment in Fixed Assets (IIFA), Growth Rate of Investment in Reconstruction and Technological Transformation (Growth Rate of Investment in Reconstruction and Technological Transformation) The paper constructs 15 driving factors, namely, real estate investment transformation (RTT), real estate development investment (IRD), fixed asset investment growth rate (IFA), and private fixed asset investment growth rate (NFA).

[0044] Step 4: Use the factor detector in the geographic detector to measure the independent explanatory power q and the corresponding significance test p value of the 15 driving factors selected in step 3 on the distribution of production and construction projects identified and investigated (as shown in Table 3). Then use the interaction detector in the geographic detector to identify the interaction influence between different driving factors. The results are as follows: Figure 3 shown.

[0045] Table 3

[0046]

[0047] Step 5: According to the corresponding q value and p value in Table 3 and Figure 3 In order to understand the interaction between the driving factors, 10 driving factors with significant influence and mutual reinforcing influence, including HP, PPR, CU, QAU, GDP, PI, SI, TI, VPE and IRD, were selected to construct a hierarchical model. Referring to the 1-9 scale method of hierarchical analysis, starting from the second level of the hierarchical model, for the driving factors of the same level belonging to each driving factor of the previous level, a judgment matrix was constructed until the lowest level (such as Figure 4 After calculating the single ranking weight vector and the total ranking weight vector and performing consistency tests respectively, the weights corresponding to the 10 driving factors selected in 2020 are obtained (as shown in Table 4). Finally, the UVPI index for the susceptibility prediction of unapproved production and construction projects in 2021 is constructed. The specific formula of UVI is as follows:

[0048] UVI=0.1667*HP+0.1667*PPR+0.1667*CU+0.1667*QAU+0.0765*GDP+0.0765*SI+0.0765*TI+0.0402*PI+0.0402*VPE+0.0233*IRD

[0049] Table 4

[0050]

[0051] Step 6: Calculate the susceptibility prediction index of unapproved production and construction projects for each municipal administrative region in Hubei Province in 2021, and use the Pearson test to verify the correlation with the actual results of the production and construction projects that were identified and investigated in 2021. The results are shown in Table 5. The UVPI established based on the driving factors in 2020 is significantly correlated with the actual production and construction projects that were identified and investigated in 2021. The UVPI is constructed based on the driving factor data in 2021 to predict the areas prone to unapproved production and construction projects in 2022, and the degree of susceptibility is divided into large, large, medium, small, and small according to the natural breakpoint method, and is intuitively represented in the form of a map. The results are shown in Table 5. Figure 5 shown.

[0052] Table 5

[0053]

[0054] Another aspect of the present invention provides a distribution trend prediction system for production and construction projects that are built without approval, comprising: a computer-readable storage medium and a processor;

[0055] The computer-readable storage medium is used to store executable instructions;

[0056] The processor is used to read the executable instructions stored in the computer-readable storage medium to execute the method for predicting the distribution trend of production and construction projects that have been built without approval as described in the first aspect.

[0057] On the other hand, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting distribution trends of production and construction projects that have been built without approval as described in the first aspect.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0059] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting the distribution trend of production and construction projects that have been built without approval, characterized in that: The steps include: Step 1: Obtain data on production and construction projects that were investigated and dealt with without approval in the current year in the study area; Step 2: spatially match and link the statistical data of the production and construction projects that have been investigated and punished without approval in the study area this year obtained in step 1 with the city-level administrative division surface vectors in the study area, and summarize them to obtain the number of production and construction projects that have been investigated and punished without approval in each city-level administrative district in the study area this year; Step 3: Obtain the driving indicators that potentially drive the illegal and irregular behavior of building production and construction projects without approval in each city-level administrative district in the study area in the previous year, wherein the driving indicators include population indicators and economic indicators, and establish at least one driving factor based on the obtained driving indicators; Step 4: Use the factor detector module in the geographic detector to measure the independent explanatory power q of the driving factors in step 3 on the number of production and construction projects that were investigated and punished without approval in the study area in the annual municipal administrative districts obtained in step 2, and use the interaction detector module in the geographic detector to identify whether there is an interactive enhancement effect between different driving factors; Step 5: According to the independent explanatory power q obtained in step 4 and the driving factors with interactive enhancement effects identified by the interaction detector, several driving factors in step 3 are selected to construct a hierarchical model. Starting from the second layer of the hierarchical model, for the driving factors of the same layer that belong to each driving factor of the previous layer, a judgment matrix is ​​constructed until the bottom layer. After calculating the single sorting weight vector and the total sorting weight vector and performing consistency tests respectively, the weight of each driving factor is obtained, and finally the calculation formula of the susceptibility prediction index UVPI of production and construction projects built without approval is constructed; Step 6, calculate the UVPI of the susceptibility prediction index of production and construction projects that have been built without approval for each municipal administrative district in the study area this year according to the calculation formula of UVPI constructed in step 5, and verify the correlation with the actual data of the results of production and construction projects that have been built without approval this year using the Pearson test. If there is a significant correlation between the UVPI of this year and the actual data, the UVPI of the next year is constructed based on the driving factor data of this year to predict the areas prone to production and construction projects that have been built without approval next year, and divide the susceptibility degree into large, relatively large, medium, relatively small, and small according to the natural breakpoint method, and intuitively represent it in the form of a map.

2. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 1, characterized in that: The data of production and construction projects that have been identified and investigated for construction without approval in the study area this year in step 1 is a kind of POI data, including latitude and longitude spatial information and attribute information, and the attribute information includes identification code, project name, construction unit, contact person, contact number, project category, disturbance change type, completion status, road section, investigation and punishment status, and investigation and punishment time.

3. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 1, characterized in that: Step 2 specifically includes: according to the spatial position relationship, the attribute table information of the POI data of the production and construction projects that have been identified and investigated without approval and are located within a certain city-level administrative district surface vector is summarized, and the summarized attribute table information is assigned to the city-level administrative district surface vector, wherein each row of data in the city-level administrative district surface vector represents the relevant attribute information of a production and construction project that has been built without approval.

4. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 1, characterized in that: The population indicators described in step 3 include the household registered population and the permanent population. The economic indicators include the number of legal entities, above-scale units, gross regional product, primary industry, secondary industry, tertiary industry, added value of the private economy, growth rate of infrastructure investment, growth rate of industrial investment, growth rate of renovation and technological transformation investment, real estate development investment, growth rate of fixed asset investment, and growth rate of private fixed asset investment.

5. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 1, characterized in that: The geographical detector described in step 4 is used to detect spatial heterogeneity and reveal the driving force behind it. Spatial heterogeneity means that the same geographical phenomenon shows similarity within the same sub-region, but its distribution shows differences among different sub-regions.

6. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 5, characterized in that: The factor detector module is used to detect the spatial heterogeneity of the identified and punished production projects constructed without approval and reveal its interaction with the driving factors described in step 3, as well as the strength, direction, linear or non-linear nature of the interaction. The factor detector uses the q value to measure the extent to which the driving factor explains the spatial differentiation of attribute Y (i.e., identifying and investigating production projects that were built without approval), and its expression is: In the formula, h = 1, ..., L, L is the number of categories of driving factors; N h and N are the number of units in layer h and the whole area, respectively; and σ 2 are the variances of the Y values ​​of layer h and the whole region, respectively. The range of q is [0,1]. The larger the value, the stronger the explanatory power of the driving factor X on Y, and vice versa. At the same time, there is a significance test p value for each corresponding q value. If the p value is less than 0.05, it means that the difference is significant. If P is less than 0.01, the difference is extremely significant, that is, the smaller the p value, the higher the reliability of the inference that a driving factor X has an impact on the Y value.

7. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 6, characterized in that: Based on the function of the factor detector module, the interaction detector module further identifies the influence of the interaction between different driving factors. By calculating the q(x1∩x2) value, it is determined whether the combined effect of the driving factors x1 and x2 on the dependent variable Y is enhanced or weakened. After comparing the q(x1∩x2) value with the values of q(x1) and q(x2), the relationship of its influence on Y can be divided into the following five types: non-linear weakening, q(x1∩x2) < min[q(x1), q(x2)]; Single linear weakening, min[q(x1), q(x2)] < q(x1∩x2) < max[q(x1), q(x2)]; double linear weakening, q(x1∩x2) > max[q(x1), q(x2)]; independent of each other, q(x1∩x2) = q(x1) + q(x2); non-linear strengthening, q(x1∩x2) > q(x1) + q(x2).

8. The method for predicting the distribution trend of production and construction projects that have been built without approval as claimed in claim 1, characterized in that: The Pearson test described in step 6 is used to measure the correlation between two variables by calculating the Pearson correlation coefficient. The correlation coefficient is obtained by dividing the covariance by the standard deviations of the two variables. The formula is as follows: Where n is the number of samples, E(X), σ x They are respectively i The sample mean and sample standard deviation of the sample.

9. A distribution trend prediction system for production and construction projects that have been built without approval, comprising: A computer-readable storage medium and a processor; The computer-readable storage medium is used to store executable instructions; The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the method for predicting the distribution trend of production and construction projects constructed without approval as described in any one of claims 1-8.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting distribution trends of production and construction projects that have been built without approval as described in any one of claims 1 to 8.

Images