Urban and rural construction land integrated reference land price evaluation method and system
The integrated benchmark land price assessment method for urban and rural construction land based on GBDT solves the problem of the lack of unified assessment in the urban and rural construction land market, realizes the unification of land use and location level, provides price assessment for collective construction land entering the market, and supports the integration of the urban and rural construction land market.
Patent Information
- Application Number
- CN202510749766.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-06
- Publication Date
- 2025-11-07
AI Technical Summary
The lack of existing technology for integrated benchmark land price assessment of urban and rural construction land leads to large differences in transaction prices in neighboring areas, resulting in a lack of a systematic approach that affects the entry of collectively owned commercial construction land into the market and hinders the unification of the urban and rural construction land market.
A land benchmark price prediction model is constructed based on gradient boosting decision tree (GBDT). By combining land transaction data and factors affecting land prices, and through data preprocessing and model training, the average land price of each land grade is calculated. The model takes into account the cost differences between state-owned construction land and collective construction land, and provides a unified assessment method.
It has achieved the unification of urban and rural construction land use classification and location level, provided a price assessment basis for the entry of collectively owned commercial construction land into the market, and supported the integrated development of urban and rural construction land market.
Smart Images
Figure CN120912277A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of land price evaluation, in particular to a method and system for evaluating integrated benchmark land price of urban and rural construction land. BACKGROUND
[0002] The urban and rural unified construction land market system aims to put collective construction land and state-owned construction land into the market on an equal footing, and to achieve the same price. However, in practice, the pricing lacks unified reference in the process of promoting the collective operational construction land into the market, resulting in a large difference in transaction prices in adjacent regions, no systematicity, damage to the interests of the assignee, and hindering the goal realization. Therefore, establishing a scientific and reasonable method for evaluating integrated benchmark land price of urban and rural construction land, and achieving the differentiation and unity of urban and rural construction land, is a key technical problem for building the urban and rural unified construction land market system.
[0003] The existing benchmark land price evaluation of urban and rural construction land mainly establishes the benchmark land price evaluation system of state-owned construction land and collective construction land respectively, among which the benchmark land price evaluation of collective construction land mostly refers to the urban land valuation regulations, and lacks a method for integrated benchmark land price evaluation of urban and rural construction land. In addition, the mainstream benchmark land price evaluation system often uses multi-factor comprehensive scoring method for land grading, and uses market comparison method, income restoration method, etc. to calculate the benchmark land price, which fails to consider the nonlinear relationship between influencing factors and land price, and has certain limitations. SUMMARY
[0004] The purpose of the present application is to provide a method for evaluating integrated benchmark land price of urban and rural construction land, which solves the problem of lack of integrated calculation of benchmark land price of urban and rural construction land in the prior art, comprising the following steps: S1. Obtain land transaction data and land price influencing factor data, and preprocess the data, obtain land price feature data set based on the preprocessed data, and divide the land price feature data set into training set and test set; S2. Construct a land benchmark land price prediction model based on Gradient Boosting Decision Tree (GBDT), and train and test the model using the training set and the test set respectively to obtain the tested model; S3. Input the land price influencing factor data of the area to be evaluated into the tested model to obtain the land price of each spatial grid, and calculate the land price mean value of each land grade; S4. If the to-be-evaluated area is state-owned construction land, the average land price is taken as the benchmark land price of the to-be-evaluated area; if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = average land price of the same level of state-owned construction land - urban house demolition management fee - urban infrastructure matching fee - land value-added tax - urban maintenance and construction tax - education fee surcharge - local education fee surcharge + unemployment insurance for farmers.
[0005] Further, the preprocessing of the data comprises: data cleaning, data conversion, and filling of missing values by using an interpolation method.
[0006] Further, the land price feature data set is obtained based on the preprocessed data, comprising: determining a grid size based on the preprocessed data; processing the preprocessed data by using a Fishnet tool of ArcGIS based on the grid size, assigning spatial attributes by using a spatial connection function of ArcGIS, and constructing a land price feature data set; Further, the land transaction data comprises: plot area, utilization type, land grade, transaction price data, transaction date, and plot ratio; and the land price influencing factor data comprises: basic facility condition data, environmental condition data, social and economic condition data, traffic condition data, and regional planning data.
[0007] The basic facility condition data comprises: basic facility completeness and public facility completeness; the environmental condition data comprises: environmental quality degree, green coverage, and water coverage; the social and economic condition data comprises: population quantity, industrial aggregation degree, and commercial and service prosperity degree; and the traffic condition data comprises: road accessibility, bus convenience, and external traffic convenience.
[0008] Further, The basic facility completeness comprises: education POI data and medical POI data. The public facility completeness comprises public facility POI data. The environmental quality degree comprises an air pollution index. The green coverage comprises green AOI data. The water coverage comprises water AOI data. The population quantity comprises resident population data. The industrial aggregation degree comprises enterprise institution POI data. The commercial and service prosperity degree comprises catering POI data and financial POI data. The road accessibility comprises road AOI data and building AOI data. The bus convenience comprises bus POI data. The external traffic convenience degree comprises external traffic POI data.
[0009] Further, the land benchmark land price prediction model constructed based on the GBDT is composed of M decision trees, and when the model fits the mapping relationship between the input training set X and the land price data set Y, the mapping relationship is realized through the step-by-step iteration prediction of the M decision trees: The GBDT formula is: , Wherein, y Indicates the land price, Indicates the weight of the mth decision tree, Indicates the mth decision tree, x Indicates the input vector, Indicates the parameter of the mth decision tree. , Wherein, Indicates the mth GBDT model, Indicates the (m-1)th GBDT model. The parameter calculation formula of the mth decision tree is: , , Wherein, Indicates the loss function of the mth decision tree.
[0010] The application further provides a land benchmark land price evaluation system for urban and rural construction land integration, comprising: A data acquisition module is configured to acquire land transaction data and land price influencing factor data, pre-process the data, obtain land price feature data set based on the pre-processed data, and divide the land price feature data set into a training set and a test set. A model construction and training and testing module is configured to construct a land benchmark land price prediction model based on the GBDT, train and test the model using the training set and the test set respectively, and obtain the tested model. A land price average value calculation module is configured to input the land price influencing factor data of the to-be-evaluated area into the tested model to obtain the land price of each spatial grid, and calculate the land price average value of each land grade. A benchmark land price evaluation module is configured to evaluate the benchmark land price, wherein if the to-be-evaluated area is state-owned construction land, the land price average value is taken as the benchmark land price of the to-be-evaluated area; and if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = land price average value of the same grade state-owned construction land of the same land class - urban house demolition management fee - urban infrastructure matching fee - land value-added tax - urban maintenance and construction tax - education fee surcharge - local education fee surcharge + unemployment farmer insurance.
[0011] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the urban and rural construction land integrated benchmark land price evaluation method.
[0012] The application further provides an electronic device, which comprises a processor and a memory, and the processor and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program comprises computer readable instructions, and the processor is configured to invoke the computer readable instructions to execute the urban and rural construction land integrated benchmark land price evaluation method.
[0013] The application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the steps of the urban and rural construction land integrated benchmark land price evaluation method.
[0014] The application provides the technical scheme, and the beneficial effects are as follows: The application provides an urban and rural construction land integrated benchmark land price evaluation method. The method constructs a complete land price characteristic data set based on land transaction data and land price influence factor data, and combines GBDT to construct a land benchmark land price prediction model, considers the cost difference of collective construction land and state-owned construction land from the land price constituent elements, on the one hand, realizes the unified use classification of urban and rural construction land, and realizes the connection of location and grade division, provides a price evaluation basis for the marketization of collective business construction land; on the other hand, the model considering the nonlinear relationship of influence factors is provided, and technical support is provided for the construction of the integrated market of urban and rural construction land. BRIEF DESCRIPTION OF DRAWINGS
[0015] Figure 1 is a flowchart of an urban and rural construction land integrated benchmark land price evaluation method according to an embodiment of the application; Figure 2 is a block diagram of an electronic device in an example embodiment according to the application. DETAILED DESCRIPTION
[0016] In order to make the purpose, technical scheme and advantages of the application more clear, the embodiments of the application will be further described below with reference to the drawings.
[0017] The flowchart of the urban and rural construction land integrated benchmark land price evaluation method according to an embodiment of the application is as shown in Figure 1 , and specifically comprises the following steps: S1. Obtain land transaction data and land price influencing factor data, the land transaction data containing actual transaction land price, which is the label data of land price. The land price influencing factor data includes: ① administrative factor; ② population factor; ③ social factor; ④ economic factor; ⑤ international factor, each factor having a certain weight influence on land price.
[0018] First, data cleaning and data conversion are performed, repeated data in the data is cleaned, the data is normalized, and the interpolation method is used to fill in the missing values.
[0019] The pre-processed data is processed to obtain a land price feature data set, including: (1) Based on the regional characteristics of the selected site area in the processed data, the grid size is determined; (2) Based on the grid size, the fishnet tool of ArcGIS is used to process the processed data, the spatial connection function of ArcGIS is used to assign spatial attributes, and the land price feature data set is constructed.
[0020] The land transaction data includes: plot area, utilization type, land grade, transaction price data, transaction date, plot ratio; the land price influencing factor data includes: basic facility condition data, environmental condition data, social and economic condition data, traffic condition data, regional planning data.
[0021] The basic facility condition data includes: basic facility completeness, public facility completeness; the environmental condition data includes: environmental quality degree, green coverage, water coverage; the social and economic condition data includes: population, industrial concentration, commercial prosperity; the traffic condition data includes: road accessibility, bus convenience, external traffic convenience.
[0022] The basic facility completeness includes: education POI (Point of Interest) data, medical POI data; the public facility completeness includes public facility POI data; the environmental quality degree includes air pollution index; the green coverage includes green AOI (Area of Interest) data; the water coverage includes water AOI data; the population includes permanent population data; the industrial concentration includes enterprise POI data; the commercial prosperity includes catering POI data, financial POI data; the road accessibility includes road AOI data, building AOI data; the bus convenience includes bus POI data; the external traffic convenience includes external traffic POI data.
[0023] S2. A land benchmark land price prediction model is constructed based on gradient boosting decision tree (GBDT), the model is trained and tested using the training set and the test set, and the tested model is obtained.
[0024] The land benchmark land price prediction model based on GBDT is composed of M (M>1) decision trees. The land price feature data set is input into the GBDT model, and the decision tree is iteratively constructed. For each iteration, the residual of the current model for each sample is calculated. According to these residuals as target variables, a new decision tree is generated by using a regression tree to fit the data. When the preset maximum number of iterations is reached, the residuals of all samples are small enough, or the newly added tree cannot significantly reduce the loss function, the iteration is stopped.
[0025] When the model fits the mapping relationship between the input training set X and the land price data set Y, it is realized by step-by-step iteration prediction of M decision trees: The GBDT formula is: , Wherein, y represents the land price, represents the weight of the mth decision tree, represents the mth decision tree, x represents the input vector, represents the parameter of the mth decision tree. , Wherein, represents the mth GBDT model, represents the (m-1)th GBDT model. The parameter calculation formula of the mth decision tree is: ， , Wherein, represents the loss function of the mth decision tree.
[0026] S3. Input the land price influencing factor data of the area to be evaluated into the tested model to obtain the land price of each spatial grid, and calculate the land price average of each land grade.
[0027] The calculation formula of the mth step of GBDT prediction data is: , Wherein, represents the prediction value of the mth sample grid after m iterations, i represents the prediction value of the mth sample grid after m-1 iterations. i
[0028] S4. If the to-be-evaluated area is state-owned construction land, the average land price is taken as the benchmark land price of the to-be-evaluated area of the same land grade; if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = average land price of state-owned construction land of the same grade - urban house relocation management fee - urban infrastructure matching fee - land value-added tax - urban maintenance and construction tax - education fee surcharge - local education fee surcharge + unemployment insurance for farmers.
[0029] The application further provides an integrated benchmark land price evaluation system for urban and rural construction land, comprising: a data acquisition module, configured to acquire land transaction data and land price influence factor data, and to pre-process the data, to obtain land price feature data sets based on the pre-processed data, and to divide the land price feature data sets into a training set and a test set; a model construction and training and testing module, configured to construct a land benchmark land price prediction model based on GBDT, and to train and test the model using the training set and the test set respectively, to obtain a tested model; a land price average value calculation module, configured to input the to-be-evaluated area land price influence factor data into the tested model to obtain the land price of each spatial grid, and to calculate the land price average value of each land grade; a benchmark land price evaluation module, configured to evaluate the benchmark land price, if the to-be-evaluated area is state-owned construction land, the average land price is taken as the benchmark land price of the to-be-evaluated area; if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = average land price of state-owned construction land of the same grade - urban house relocation management fee - urban infrastructure matching fee - land value-added tax - urban maintenance and construction tax - education fee surcharge - local education fee surcharge + unemployment insurance for farmers.
[0030] In an example embodiment, a computer readable storage medium is included, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned integrated benchmark land price evaluation method for urban and rural construction land.
[0031] Please refer to Figure 2 In an example embodiment, an electronic device is further included, comprising at least one processor, at least one memory, and at least one communication bus.
[0032] The memory stores a computer program, and the computer program comprises computer readable instructions; the processor invokes the computer readable instructions stored in the memory through the communication bus, and executes the above-mentioned integrated benchmark land price evaluation method for urban and rural construction land.
[0033] The application further provides a computer program product, comprising a computer program, characterized in that the computer program is executed by a processor to implement the steps of the above-mentioned integrated benchmark land price evaluation method for urban and rural construction land.
[0034] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Numerous modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without the use of the inventive faculty. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An integrated urban and rural construction land benchmark land price evaluation method, characterized in that, The method comprises the following steps: S1. Obtain land transaction data and land price influencing factor data, and pre-process the data, obtain land price feature data set based on the pre-processed data, and divide the land price feature data set into a training set and a test set; S2. Construct a land benchmark land price prediction model based on GBDT, train and test the model using the training set and the test set respectively, and obtain the model after testing; S3. Input the land price influencing factor data of the to-be-evaluated area into the model after testing to obtain the land price of each spatial grid, and calculate the average land price of each land grade; S4. If the to-be-evaluated area is state-owned construction land, the average land price is taken as the benchmark land price of the to-be-evaluated area; if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = average land price of the same grade state-owned construction land of the same land type - urban house relocation management fee - urban infrastructure matching fee - land value-added tax - urban maintenance and construction tax - education fee surcharge - local education fee surcharge + unemployment farmer insurance.
2. The integrated urban and rural construction land benchmark land price evaluation method according to claim 1, characterized in that, The data pre-processing comprises: data cleaning, data conversion, and filling of missing values by using an interpolation method.
3. The integrated urban and rural construction land benchmark land price evaluation method according to claim 1, characterized in that, The land price feature data set is obtained based on the pre-processed data, which comprises: determining a grid size based on the pre-processed data; processing the data by using a fishnet tool of ArcGIS based on the grid size, assigning spatial attributes by using a spatial connection function of ArcGIS, and constructing the land price feature data set.
4. The integrated urban and rural construction land benchmark land price evaluation method according to claim 1, characterized in that, The land transaction data comprises: plot area, utilization type, land grade, transaction price data, transaction date, and plot ratio; the land price influencing factor data comprises: basic facility condition data, environmental condition data, social and economic condition data, traffic condition data, and regional planning data; The basic facility condition data comprises: basic facility completeness and public facility completeness; the environmental condition data comprises: environmental quality degree, green coverage, and water coverage; the social and economic condition data comprises: population, industrial aggregation, and commercial and service prosperity; and the traffic condition data comprises: road accessibility, bus convenience, and external traffic convenience.
5. The method according to claim 4, wherein the basic facility completeness comprises: education POI data and medical POI data; the public facility completeness comprises public facility POI data; the environmental quality degree comprises an air pollution index; the green coverage comprises green AOI data; the water coverage comprises water AOI data; the population comprises permanent population data; the industrial aggregation comprises enterprise POI data; the commercial and service prosperity comprises catering POI data and financial POI data; the road accessibility comprises road AOI data and building AOI data; the bus convenience comprises bus POI data; the external traffic convenience comprises external traffic POI data.
6. The integrated urban and rural construction land benchmark land price assessment method according to claim 1, characterized in that, The land benchmark land price prediction model constructed based on GBDT is composed of M decision trees, and when the model fits the mapping relationship between the input training set X and the land price data set Y, the mapping relationship is realized by step-by-step iteration prediction of the M decision trees: the GBDT formula is: ， wherein, y denotes the land price, denotes the mth step decision tree weight, denotes the mth step decision tree, x denotes the input vector, denotes the parameter of the mth step decision tree; and the model iteration calculation formula is: ， wherein, denotes the m-th step GBDT model, denotes the m-1-th step GBDT model; The parameter calculation formula of the m-step decision tree is: ， ， wherein, Lmrepresents the loss function of the mth decision tree.
7. An integrated urban and rural construction land benchmark land price evaluation system, characterized by, Comprise: The data acquisition module is used for acquiring land transaction data and land price influence factor data, and preprocessing the data, obtaining land price feature data set based on the preprocessed data, dividing the land price feature data set into training set and test set; The model construction and training, testing module is used for constructing land benchmark land price prediction model based on GBDT, training and testing the model using the training set and the test set respectively, and obtaining the tested model; The land price average calculation module is used for inputting the land price influence factor data of the to-be-evaluated area into the tested model to obtain the land price of each spatial grid, and calculating the land price average of each land grade; The benchmark land price evaluation module is used for benchmark land price evaluation, if the to-be-evaluated area is state-owned construction land, the land price average is taken as the benchmark land price of the to-be-evaluated area; if the to-be-evaluated area is collective construction land, the benchmark land price is calculated according to the following formula: benchmark land price = land price average of the same grade state-owned construction land of the same land class - urban house demolition management fee - urban infrastructure matching fee - land value-added tax - urban maintenance construction tax - education fee surcharge - local education fee surcharge + unemployed peasant insurance.
8. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by the processor to realize the method of any one of claims 1-6.
9. An electronic device, comprising: The processor and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program comprises computer readable instructions, and the processor is configured to call the computer readable instructions to execute the method of any one of claims 1-6.
10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1-6.