Intelligent algorithm for evaluating target land price based on market land price

Abstract

The invention discloses an intelligent algorithm for evaluating a target land price based on a market land price. The intelligent algorithm comprises the following steps: 1) acquiring target land parcel data; 2) based on the target land parcel data, using a GIS tool to delimit a peripheral area range of the target land parcel, and screening out similar land similar to the target land parcel in use, property and planning index from the determined peripheral area range; 3) calculating the average unit price of the same kind of land; 4) adjusting the average unit price based on land use, planning indexes and position advantages; and 5) based on the adjusted average unit price and the area of the target land parcel, obtaining the land price of the target land parcel, and performing visualization. According to the method, the economic value and potential value of the land are quantified in combination with multi-source data, and the influence of policy adjustment and market fluctuation on the land value is tracked in real time; and a scientific basis is provided for time sequence planning of land collection, storage, transfer and development.

Description

Technical Field

[0001] This invention relates to the field of target land price assessment, specifically an intelligent algorithm for assessing target land prices based on market land prices. Background Technology

[0002] With the rapid development of cities and the increasing scarcity of land resources, the scientific management and effective use of land has become an important issue in urban planning and development.

[0003] Land value analysis can strengthen land management, improve the efficiency of land resource utilization, realize the preservation and appreciation of land assets, and thus provide strong support for the sustainable development of cities.

[0004] However, existing land valuation methods have the following drawbacks:

[0005] 1. The vague definition of supply and demand areas leads to significant differences between the selected cases and the market environment of the target plots, affecting the rationality of the assessment results.

[0006] 2. Some assessment methods still use benchmark land prices that are more than 6 years old, or incorrectly apply different levels of correction systems, resulting in confusion about the connotation of land prices.

[0007] 3. Some assessment reports lack sufficient basis when using land price indices and fail to reflect the latest market fluctuations.

[0008] Therefore, it is necessary to establish a scientific and efficient value analysis model to accurately assess land value and provide a basis for decision-making in urban planning and rational allocation of land resources. Summary of the Invention

[0009] The purpose of this invention is to provide an intelligent algorithm for assessing target land prices based on market land prices, comprising the following steps:

[0010] 1) Obtain data on the target land parcel, including basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data;

[0011] 2) Based on the target plot data, use GIS tools to delineate the area surrounding the target plot, and then filter out similar land with the same use and planned land use nature as the target plot within the determined area.

[0012] 3) Calculate the average unit price of similar land; the average unit price equals the total price divided by the total gross floor area;

[0013] 4) Adjust the average unit price based on land use and planning indicators;

[0014] 5) Based on the adjusted average unit price and the area of ​​the target plot, the land price of the target plot is obtained and visualized.

[0015] Furthermore, the basic attribute data includes land parcel area, shape, ownership, planned use, plot ratio, building density, benchmark land price, land transfer, and land allocation data.

[0016] The market transaction data includes the historical transaction price of the land parcel, the premium rate, the auction failure rate, and the types of bidding companies.

[0017] Furthermore, the spatial correlation data includes rivers, mountains, highways and expressways, distances to nearby subway stations, number of schools / hospitals / commercial areas within 1km, and land accessibility index; wherein, the land accessibility index refers to the total number of bus stops within a 300km radius of the land plot that can be reached without transfers by all bus routes stopping there, as a percentage of the total number of bus stops in the surveyed area.

[0018] Furthermore, the socio-economic data includes regional GDP growth rate, population density, industrial layout planning, and major infrastructure project implementation plans; major infrastructure projects include high-speed rail stations and industrial parks.

[0019] Furthermore, the policy constraint data includes building height restrictions, ecological red line boundaries, and land transfer restrictions.

[0020] Furthermore, step 2), the step of delineating the area surrounding the target plot, includes:

[0021] 1) Determine the administrative boundaries of the target land parcel;

[0022] 2) Delineate the area surrounding the target plot based on the preset buffer zone distance; the area surrounding the target plot shall not exceed the planning unit where the target plot is located, and shall be located on the same side of the target plot as the river, highway, or expressway.

[0023] Furthermore, in step 3), the average unit price of similar land parcels is shown below:

[0024]

[0025] In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i ω is the unit price of parcel i of the same type; i For weights.

[0026] Furthermore, the adjustment method for the average unit price is as follows:

[0027] For mixed-use residential and commercial land with rail transit stations, the average unit price will be increased by 15%.

[0028] For land designated solely for residential use, the average unit price will be increased by 10%.

[0029] For ordinary residential and commercial mixed-use land, the price will be increased by 5% based on the average unit price;

[0030] For mixed-use commercial and residential land, the average unit price will not be adjusted;

[0031] For purely commercial land, the average unit price will be reduced by 5%.

[0032] For plots with a floor area ratio greater than 3, the average unit price will be reduced by 5%.

[0033] A system based on the aforementioned intelligent algorithm includes a data acquisition module, a similar land parcel evaluation module, an average unit price calculation module, an average unit price adjustment module, a land price evaluation module, and a visualization module.

[0034] The data acquisition module acquires data of the target land parcel;

[0035] The similar land parcel assessment module uses GIS tools to delineate the surrounding area of ​​the target land parcel based on the target land parcel data, and filters out similar land parcels with similar uses, properties and planning indicators to the target land parcel within the determined surrounding area.

[0036] The average unit price calculation module calculates the average unit price of similar land.

[0037] The average unit price adjustment module adjusts the average unit price based on land use, planning indicators, and location advantages;

[0038] The land price assessment module calculates the land price of the target plot based on the adjusted average unit price and the area of ​​the target plot.

[0039] The visualization module generates reports containing data and charts, and uses GIS tools or visualization libraries to generate maps that display the target plot, surrounding plots, and their transaction information.

[0040] The technical effects of this invention are undeniable. This invention combines multi-source data to quantify the economic and potential value of land, and tracks in real time the impact of policy adjustments and market fluctuations on land value; providing a scientific basis for land acquisition, transfer, and development sequence planning. Attached Figure Description

[0041] Figure 1 This is a flowchart of the method. Detailed Implementation

[0042] The present invention will be further described below with reference to embodiments, but it should not be construed that the scope of the present invention is limited to the following embodiments. Various substitutions and modifications made based on ordinary technical knowledge and common practices in the art without departing from the above-described technical concept of the present invention should be included within the scope of protection of the present invention.

[0043] Example 1:

[0044] See Figure 1 A smart algorithm for assessing target land prices based on market land prices includes the following steps:

[0045] 1) Obtain data on the target land parcel, including basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data;

[0046] 2) Based on the target plot data, use GIS tools to delineate the area surrounding the target plot, and then filter out similar land with the same use and planned land use nature as the target plot within the determined area.

[0047] 3) Calculate the average unit price of similar land; the average unit price equals the total price divided by the total gross floor area;

[0048] 4) Adjust the average unit price based on land use and planning indicators;

[0049] 5) Based on the adjusted average unit price and the area of ​​the target plot, the land price of the target plot is obtained and visualized.

[0050] The basic attribute data includes land parcel area, shape, ownership, planned use, plot ratio, building density, benchmark land price, land transfer, and land allocation data.

[0051] The market transaction data includes the historical transaction price of the land parcel, the premium rate, the auction failure rate, and the types of bidding companies.

[0052] The spatial correlation data includes rivers, mountains, highways and expressways, distances to nearby subway stations, number of schools / hospitals / commercial areas within 1km, and land accessibility index; among which, the land accessibility index refers to the total number of bus stops within a 300km radius of the land plot that can be reached without transfers by all bus routes stopping there, as a percentage of the total number of bus stops in the surveyed area.

[0053] The socio-economic data includes regional GDP growth rate, population density, industrial layout planning, and major infrastructure project implementation plans; major infrastructure projects include high-speed rail stations and industrial parks.

[0054] The policy constraint data includes building height restrictions, ecological red line boundaries, and land transfer restrictions.

[0055] Step 2), the step of delineating the area surrounding the target plot includes:

[0056] 1) Determine the administrative boundaries of the target land parcel;

[0057] 2) Delineate the area surrounding the target plot based on the preset buffer zone distance; the area surrounding the target plot shall not exceed the planning unit where the target plot is located, and shall be located on the same side of the target plot as the river, highway, or expressway.

[0058] In step 3), the average unit price of similar land parcels is shown below:

[0059]

[0060] In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i ω is the unit price of parcel i of the same type; i For weights.

[0061] The adjustment method for the average unit price is as follows:

[0062] For mixed-use residential and commercial land with rail transit stations, the average unit price will be increased by 15%.

[0063] For land designated solely for residential use, the average unit price will be increased by 10%.

[0064] For ordinary residential and commercial mixed-use land, the price will be increased by 5% based on the average unit price;

[0065] For mixed-use commercial and residential land, the average unit price will not be adjusted;

[0066] For purely commercial land, the average unit price will be reduced by 5%.

[0067] For plots with a floor area ratio greater than 3, the average unit price will be reduced by 5%. These additions and subtractions can be accumulated.

[0068] Example 2:

[0069] A smart algorithm for assessing target land prices based on market land prices includes the following steps:

[0070] 1) Obtain data on the target land parcel, including basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data;

[0071] 2) Based on the target plot data, use GIS tools to delineate the area surrounding the target plot, and then filter out similar land with the same use and planned land use nature as the target plot within the determined area.

[0072] 3) Calculate the average unit price of similar land; the average unit price equals the total price divided by the total gross floor area;

[0073] 4) Adjust the average unit price based on land use and planning indicators;

[0074] 5) Based on the adjusted average unit price and the area of ​​the target plot, the land price of the target plot is obtained and visualized.

[0075] Example 3:

[0076] A smart algorithm for assessing target land prices based on market land prices, with the same technical content as in Embodiment 2, further comprising the following basic attribute data: land area, shape, ownership, planned use, plot ratio, building density, benchmark land price, land transfer, and land allocation data.

[0077] The market transaction data includes the historical transaction price of the land parcel, the premium rate, the auction failure rate, and the types of bidding companies.

[0078] Example 4:

[0079] A smart algorithm for assessing target land prices based on market land prices, with technical content the same as any one of embodiments 2-3. Further, the spatial correlation data includes rivers, mountains, highway and expressway divisions, distances to nearby subway stations, number of schools / hospitals / commercial districts within 1km, and land accessibility index; wherein, the land accessibility index refers to the percentage of the total number of bus stops within a 300km radius of the land plot that can be reached without transfers by all bus routes stopping at them.

[0080] Example 5:

[0081] A smart algorithm for assessing target land prices based on market land prices, with technical content the same as any one of embodiments 2-4. Further, the socio-economic data includes regional GDP growth rate, population density, industrial layout planning, and major infrastructure project implementation plans; major infrastructure projects include high-speed rail stations and industrial parks.

[0082] Example 6:

[0083] A smart algorithm for assessing target land prices based on market land prices, with technical content the same as any one of embodiments 2-5. Furthermore, the policy constraint data includes building height restrictions, ecological red line ranges, and land transfer restrictions.

[0084] Example 7:

[0085] A smart algorithm for assessing target land prices based on market land prices, with technical content identical to any one of embodiments 2-6, further comprising, in step 2), delineating the area surrounding the target land parcel, including:

[0086] 1) Determine the administrative boundaries of the target land parcel;

[0087] 2) Delineate the area surrounding the target plot based on the preset buffer zone distance; the area surrounding the target plot shall not exceed the planning unit where the target plot is located, and shall be located on the same side of the target plot as the river, highway, or expressway.

[0088] Example 8:

[0089] A smart algorithm for assessing target land prices based on market land prices, with technical content identical to any one of embodiments 2-7, further comprising the following step 3): The average unit price of similar land parcels is as follows:

[0090]

[0091] In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i This is the unit price for parcel i of the same type.

[0092] Example 9:

[0093] A smart algorithm for assessing target land prices based on market land prices, with technical content identical to any one of embodiments 2-8, further comprising the following adjustment method for adjusting the average unit price:

[0094] For mixed-use residential and commercial land with rail transit stations, the average unit price will be increased by 15%.

[0095] For land designated solely for residential use, the average unit price will be increased by 10%.

[0096] For ordinary residential and commercial mixed-use land, the price will be increased by 5% based on the average unit price;

[0097] For mixed-use commercial and residential land, the average unit price will not be adjusted;

[0098] For purely commercial land, the average unit price will be reduced by 5%.

[0099] For plots with a floor area ratio greater than 3, the average unit price will be reduced by 5%.

[0100] Example 10:

[0101] A system based on the aforementioned intelligent algorithm includes a data acquisition module, a similar land parcel evaluation module, an average unit price calculation module, an average unit price adjustment module, a land price evaluation module, and a visualization module.

[0102] The data acquisition module acquires target land parcel data, including basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data.

[0103] The similar land parcel assessment module uses GIS tools to delineate the surrounding area of ​​the target land parcel based on the target land parcel data, and filters out similar land parcels with similar uses, properties and planning indicators to the target land parcel within the determined surrounding area.

[0104] The average unit price calculation module calculates the average unit price of similar land.

[0105] The average unit price adjustment module adjusts the average unit price based on land use, planning indicators, and location advantages;

[0106] The land price assessment module calculates the land price of the target plot based on the adjusted average unit price and the area of ​​the target plot.

[0107] The visualization module generates reports containing data and charts, and uses GIS tools or visualization libraries to generate maps that display the target plot, surrounding plots, and their transaction information.

[0108] Example 11:

[0109] A system based on the aforementioned intelligent algorithm, with the same technical content as Embodiment 10, further includes the following basic attribute data: land area, shape, ownership, planned use, plot ratio, building density, benchmark land price, land transfer, and land allocation data.

[0110] The market transaction data includes the historical transaction price of the land parcel, the premium rate, the auction failure rate, and the types of bidding companies.

[0111] Example 12:

[0112] A system based on the aforementioned intelligent algorithm, with technical content the same as in embodiments 10-11, further comprising the following spatial association data: rivers, mountains, highway and expressway divisions, distances to nearby subway stations, number of schools / hospitals / commercial districts within 1km, and land accessibility index; wherein, the land accessibility index refers to the percentage of the total number of bus stops within a 300km radius of the land plot that can be reached without transfers by all bus routes stopping at the bus stops within walking distance of the land plot, representing the total number of bus stops in the surveyed area.

[0113] Example 13:

[0114] A system based on the aforementioned intelligent algorithm, with the same technical content as embodiments 10-12, further comprising the following: the socio-economic data includes regional GDP growth rate, population density, industrial layout planning, and major infrastructure project implementation plans; major infrastructure projects include high-speed rail stations and industrial parks.

[0115] Example 14:

[0116] A system based on the aforementioned intelligent algorithm, with the same technical content as embodiments 10-13, further comprising the following policy constraint data: building height restrictions, ecological red line scope, and land transfer restrictions.

[0117] Example 15:

[0118] A system based on the aforementioned intelligent algorithm, with the same technical content as embodiments 10-14, further includes the step of delineating the area surrounding the target plot, comprising:

[0119] 1) Determine the administrative boundaries of the target land parcel;

[0120] 2) Delineate the area surrounding the target plot based on the preset buffer zone distance; the area surrounding the target plot shall not exceed the planning unit where the target plot is located, and shall be located on the same side of the target plot as the river, highway, or expressway.

[0121] Example 16:

[0122] A system based on the aforementioned intelligent algorithm, with technical content the same as in embodiments 10-15, further showing the average unit price of similar land parcels as follows:

[0123]

[0124] In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i This represents the unit price of parcel i of the same type.

[0125] Example 17:

[0126] A system based on the aforementioned intelligent algorithm, with technical content the same as in embodiments 10-16, further showing the average unit price of similar land parcels as follows:

[0127]

[0128] In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i ω is the unit price of parcel i of the same type; i For weights.

[0129] Example 18:

[0130] A system based on the aforementioned intelligent algorithm, with the same technical content as embodiments 10-17, further includes the following adjustment method for adjusting the average unit price:

[0131] For mixed-use residential and commercial land with rail transit stations, the average unit price will be increased by 15%.

[0132] For land designated solely for residential use, the average unit price will be increased by 10%.

[0133] For ordinary residential and commercial mixed-use land, the price will be increased by 5% based on the average unit price;

[0134] For mixed-use commercial and residential land, the average unit price will not be adjusted;

[0135] For purely commercial land, the average unit price will be reduced by 5%.

[0136] For plots with a floor area ratio greater than 3, the average unit price will be reduced by 5%.

[0137] Example 19:

[0138] A smart algorithm for assessing target land prices based on market land prices is described below:

[0139] 1. Data System Construction

[0140] Data types: basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data.

[0141] 1.1 Basic attribute data: detailed planning plot area, shape, ownership, planned use (residential / commercial / industrial), plot ratio, building density, benchmark land price, land supply, etc.

[0142] 1.2 Market transaction data: historical transaction prices, premium rates, auction failure rates, and types of bidding companies.

[0143] 1.3 Spatial correlation data: rivers, mountains, highways and expressways, distance to nearby subway stations (meters), number of schools / hospitals / commercial districts within 1km, and land accessibility index.

[0144] 1.4 Socioeconomic data: regional GDP growth rate, population density, industrial layout planning, and implementation plans for major infrastructure projects (such as high-speed rail stations and industrial parks).

[0145] 1.5 Policy Constraint Data: Height Restrictions, Ecological Red Line Scope, and Land Transfer Restrictions.

[0146] 2. Data Model Parameter Input Settings

[0147] 2.1 Area division: administrative boundaries (such as streets, districts), natural or transportation elements (such as rivers, roads), planning units (units, blocks), surrounding buffer distance (different distances can be set, such as 500 meters, 1 kilometer), buffer zone distance: used for the search range of surrounding plots.

[0148] 2.2 Earliest land transfer time: Filter transaction data within the last n years.

[0149] 3. Model data output results.

[0150] 3.1 Data generation: Estimated unit price (RMB / square meter) and estimated total price (RMB) of the target land parcel.

[0151] 3.2 Map Display: Location of the target plot, distribution of similar plots in the surrounding area, transaction time and unit price of each plot.

[0152] 4. Calculation process

[0153] 4.1 District Division

[0154] Based on the chosen strategy (such as buffer distance), use GIS tools to delineate the area surrounding the target parcel. Ensure that the selected area contains sufficient similar parcels for assessment.

[0155] 4.2 Screening similar land parcels

[0156] Within the defined area, select land parcels with similar uses and characteristics to the target plot. The selection criteria can be further refined based on planning indicators (such as plot ratio and building height).

[0157] 4.3 Calculate the average unit price

[0158] Arithmetic mean: Add up the unit prices of all similar land parcels and divide by the quantity.

[0159] Weighted average: The average value is calculated by weighting the land parcel area or other factors to obtain a more accurate average value.

[0160] 4.4 Data Adjustment

[0161] The average unit price was adjusted taking into account factors such as land use, planning indicators, and location advantages.

[0162] 4.5 Estimate the price of the target land parcel

[0163] Multiply the calculated average unit price by the area of ​​the target plot to obtain the total price assessment value.

[0164] 4.6 Results Output and Display

[0165] Generate reports containing data and charts. Use GIS tools or visualization libraries to generate maps that display the target plot, surrounding plots, and their transaction information.

Claims

1. An intelligent algorithm for assessing target land prices based on market land prices, characterized in that, Includes the following steps: 1) Obtain data on the target land parcel, including basic attribute data, market transaction data, spatial correlation data, socio-economic data, and policy constraint data; 2) Based on the target plot data, use GIS tools to delineate the area surrounding the target plot, and then filter out similar land with the same use and planned land use nature as the target plot within the determined area. 3) Calculate the average unit price of similar land; the average unit price equals the total price divided by the total gross floor area; 4) Adjust the average unit price based on land use and planning indicators; 5) Based on the adjusted average unit price and the area of ​​the target plot, the land price of the target plot is obtained and visualized.

2. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, The basic attribute data includes land parcel area, shape, ownership, planned use, plot ratio, building density, benchmark land price, land transfer, and land allocation data. The market transaction data includes the historical transaction price of the land parcel, the premium rate, the auction failure rate, and the types of bidding companies.

3. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, The spatial correlation data includes rivers, mountains, highways and expressways, distances to nearby subway stations, number of schools / hospitals / commercial areas within 1km, and land accessibility index; among which, the land accessibility index refers to the total number of bus stops within a 300km radius of the land plot that can be reached without transfers by all bus routes stopping there, as a percentage of the total number of bus stops in the surveyed area.

4. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, The socio-economic data includes regional GDP growth rate, population density, industrial layout planning, and major infrastructure project implementation plans; major infrastructure projects include high-speed rail stations and industrial parks.

5. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, The policy constraint data includes building height restrictions, ecological red line boundaries, and land transfer restrictions.

6. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, Step 2), the step of delineating the area surrounding the target plot includes: 1) Determine the administrative boundaries of the target land parcel; 2) Delineate the area surrounding the target plot based on the preset buffer zone distance; the area surrounding the target plot shall not exceed the planning unit where the target plot is located, and shall be located on the same side of the target plot as the river, highway, or expressway.

7. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, In step 3), the average unit price of similar land parcels is shown below: In the formula, n represents the number of parcels of the same type; P represents the average unit price of similar land parcels; i ω is the unit price of parcel i of the same type; i For weights.

8. The intelligent algorithm for assessing target land prices based on market land prices according to claim 1, characterized in that, The adjustment method for the average unit price is as follows: For mixed-use residential and commercial land with rail transit stations, the average unit price will be increased by 15%. For land designated solely for residential use, the average unit price will be increased by 10%. For ordinary residential and commercial mixed-use land, the price will be increased by 5% based on the average unit price; For mixed-use commercial and residential land, the average unit price will not be adjusted; For purely commercial land, the average unit price will be reduced by 5%. For plots with a floor area ratio greater than 3, the average unit price will be reduced by 5%.

9. A system based on the intelligent algorithm according to any one of claims 1-8, characterized in that: It includes a data acquisition module, a similar land parcel evaluation module, an average unit price calculation module, an average unit price adjustment module, a land price evaluation module, and a visualization module; The data acquisition module acquires data of the target land parcel; The similar land parcel assessment module uses GIS tools to delineate the surrounding area of ​​the target land parcel based on the target land parcel data, and filters out similar land parcels with similar uses, properties and planning indicators to the target land parcel within the determined surrounding area. The average unit price calculation module calculates the average unit price of similar land. The average unit price adjustment module adjusts the average unit price based on land use, planning indicators, and location advantages; The land price assessment module calculates the land price of the target plot based on the adjusted average unit price and the area of ​​the target plot. The visualization module generates reports containing data and charts, and uses GIS tools or visualization libraries to generate maps that display the target plot, surrounding plots, and their transaction information.

Images