Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method of urban residential land price evaluation based on transfer learning

A technology of transfer learning and land price, which is applied in product evaluation, instruments, data processing applications, etc., to achieve the effect of improving the accuracy of fitting, reducing fatal defects, and improving the accuracy of land price evaluation

Inactive Publication Date: 2019-01-04
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly aims at the characteristics of the urban residential land price data set, and proposes a feature extraction algorithm for urban residential land price based on transfer learning. defects to overcome

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method of urban residential land price evaluation based on transfer learning
  • A method of urban residential land price evaluation based on transfer learning
  • A method of urban residential land price evaluation based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Step 1. According to the selected research area, this patent takes Shenzhen as an example, and collects housing price and land price data of ten districts and counties in Shenzhen, mainly including coordinate information of points of interest and related attribute information; using Delphi method and main The component analysis method analyzes a wide variety of characteristic factors of residential land prices in Shenzhen, removes the characteristic factors with strong correlation and low importance, and determines the factors including urban expressways, expressways, buses, subways, middle schools, primary schools, kindergartens, and commercial services. There are 16 influencing factors that affect housing prices and land prices, such as degree of development, hospitals, density of catering outlets, density of financial service outlets, density of automobile service outlets, parks and green spaces, tourist attractions, regional planning prospects, and population density....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for evaluating urban residential land price based on transfer learning, which relates to a calming method of transfer learning and belongs to the field of asset evaluation, in particular to the field of land price classification and grading. The invention mainly aims at the characteristics of the urban residential land price data set, and proposes an algorithm forextracting the urban residential land price characteristics based on migration learning. Aiming at the shortcomings of the existing land price regression evaluation model, the classification and grading evaluation model is introduced to overcome the shortcomings of the urban residential land price data set. Firstly, the land price feature extractor is trained. Based on the house price data set, the relationship between the house price in the house price data set and its feature factors is fitted by using a Deep Belief Network (DBN). Secondly, the parameters of the trained DBN model are reserved, and the residential land price features are extracted based on the DBN model. Finally, based on the extracted land price feature set, the residential land price is classified and graded by using different land price classification and evaluation models.

Description

technical field [0001] The invention relates to a calming method for transfer learning, which belongs to the field of asset evaluation, in particular to the field of land price classification and grading. Background technique [0002] Urban residential land price evaluation is one of the important contents of land market management. Conventional residential land price evaluation methods mainly include steps such as feature selection, feature quantification, feature extraction, subject modeling, and land price evaluation. Among them, there are subjective quantification errors in the process of quantifying the characteristics of residential land prices, and the data of residential land prices have defects such as small sample size and unbalanced categories. The existing urban residential land price evaluation methods are mainly based on BP neural network and surface fitting model to fit the nonlinear relationship between residential land price and its influencing factors, igno...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06Q50/16
CPCG06Q30/0278G06Q50/16
Inventor 郑泽忠王娜刘佳玺谢晨牟范张彪李江
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products