Real estate dynamic valuation method and device

Abstract

The invention discloses a real estate dynamic valuation method and device, and the method comprises the steps of obtaining the prisoner information of a to-be-valuated real estate, and the prisoner information at least comprises the information of a position region where the to-be-valuated real estate is located; inputting the prisoner information of the to-be-estimated real estate into a long-short-term memory network model which is obtained through machine learning training in advance and is used for predicting the real estate unit price mean value change condition in the location area where the to-be-estimated real estate is located, and outputting real estate unit price mean value change data in the location area where the to-be-estimated real estate is located; inputting the real estate unit price mean value change data of the location area of the to-be-estimated real estate and the prisoner information of the to-be-estimated real estate into an extreme gradient rising network model which is obtained through machine learning training in advance and is used for predicting the change condition of the total price of the real estate in the location area of the to-be-estimated real estate; and outputting a dynamic assessment result of the value of the to-be-assessed real estate imprisoned product. According to the invention, dynamic evaluation of the value of the real estate pledge can be realized.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a real estate dynamic valuation method and device. Background technique [0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] As we all know, the inclusive financial services provided by major banks are to give customers a certain credit line based on the valuation of the customer's real estate mortgage. However, bank practitioners cannot accurately grasp important data and information such as real estate valuations. Most bank practitioners use on-site surveys by account managers and hire third-party evaluation agencies to conduct real estate mortgage valuations. However, these methods have problems such as low efficiency and additional expenses, which greatly increase the bank's operating ...

AI Technical Summary

Problems solved by technology

[0005] An embodiment of the present invention provides a real estate dynamic valuation method to solve the technical problem that the existing real estate collateral value evaluation system cannot dynamically evaluate the real estate collateral value. The method includes: obtaining the collateral of the real estate to be valued Information, wherein the collateral information at least includes: information on the location of the real estate to be valued; input the collateral information of the real estate to be valued into the long-term short-term memory network model, and output the real estate in the location of the real estate to be valued The change data of the average unit price, wherein the long-short-term memory network model is a model that predicts the change of the average unit price of real estate in the area where the real estate to be valued is located; the change in the average unit price of the real estate in the area where the real estate to be valued is The data and the collateral information of the real estate to be valued are input into the trained extreme gradient ascent network model, and the dynamic evaluation results of the collateral value of the real estate to be valued are output. The extreme gradient ascent network model is obtained through machine learning training in advance A model for predicting the change of the total real estate price in the area where the real estate to be valued is located

[0006] The embodiment of the present invention also provides a real estate dynamic valuation device to solve the technical problem that the existing real estate collateral value evaluation system cannot dynamically evaluate the real estate collateral value. The device includes: a real estate information acquisition module to be valued , used to obtain the collateral information of the real estate to be valued, wherein the collateral information at least includes: the location area information of the real estate to be valued; the unit price prediction module, used to input the collateral information of the real estate to be valued into In the long-term and short-term memory network model, the data of the average value change of the real estate unit price in the area where the real estate to be valued is located is output. The model of the situation; the dynamic valuation module, which is used to input the data of the average value change data of the real estate unit price in the area where the real estate to be valued is located and the collateral information of the real estate to be valued into the trained extreme gradient ascent network model, and output the The results of the dynamic evaluation of the collateral value of the value real estate, in which the extreme gradient ascent network model is a model obtained through machine learning training in advance to predict the change of the total real estate price in the area where the real estate to be valued is located

[0007] The embodiment of the present invention also provides a computer device to solve the technical problem that the existing real estate collateral value evaluation system cannot realize the dynamic evaluation of the real estate collateral value. A computer program that can run on a processor, and realize the above-mentioned real estate dynamic valuation method when the processor executes the computer program

Images