House type design scheme evaluation method based on machine learning

Abstract

The invention provides a design scheme evaluation method based on machine learning. The design scheme evaluation method comprises the following steps that S1: a design scheme acquisition device acquires a batch of design schemes from a house type design scheme library to act as samples of machine learning; S2: a user inputs house type design data through a design scheme data input terminal or the user performs house type designing through an entity design terminal, and a design scheme feature extractor extracts the features suitable for training machine learning models from the house type design schemes; and S3: a control component is provided with a house type data training set storage module which is used for storing the house type model data to be trained and a verification set storage module which is used for storing house type design scheme samples. According to the house type design scheme evaluation method based on machine learning, the high-quality house type evaluation standards can be extracted from a large number of typical design schemes, and the new models are accurately prejudged and accurately compared so that artificial error can be avoided, and the house type design schemes can be automatically evaluated.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a method for evaluating house type design schemes based on machine learning. Background technique [0002] On the cloud design platform for home decoration design, many decoration design plans are uploaded to the background every day. These design plans include good ones, poor ones and even unfinished ones. How to evaluate these design schemes, especially to filter some obviously problematic schemes, the current method mainly relies on manual screening, such as checking whether the area of ​​the apartment is reasonable, whether the number of doors and windows is correct, whether the furniture is placed correctly, etc., this kind of artificial The screening method is feasible when the number of design schemes is small, but when the number of design schemes is huge, there are obvious problems of low efficiency, and the existence of personal subjective judgment factors will...

AI Technical Summary

Problems solved by technology

How to evaluate these design schemes, especially to filter some obviously problematic schemes, the current method mainly relies on manual screening, such as checking whether the area of ​​the apartment is reasonable, whether the number of doors and windows is correct, whether the furniture is placed correctly, etc., this kind of artificial The screening method is feasible when the number of design schemes is small, but when the number of design schemes is huge, there are obvious problems of low efficiency, and the existence of personal subjective judgment factors will lead to certain misjudgments;

[0003] The current method based on manual evaluation of whether the design scheme is reasonable has low efficiency and human misjudgment factors

Images