Unlock instant, AI-driven research and patent intelligence for your innovation.

House layout method and system based on twin network

A technology of twin network and layout method, applied in biological neural network model, neural learning method, geometric CAD, etc., can solve problems such as time-consuming, labor-intensive and subjective influence

Active Publication Date: 2020-06-12
江苏艾佳家居用品有限公司 +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the existing technology, the designer usually conducts manual review to judge whether the automatically generated layout meets the relevant user needs, which results in a time-consuming and laborious process and is subject to more subjective influences

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
  • House layout method and system based on twin network
  • House layout method and system based on twin network
  • House layout method and system based on twin network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The invention discloses a twin network-based house layout scorer training method. In this method, the training set is too small to fine-tune the house layout plan designed by the master, and the furniture is properly translated, rotated, scaled, and increased or decreased to obtain more training data; secondly, the data set is divided into positive and negative sets , the positive sample set is the layout scheme of the master, and the negative sample set is the fine-tuned layout scheme; finally, the characteristics of the data in different dimensions are extracted, and input into the Siamese network for training, and finally the comprehensive score of a certain scheme can be obtained.

[0036] The method of the present invention is described in detail as follows:

[0037] The first step is to fine-tune the house layout scheme designed by the master and increase the training sample set;

[0038] The house layout designed by the master in the present invention refers to ...

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 house layout scoring device training method based on a twin network. The method comprises the following steps: firstly, aiming at an excessively small training set, finely adjusting a house layout scheme designed by a master, and properly translating, rotating, zooming, increasing and decreasing furniture to obtain more training data; secondly, positive and negative set division is performed on the data set, a positive sample set is a layout scheme of a master, and a negative sample set is a layout scheme after fine adjustment; and finally, extracting features of thedata in different dimensions, and inputting the features into the twin network for training, thereby finally obtaining a comprehensive score of a certain scheme.

Description

technical field [0001] The invention relates to a twin network-based house layout scorer training method. Background technique [0002] In the process of house automatic layout, it is usually necessary to evaluate the quality of the layout results, so the house layout scorer is very important. [0003] However, in the prior art, the designer usually conducts a manual review to judge whether the automatically generated layout meets the relevant user needs, which results in a time-consuming and laborious process and is subject to more subjective influences. Contents of the invention [0004] Based on the above problems, the present invention proposes a Siamese network-based house layout scorer training method. First, in view of the small training set and the lack of negative samples, fine-tune the house layout plan designed by the master, and properly translate, rotate, scale, and increase or decrease the furniture to obtain more training data; secondly, the data set is pos...

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
IPC IPC(8): G06F30/13G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 陈旋吕成云黄书贤
Owner 江苏艾佳家居用品有限公司