A home design method based on deep neural network

A deep neural network and home design technology, applied in the field of deep learning, can solve problems such as design styles that cannot be learned, and achieve a more intelligent effect

Active Publication Date: 2018-12-11
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a home furnishing design method based on a deep neural network in view of the technica

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 home design method based on deep neural network
  • A home design method based on deep neural network
  • A home design method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A home design method based on a deep neural network. Firstly, a sequential structure home prediction model based on dependency features is proposed, and the model is designed and used to extract the structural features between home characters and learn the prediction of the order placement sequence. The specific implementation steps are as follows:

[0042] Step 1. Labeling of household datasets and collation of datasets

[0043]The home design display is collected from professional website home design drawings and home floor plans. The standard used in the pictures is that the space is relatively complete and the home display meets the medium-sized house specifications. The homes involved are marked, and the choice of home labeling tends to be volume. Objects that are relatively large and individually independent, use English words to indicate the category of objects, and household objects are placed around the wall for a week, and the order of these household furnishi...

Embodiment 2

[0060] A home design method based on a deep neural network, which further introduces parameter constraints that limit the relative size of home objects, and builds a two-way layered home prediction model. In the prediction stage, cluster search is used to screen parameters, and the scheme design of the home sequence is completed. The model flow is as follows: figure 2 shown. The specific implementation steps are as follows:

[0061] Step 1: Construction of a hierarchical phrase-level household data set

[0062] Add a number after each home character, that is, the size of the number indicates the size of the home. Here it indicates the length of the wall relative to it. For each type of home, set several different sizes that are commonly used; Next To construct a hierarchical input and output pair, due to the introduction of size parameters, each wall needs to be predicted separately, and a pair of input and output sequence pairs in a non-sequential structure constitutes a c...

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 relates to a home design method based on a deep neural network, belonging to the technical field of the deep neural network and the home design. At first, the household design display iscollected to mark the household, and then the serial data is generated based on the labeled household placement sequence. Secondly, the prediction model of home furnishings is designed. Based on theprediction model, the structural features between characters of furniture are extracted, the sequence data are learned and the order of home furnishings is predicted. Based on the parameter constraintof the relative size of household objects, a bi-directional hierarchical household prediction model is designed, and then hierarchical recursive multi-round prediction is carried out, so that the multi-round prediction results are more in line with the actual situation of household design. Finally, according to the requirements of different design styles in practical application, the home forecasting model is designed for specific style. The method utilizes a three-dimensional engine to perform three-dimensional household scene rendering, and intuitively proves the effectiveness of the modeland the style learning advantage in a three-dimensional manner.

Description

technical field [0001] The invention relates to a home design method based on a deep neural network, which belongs to the technical field of deep learning. Background technique [0002] Deep Neural Network (DNN) is the foundation of many modern AI applications. Different from traditional machine learning algorithms, it can learn features from data autonomously. This process does not require human intervention, is more intelligent, and is more in line with the mechanism of human perception of the world. In addition, in many fields, the accuracy of DNN has surpassed that of human beings. As a parent class, DNN contains four main algorithms: convolutional neural network, deep stack autoencoder network, recurrent neural network, and generative confrontational network. The internet. Among them, the convolutional neural network is deepened in space, and the recurrent neural network is deepened in time. [0003] Recurrent Neural Network (RNN) is mainly used in natural language p...

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): G06F17/50G06N3/04G06N3/08
CPCG06N3/08G06F2111/08G06F30/13G06N3/044G06N3/045
Inventor 陈宇峰李博吴丹霍盼盼陶泽綦白学营
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap