A furniture layout method and system based on piecewise reinforcement learning technology

Abstract

The invention discloses a furniture layout method based on a piece-by-piece reinforcement learning technology, which includes a furniture layout environment building step, a furniture layout reinforcement learning training step, and a furniture layout generation step using reinforcement learning. First, use artificial technology to evaluate and score specific furniture layout plans, and perform feature extraction processing on these data; secondly, use neural network algorithm to perform regression learning, and use the trained neural network to simulate the designer's score; then for a specific state Space and behavioral action space use reinforcement learning technology to learn according to the feedback of the environment; finally, use the trained reinforcement learning model to lay out specific furniture in actual use. The method of the invention has strong applicability in the implementation process, realizes the automation of furniture layout, reduces the design cost, and greatly improves the design efficiency.

Description

technical field [0001] The present invention relates to reinforcement learning technology, in particular to a furniture layout method based on piecewise reinforcement learning technology. Background technique [0002] At present, reinforcement learning technology has been widely used in high-dimensional control problems (such as robots, etc.), industrial automation, and finance. In the home decoration industry, the effect of furniture layout depends heavily on the designer. Designers are roughly divided into two categories, one is ordinary designers and the other is professional designers. In order to satisfy customers, ordinary designers often need a lot of time to design drawings, occupying a lot of designer resources, and professional designers. Designer design drawings often require high prices and do not have universal applicability. [0003] With the in-depth development of the real estate industry, the home decoration industry has also achieved great development, an...

AI Technical Summary

Problems solved by technology

Designers are roughly divided into two categories, one is ordinary designers, and the other is professional designers. In order to satisfy customers, ordinary designers often need a lot of time to design drawings, which takes up a lot of designer resources, while professional designers Designer design drawings often require high prices and do not have universal applicability

Images