Intelligent design method of customized furniture based on modular theory and artificial intelligence

Abstract

This study explores the intelligent design method of customized furniture based on modular theory and artificial intelligence technology, aiming to improve design efficiency and customer satisfaction. The research focuses on how to optimize the customized furniture design process through modular design and artificial intelligence technology, achieving a balance between personalization and cost-effectiveness. The research methods involve building modular design processes, utilizing artificial intelligence to assist in module selection and combination optimization, and applying augmented reality technology in design. The results showed that the proposed model performed the best on the training set, with an accuracy of 92%, a precision of 88%, a recall of 90%, an F1 score of 89%, an area under the curve ratio of 95%, and a logarithmic loss of 0.21. The corresponding values on the validation set decreased to 89%, 85%, 86%, 85%, and 93%, while the logarithmic loss increased to 0.28. In addition, in the performance comparison, the structural similarity index value of the model increased from 0.350 to 0.912, and the peak signal-to-noise ratio increased from 13.542 decibels to 22.759 decibels, demonstrating good performance. These evaluation metrics (accuracy, precision, recall, and F1 score) were used to assess the classification performance of the AI model in selecting optimal module combinations and generating rendered design schemes that best match user preferences. The proposed approach, named Modular Customized Furniture Intelligent Design System (MoCFIDS), integrates modular theory with AI-assisted module optimization and augmented reality for design validation. Comparative experiments with state-of-the-art models such as CycleGAN and MUNIT showed that MoCFIDS significantly outperformed them in terms of SSIM, PSNR, and computational efficiency, highlighting its superior capability in producing high-quality, user-preferred furniture designs. The research significance lies in the fact that the modular intelligent design method for customized furniture has improved the efficiency and quality of customized furniture design, delivering more personalized and cost-effective design outcomes.