Target Mining and Recognition of Product Form Innovation Design Based on Image Word Similarity Model

Abstract

Product Kansei image design is one of the research hotspot of product emotional design. Due to the subjectivity, low efficiency, and low level of intelligence in the existing product form innovation design methods in the mining of design goals. This study combines the semantic dictionary of Tongyici Cilin with Kansei engineering theory and uses clustering analysis algorithm, semantic difference method, and word similarity calculation method to realize product Kansei image design. Tongyici Cilin is a computable Chinese semantic dictionary. In this study, we innovatively introduced Tongyici Cilin into the image word similarity calculation in product image design. First, the product image design process based on Tongyici Cilin is proposed. Then, we establish a model of image word similarity calculation using the common distance, difference distance, common adjustment parameter, and differential adjustment parameter. By comparing with international standard data, it is confirmed that the image word similarity calculation model proposed in this article is effective and efficient. Using the sedan image design of middle-aged, middle-income men as an example, the sedan form style of each target image was successfully derived from the Internet-based questionnaire. Based on the case studies, we determined that it is effective to use the Tongyici Cilin semantic dictionary to determine the target image and improve the efficiency of product image design.