A cosmetic packaging design method based on online reviews

To address the transformation of user experience and packaging iteration in cosmetics due to the diversification of usage scenarios and demands, this study capitalizes on the advancements in artificial intelligence across user analysis, data analysis, and generative design domains, and proposes a cosmetic packaging design approach centered around online reviews. In this study, 124,879 pieces of user review data were collected from JingDong (JD), a Chinese e-commerce platform, using Python programming technology. Five topics are clustered through the application of the Latent Dirichlet Allocation (LDA) topic model. By integrating the coding of Grounded Theory, 18 demand elements within six core categories are summarized. The Kano model and the Analytic Hierarchy Process (AHP) are employed to classify and rank these demands. Notably, aspects such as strong brand recognition (M1, 0.2182), strong brand value perception (M5, 0.1129), and visually appealing and refined aesthetics (A5, 0.0983) exhibit relatively high weights. Subsequently, six lipstick packaging design schemes are developed by combining traditional software with the MidJourney generative artificial intelligence tool. Through comprehensive evaluation using the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method, the optimal Scheme c is identified and further optimized. This study constructs a comprehensive design strategy with user online reviews at its core, encompassing data collection, analysis, scheme design, artificial intelligence (AI)-assisted design, and evaluation. It is recommended that the application of artificial intelligence (AI)-assisted design be significantly enhanced throughout the entire design process, enabling precise and rapid generation of design schemes, streamlining the process, and shortening the development cycle.