Key points are not available for this paper at this time.
This study proposes an AI-based product packaging design method, utilising Artificial Intelligence Generated Content (AIGC) to improve packaging design efficiency, with empirical analysis conducted on jasmine tea packaging design. Firstly, the study collects user reviews related to packaging from e-commerce platforms through Python web scraping, aiming to uncover potential user needs. Next, the Biterm Topic Model (BTM) is employed to analyse the collected textual data, identifying key demands in packaging design. The Hierarchical Analysis Process (AHP) is then applied to classify and prioritise these demands, clarifying the core needs. Subsequently, ChatGPT is utilised to transform the key requirements into design language suitable for the Midjourney platform, automatically generating creative packaging design proposals, thereby enhancing design efficiency and ensuring the proposals better meet user needs. To further optimise the designs, the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method is applied for comprehensive evaluation, selecting the optimal design, and optimisation is performed through computer-aided design techniques. The results indicate that this method effectively integrates big data analysis, generative artificial intelligence, and multi-criteria decision-making, enhancing both the efficiency and quality of packaging design, providing a new technological framework for future packaging design research.
Gao et al. (Tue,) studied this question.