Big Data and AI-Driven Product Design: A Survey

Abstract

As living standards improve, modern products need to meet increasingly diversified and personalized user requirements. Traditional product design methods fall short due to their strong subjectivity, limited survey scope, lack of real-time data, and poor visual display. However, recent progress in big data and artificial intelligence (AI) are bringing a transformative big data and AI-driven product design methodology with a significant impact on many industries. Big data in the product lifecycle contains valuable information, such as customer preferences, market demands, product evaluation, and visual display: online product reviews reflect customer evaluations and requirements, while product images contain shape, color, and texture information that can inspire designers to quickly generate initial design schemes or even new product images. This survey provides a comprehensive review of big data and AI-driven product design, focusing on how big data of various modalities can be processed, analyzed, and exploited to aid product design using AI algorithms. It identifies the limitations of traditional product design methods and shows how textual, image, audio, and video data in product design cycles can be utilized to achieve much more intelligent product design. We finally discuss the major deficiencies of existing data-driven product design studies and outline promising future research directions and opportunities, aiming to draw increasing attention to modern AI-driven product design.

The Integration of Kansei Engineering and Kano Model on Natural Language Processing (NLP) to Support Development of Service Product in the Borobudur Temple Tourism

“…Several studies have been conducted using numerous methods, including naïve bayes, to understand people needs based on their social media activities, complaints, or reviews [14], [15], [16], [17], neural network [15], [18], Natural Language Processing (NLP) [19], [20], [21], [22], [23], [24], multimodal analysis [25], machine learning [26], [27] or combination of some methodologies [28]. The results showed that the availability of textual reviews was beneficial, providing better data acquisition, less time-consuming, and guaranteeing data authenticity [29]. Due to the high number of reviews, this study proposed text mining by integrating NLP as a tool to convert everyday language into a format understood by machines.…”

“…Although models showed the ability to improve product, there is a need to understand new visitors' voices to ensure the relevance of newly developed product. Kano model in product development could classify five costumer's needs and requirements, including must-be, one-dimensional, attractive, indifferent, and reverse [29]. According to Chen et al [34], Kano model could help decision-makers understand the relationship between customer satisfaction with product attributes, as stated by Bi et al [35], Gan et al [36], Lai et al [37], Liu et al [38], Avikal et al [39], and Asian et al [40].…”

Exploring the Dual Potential of Artificial Intelligence-Generated Content in the Esthetic Reproduction and Sustainable Innovative Design of Ming-Style Furniture

“…By simulating the human creative process, AIGC can autonomously generate artistic works in various forms, including music, text, and images [2]. The evolution of this technology not only provides artists and designers with new creative tools but also offers new possibilities for the preservation and innovation of traditional cultures [3,4].…”