Digital Designer: Emulation of Empathy-Driven Design with Generative AI

Design is critical in creating impactful systems, especially in domains like IoT applications where user needs are complex and dynamic. Traditional design thinking methods focus on empathy and creativity, essential for designing adaptive systems. However, capturing nuanced user requirements and generating creative solutions can be costly and time-consuming. This work explores the role of AI, specifically Large Language Models (LLMs) and diffusion models, in enhancing design thinking by generating inclusive user needs and creating innovative design solutions. We present a method for leveraging LLMs to understand and interpret user requirements, which then inform generative design processes through a diffusion model. We demonstrate this approach through case studies of adaptive assistive devices, showing how this AI-driven design process enhances both creativity and empathy. Our results show significant improvements in both design quality (PDS scores: 4.75 vs 2.75) and creativity (CPSS scores: 4.0 vs 1.75), suggesting that emulating the design thinking process when generating solutions with AI enables smarter and more empathetic design solutions.