Answers are grounded in this paper and cite their sources.
Methodological study demonstrates structured translation of visitor experience configurations into digital museum design concepts, highlighting effective human-AI collaborative service innovation.
Digital cultural services, such as museum virtual exhibitions, must create meaningful visitor experiences. However, design teams often face complex combinations of user, technological, and experiential factors. Existing analytical methods can identify these conditions, but do not easily interpret them into design solutions. This study aims to develop a structured Human–AI collaborative framework that converts configurational insights into service innovation concepts for digital museum exhibitions. This study introduces a novel Hybrid Human–LLM framework that integrates fuzzy-set Qualitative Comparative Analysis (fsQCA), TRIZ inventive principles, and Large Language Models (LLMs) with Human-in-the-Loop validation for cultural service design. The four-stage process begins with fsQCA identifying configurational pathways to high perceived visitor impact. LLM-assisted reasoning then translates these configurations into TRIZ technical contradictions, followed by TRIZ-based concept generation. Finally, expert evaluation validates the proposed designs. Key findings include: (1) fsQCA revealed two pathways to high impact, including a compensatory pathway requiring neither advanced technology nor high social interaction; (2) LLMs effectively interpreted configurations as contradictions between information richness and cognitive effort; (3) four service concepts emerged – Adaptive Narrative Pods, Emotive Texture Overlay, Guided Audio Journeys, and Reflective Exit Synthesis; and (4) expert validation confirmed their configurational relevance, feasibility, and cultural value.
No takes yet. Share an insight, caveat, or question.
Gilani et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: