A Digital and Intelligent Design Paradigm for Exhibition Space based on Knowledge Graph & Generative AI
Xinlan Yu, Linhui Hu, Tao Cheng · 2024
This paper addresses the deficiencies in traditional design methods for exhibition spaces, particularly in terms of efficiency, customization, iterative speed, and design cycles. Specifically, it highlights the issues with the emerging digitalized design methods based on Generative Artificial Intelligence (genAI), such as non-standard and unstructured input expressions, high inconsistency in output results, and low repeatability. By utilizing the Knowledge Graph (KG) to achieve accurate semantic representation and orderly contextual association, as well as structured and standardized expression, this study explores and establishes a KG-genAI-based paradigm for the digital and intelligent design of exhibition spaces (KG-genAI-PDIDES). This paradigm drives Midjourney and Stable through unstructured natural language prompting methods for the digital design of UAV exhibition spaces. Comparative analysis of the results demonstrates that the proposed KG-genAI-PDIDES significantly enhances the standardization of input expression and consistency of output results, offering a new design paradigm for the digitization of exhibition spaces.