Gen-Diaolou: An Integrated AI-Assisted Interactive System for Diachronic Understanding and Preservation of the Kaiping Diaolou

TL;DR

Kaiping Diaolou faces authenticity and engagement challenges in heritage preservation. The authors introduce Gen-Diaolou, an integrated AI-assisted system with a Knowledge Module and a GenAI Module to foster diachronic understanding and preservation awareness, evaluated through a formative study, a pilot, and a museum field study. Results show improved factual learning and, notably, enhanced conceptual understanding and preservation-oriented attitudes when GenAI is used, with strong evidence of user engagement and low workload. The work contributes design principles and an architectural framework for AI-assisted cultural heritage learning and co-creation, offering practical guidance for scalable, authentic, and participatory digital heritage experiences. It advances human–AI collaboration in CH by shifting learners toward active interpretation, exploration, and stewardship across museum and site contexts.

Abstract

The Kaiping Diaolou and Villages, a UNESCO World Heritage Site, exemplify hybrid Chinese and Western architecture shaped by migration culture. However, architectural heritage engagement often faces authenticity debates, resource constraints, and limited participatory approaches. This research explores current challenges of leveraging Artificial Intelligence (AI) for architectural heritage, and how AI-assisted interactive systems can foster cultural heritage understanding and preservation awareness. We conducted a formative study (N=14) to uncover empirical insights from heritage stakeholders that inform design. These insights informed the design of Gen-Diaolou, an integrated AI-assisted interactive system that supports heritage understanding and preservation. A pilot study (N=18) and a museum field study (N=26) provided converging evidence suggesting that Gen-Diaolou may support visitors' diachronic understanding and preservation awareness, and together informed design implications for future human-AI collaborative systems for digital cultural heritage engagement. More broadly, this work bridges the research gap between passive heritage systems and unconstrained creative tools in the HCI domain.

Figures (14)

• Figure 1: Examples of representative Kaiping Diaolou sites included in our data collection.
• Figure 2: Co-design workshop procedure. The session included Phase 1, Introduction (20 minutes), and Phase 2, Co-design (70 minutes). Participants engaged in two tasks: Task 1, AI-assisted Image Generation and Reflection; and Task 2, Prototype Iteration and Ideation.
• Figure 3: UI of the Gen-Diaolou Knowledge Module.
• Figure 4: UI of the Gen-Diaolou GenAI Module: (i) presets and effects, (ii) an idea-to-prompt converter with LLM scaffolding, and (iii) a canvas with refine and save controls.
• Figure 5: Detailed example of the authenticity guardrails workflow for Historical Reconstruction in the GenAI Module.