← Publications
journal2026SJR Q1

Improving Access to Building Licensing Information in Australia: Design and Development of a Graph-Based Retrieval-Augmented Generation (RAG) Artificial Intelligence (AI) System

Diya Yan, Jiate Liu, Bocheng Han, Zhengyi Yang, Jun He, Jirong Xu, Riza Yosia Sunindijo, Cynthia Changxin Wang

Buildings

RAIDS Lab Authors

Zhengyi Yang
Zhengyi Yang
Director

Details

Year
2026
Venue
Buildings
Publisher
Multidisciplinary Digital Publishing Institute (MDPI)
Rankings
SJR Q1

Research Area

Data for Real-World Applications

Tags

ConstructionApplicationRAG

Resources

PDF ↗DOI ↗

Abstract

Digital technologies have been widely adopted to improve efficiency, transparency, and decision making in the construction industry. However, regulatory processes such as building license and registration applications remain complex, fragmented, and difficult for applicants to navigate, particularly for early career practitioners and small businesses. This study presents the design and development of a graph-based retrieval-augmented generation (RAG) artificial intelligence (AI) system that assists users in applying for building licenses and registrations in Australia. By integrating eight regulatory burden frameworks, this study identified ten categories of licensing-related burden. A three-layer system architecture was subsequently proposed for the Australian construction licensing context, and a prototype is implemented using the New South Wales (NSW) regulatory framework. The system provides context-aware responses, step-by-step guidance, and tailored information based on user queries, thereby reducing regulatory burden for individuals, companies, and industry bodies. Prototype evaluation against general-purpose AI tools indicates improved information accessibility and reduced application-related friction in representative licensing scenarios. This study sheds light on AI-enabled regulatory support systems and demonstrates how graph-based RAG could improve accessibility and usability of construction related licensing processes. The findings have implications for policymakers, regulators, and researchers seeking to leverage AI to support digital transformation in the construction industry.

Author Affiliations

Diya Yan
University of New South Wales
Jiate Liu
University of New South Wales
Bocheng Han
University of New South Wales
Zhengyi Yang
University of New South Wales
Jun He
Arcova Pty. Ltd.
Jirong Xu
Jorico Training Pty. Ltd.
Riza Yosia Sunindijo
University of New South Wales
Cynthia Changxin Wang
University of New South Wales

BibTeX

@article{yan2026improving,
  title = {Improving Access to Building Licensing Information in Australia: Design and Development of a Graph-Based Retrieval-Augmented Generation (RAG) Artificial Intelligence (AI) System},
  author = {Yan, Diya and Liu, Jiate and Han, Bocheng and Yang, Zhengyi and He, Jun and Xu, Jirong and Sunindijo, Riza Yosia and Wang, Cynthia Changxin},
  volume = {16},
  issn = {2075-5309},
  url = {http://dx.doi.org/10.3390/buildings16061224},
  doi = {10.3390/buildings16061224},
  number = {6},
  journal = {Buildings},
  publisher = {MDPI AG},
  year = {2026},
  month = Mar,
  pages = {1224}
}