Authors
Zhuoqun Zhang; Chunhui Zhao; D.Y. Li; Peijie Li; Yingfu Chen; Hao Zhu; Daguang Han
Journal
Buildings, 2026
DOI
10.3390/buildings16040719
Licence
CC-BY
Citations
1 (OpenAlex, 3 Aug 2026)

Key findings

  • Results: Tested on a real-world power infrastructure project, the framework was found to be 95.8% accurate in translation and 98.3% feasible in rule execution, outperforming benchmark automated approaches.
  • The human effort was reduced by 90% (168 h vs.
  • 1620 h), and processing of regulatory changes was sped up by 94%.

Abstract

Objective: This paper seeks to provide an effective and automated method for the creation and updating of building information modeling compliance rules using the integration of human-in-the-loop collaboration with advanced natural language processing. Methods: We propose a hybrid approach that integrates BERT-based semantic extraction, CFG structural validation, and confidence-based expert review. Results: Tested on a real-world power infrastructure project, the framework was found to be 95.8% accurate in translation and 98.3% feasible in rule execution, outperforming benchmark automated approaches. The human effort was reduced by 90% (168 h vs. 1620 h), and processing of regulatory changes was sped up by 94%. Conclusion: Data analysis shows that collaborative intelligence is a significant factor in closing the semantic and pragmatic gap for regulatory compliance. Compared with fully automated “black box” approaches, this method supplies a tractable, manageable, and operationally valid solution, giving a competitive edge over existing digital construction methods.

Cite this work

@article{han2026humanintheloop,
  title   = {Human-in-the-Loop Semantic Rule Base Generation and Dynamic Updating for Automated BIM Compliance Checking: A Knowledge Graph Approach},
  author  = {Zhuoqun Zhang and Chunhui Zhao and D.Y. Li and Peijie Li and Yingfu Chen and Hao Zhu and Daguang Han},
  journal = {Buildings},
  year    = {2026},
  doi     = {10.3390/buildings16040719},
}

Related work

Author identity: ORCID 0000-0003-3787-963X · Google Scholar