A human-in-the-loop automated framework for high-precision bridge maintenance knowledge graphs: from construction to refinement with LLMs and GNNs

Li, Xuetong, Wang, Dalei, Yuan, Jie, Pan, Yue, Liu, Jiucai ORCID: https://orcid.org/0009-0001-7056-8983, Cheng, Jack C.P. and Chen, Airong 2026. A human-in-the-loop automated framework for high-precision bridge maintenance knowledge graphs: from construction to refinement with LLMs and GNNs. Advanced Engineering Informatics 76 , 105034. 10.1016/j.aei.2026.105034

Full text not available from this repository.

Abstract

The digital transformation of bridge maintenance is critically hindered by the fragmentation of multi-source heterogeneous data and the lack of semantic interoperability across engineering documents. This paper proposes a human-in-the-loop automated construction and refinement framework for Bridge Maintenance Knowledge Graphs (BM-KG). The framework synergizes ontology-guided Large Language Models (LLMs) with enhanced Graph Neural Networks (GNNs) within a systematic “extraction–fusion–completion” pipeline. First, to guarantee high-precision extraction, an ontology-guided LLM module is developed, employing domain constraints and dynamic prompts to transform unstructured text into traceable triples. Second, to ensure rigorous knowledge fusion, a parent–child collaborative strategy is introduced, utilizing spatial hierarchy to uniquely align entities and resolve attribute conflicts. Finally, to facilitate credible knowledge completion, an Ontology-enhanced Hybrid GNN (OH-GNN) is proposed, embedding engineering logic into graph learning to reliably infer implicit relationships. Experiments on a large-scale professional bridge corpus demonstrate the framework’s high-precision and superiority: it achieves an F1-score of 91.29% in knowledge extraction, significantly outperforming traditional supervised baselines; attains an entity alignment F1-score of 85.71% in knowledge fusion; and improves link prediction MRR to 0.476 while reducing the OCVR to 5.1% in completion tasks. Furthermore, holistic ablation studies confirm the contribution of each core component. The proposed framework provides an advanced informatics foundation for intelligent lifecycle management and decision support in bridge engineering.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Schools > Engineering
Publisher:	Elsevier
ISSN:	1474-0346
Date of Acceptance:	30 June 2026
Last Modified:	13 Jul 2026 15:15
URI:	https://orca.cardiff.ac.uk/id/eprint/188180

Actions (repository staff only)

Edit Item