Automatic generation of findings using generative AI for inspection report support under the new guidelines －Introduction of inspection record retrieval and similar image group search－

Abstract

In response to the 2024 revision of the bridge inspection guidelines, which shifted the unit of findings creation from the component level to the system level, this study proposes an automatic findings generation method tailored to the new requirements. The proposed method is composed of three stages: (i) extraction of relevant inspection records based on predefined inspection information, (ii) selection of representative records using the similarity between groups of distress images, and (iii) findings generation using a Multimodal Large Language Model. Experimental evaluations using bridge inspection data from Hokkaido demonstrate that the proposed method outperforms comparative baselines across all findings categories in terms of generation accuracy. Furthermore, we conducted an additional experiment to assess the validity of selecting representative distress images based on the generated findings, confirming both the practical applicability and remaining challenges of the proposed approach for real-world deployment.