|国家预印本平台
首页|Risk identification based on similar case retrieval enhancement,

Risk identification based on similar case retrieval enhancement,

Risk identification based on similar case retrieval enhancement,

来源:Arxiv_logoArxiv
英文摘要

The goal of construction site risk and hazard identification is to enhance safety management through automation. Existing research based on large language models falls into two categories: image-text matching for collaborative reasoning, which struggles with complex hazard features, and instruction fine-tuning or dialogue guidance using professional datasets, which suffers from high training costs and poor generalization.To address this, we propose a hazard identification method using similar case retrieval enhancement. By integrating external knowledge and retrieved case contexts via prompt fine-tuning, we mitigate misjudgments caused by limited domain knowledge and weak feature associations. Our method includes three modules: retrieval library, image similarity retrieval, and large model retrieval enhancement, enabling efficient recognition without training. Experiments on real construction data show significant improvements. For instance, GLM-4V's recognition accuracy increased to 50\%, a 35.49\% boost. The method enhances accuracy, context understanding, and stability, offering new theoretical and technical support for hazard detection.

Jiawei Li、Chengye Yang、Yaochen Zhang、Weilin Sun、Lei Meng、Xiangxu Meng

安全科学自动化技术、自动化技术设备计算技术、计算机技术

Jiawei Li,Chengye Yang,Yaochen Zhang,Weilin Sun,Lei Meng,Xiangxu Meng.Risk identification based on similar case retrieval enhancement,[EB/OL].(2025-08-04)[2025-08-19].https://arxiv.org/abs/2508.02073.点此复制

评论