Named entity recognition model for bridge inspection report with multi-features fusion and correction method

Bridge inspection reports serve as valuable sources for assessing bridge condition and guiding maintenance, yet accurately extracting structured information from them remains a challenge. Current Named Entity Recognition (NER) models fail to fully leverage unique inspection report text features like Chinese character properties and entity distribution patterns, and the presence of missed or misclassified entities also negatively impacts entity recognition accuracy. To address these challenges, this paper proposed an NER model, MF-Attention-BiLSTM-CRF, that integrates Multi-Features (MF) fusion and correction method to accurately extract key information from bridge inspection reports. Furthermore, according to the characteristics of report texts, an improved Easy Data Augmentation (EDA) method was proposed to construct a bridge inspection report dataset with 23,192 characters and 2,752 entities. Experimental results demonstrate that the proposed model outperforms prior models, general domain models, and large language models, achieving an optimal F1 score of 89.3%. This work advances intelligent infrastructure management systems that strongly support intelligent early warning, predictive maintenance, and decision-making applications.