Intelligent Classification of Engineering Safety Accident Causes Based on Natural Language Reasoning Mechanism

DOI

10.2991/978-94-6463-658-1_31How to use a DOI?

Keywords

Engineering construction safety accidents; Text classification; StructBERT; Natural language reasoning mechanism

Abstract

Timely and accurate identification of the causes of safety accidents is very important for preventing accidents from happening again and improving the efficiency of safety management. However, a large number of complex and heterogeneous unstructured and semi-structured safety accident text data will be generated in the process of engineering construction, and the traditional manual analysis method is time-consuming, labor-intensive and error-prone. Therefore, this paper proposes an intelligent classification technology based on natural language reasoning mechanism for engineering construction safety accidents. First, the StructBERT model is used to analyze the features of the unlabeled safety accident data, and the text data is set as the premise of natural language reasoning. Then, the hypothesis is constructed by using the type label of each cause factor. Then, the relationship between the premise and the hypothesis is deduced, so as to determine the label to which the text belongs. Thus, the automatic classification of the causes of security accidents is realized. Finally, the performance of the method is tested by combining the data sets of power plant, power grid, municipal and hydropower engineering fields. The experimental results show that the proposed method performs well on the data sets of four engineering fields. Compared with the existing models based on machine learning and deep learning, the superiority and reliability of the proposed method are proved, which provides information support for the safety management and accident cause analysis in the engineering construction field.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Binghua Shen
PY  - 2025
DA  - 2025/03/03
TI  - Intelligent Classification of Engineering Safety Accident Causes Based on Natural Language Reasoning Mechanism
BT  - Proceedings of the 2024 10th International Conference on Architectural, Civil and Hydraulic Engineering (ICACHE 2024)
PB  - Atlantis Press
SP  - 301
EP  - 311
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-658-1_31
DO  - 10.2991/978-94-6463-658-1_31
ID  - Shen2025
ER  -