A Study on Enhancing Chemical Safety Management in Workplaces through Artificial Intelligence 


Vol. 40,  No. 3, pp. 38-45, Jun.  2025
10.14341/JKOSOS.2025.40.3.38


PDF
  Abstract

In this study, we developed a system that automatically provides both the latest material safety data sheet (MSDS) and a condensed "One-Page Sheet MSDS" using only an image of a chemical bottle label. The system is based on the retrieval-augmented generation technique. It extracts key identifying information about the chemical substance (product name and chemical abstracts service number) from the label, then performs vector similarity-based document retrieval followed by summarization using a large language model. Additionally, the system generates an automated safety checklist for users to verify based on the extracted MSDS content. This allows users to quickly and intuitively understand the properties and hazards of chemical substances. The system is expected to significantly improve the efficiency of chemical safety management in workplaces and help prevent chemical accidents.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

복정규, 조현숙, 정한일, "A Study on Enhancing Chemical Safety Management in Workplaces through Artificial Intelligence," Journal of the Korean Society of Safety, vol. 40, no. 3, pp. 38-45, 2025. DOI: 10.14341/JKOSOS.2025.40.3.38.

[ACM Style]

복정규, 조현숙, and 정한일. 2025. A Study on Enhancing Chemical Safety Management in Workplaces through Artificial Intelligence. Journal of the Korean Society of Safety, 40, 3, (2025), 38-45. DOI: 10.14341/JKOSOS.2025.40.3.38.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

pISSN : 1229 - 9197
eISSN : 1875 - 0052

Impact Factor(2022): 2.5