All Issue

2022 Vol.1, Issue 4 Preview Page
Proposal of a Workflow Model for Generating a Construction Safety Guideline Knowledge Graph

건설안전지침 지식그래프 생성 워크플로우 모델 제안

Woo Hyuk Kim1
,
Jung Won Lee2
,
Seungjun Ahn3*
김 우혁1
,
이 중원2
,
안 승준3*
1Bachelor’s degree student, Department of Civil and Environmental Engineering, Hongik University
2Bachelor’s degree student, Department of Civil and Environmental Engineering, Hongik University
3Assistant Professor, Department of Civil and Environmental Engineering, Hongik University
1홍익대학교 건설환경공학과 학사과정
2홍익대학교 건설환경공학과 학사과정
3홍익대학교 건설환경공학과 조교수
*Corresponding Author
26 December 2022. pp. 46-54
PDF XML Citation
Abstract

Most of the construction safety guidelines exist in the form of text, such as webpage documents or PDFs, and as such, they are fragmented and difficult to search in an integrated way. To address this issue, this paper proposes a workflow model for generating a construction safety guideline knowledge graph. The proposed workflow is based on Natural Language Processing techniques, so the transformation of text data into a knowledge DB can be partially automated. Specifically, it is proposed that the construction safety guidelines existing in PDFs are first transformed into a table that has the fields of “category” and “content,” in which category means the topic and content is the content of the safety guideline. Then, keywords are extracted from each of the contents using an NLP technique, such as TF-IDF. Once all keywords are extracted and added to the table data, the dataset is transformed into a knowledge DB following the format of a Graph DB. Once this transformation process is complete, the knowledge graph can respond to complex queries such as conditional matching queries. This paper includes a case study to illustrate the proposed workflow and demonstrate the proposed method's effectiveness in producing a knowledge graph that can be used as a knowledge base for information searches regarding construction safety management methods.

Keywords
Construction Safety Guideline
Knowledge Graph
Ontology
Natural Language Processing (NLP)
Automation

건설안전관리지침은 모두 분절된 PDF 문서로 존재하고 있어, 관련된 지침 내용의 상호관련성 파악이 어렵고 실무에 사용이 매우 불편하다. 이러한 배경에서 본 연구의 목표는 자연어처리 기술을 이용해 텍스트 형태로 존재하는 건설안전관리 지침의 내용을 지식그래프(Knowledge Graph)로 변환하는 워크플로우 모델을 개발하는 것이다. 건설작업안전지침 PDF 문서들을 출발점으로 하여, 문서 전처리 및 키워드추출을 거쳐 건설안전지침 텍스트데이터의 범주(category)-내용(content)-키워드(keyword) 리스트를 담고 있는 테이블데이터를 생성하고, 이 데이터를 지식그래프 DB로 변환하는 과정을 제안한다. 제안된 워크플로우 모델의 검증을 위해 사례연구를 사용하였으며, 사례 연구의 결과는 제안된 지식그래프 생성 워크플로우 모델이 건설안전지침 문서에 담긴 내용을 지식그래프 DB 형태로 효과적으로 변환하였으며, 이 지식그래프는 안전관리에 관련된 통합적 지식검색에 사용될 수 있음을 보인다.

키워드
건설안전지침
지식그래프
온톨로지
자연어처리
자동화
References
1
한국산업안전보건공단 (2020). KOSHA Guide 건설안전지침 목록, < https://www.kosha.or.kr/kosha/data/guidanceC.do >
2
Chi, N.-W., Lin, K.-Y., and Hsieh, S.-H. (2014). Using ontology-based text classification to assist Job Hazard Analysis. Advanced Engineering Informatics, 28, pp. 381-94. 10.1016/j.aei.2014.05.001
3
Garreta, R., and Moncecchi, G. (2013). Learning scikit-learn: machine learning in python. Packt Publishing Ltd.
4
Goh, Y.M., and Chua, D.K.H. (2009). Case-based reasoning for construction hazard identification: Case representation and retrieval. Journal of construction engineering and management, 135(11), pp. 1181-89. 10.1061/(ASCE)CO.1943-7862.0000093
5
Goh, Y.M., and Chua, D.K.H. (2010). Case-based reasoning approach to construction safety hazard identification: Adaptation and utilization, Journal of Construction Engineering and Management, 136(2), pp. 170-78. 10.1061/(ASCE)CO.1943-7862.0000116
6
Kim, H., Lee, H.S., Park, M., and Choi, B. (2013). Automated Information Retrieval for Hazard Identification in Construction Sit., ASCE International Workshop on Computing in Civil Engineering, pp. 897-904. 10.1061/9780784413029.112
7
Kim, K., Cho, Y., and Zhang, S. (2016a). Integrating work sequences and temporary structures into safety planning: Automated scaffolding-related safety hazard identification and prevention in BIM. Automation in construction, 70, pp. 128-42. 10.1016/j.autcon.2016.06.012
8
Kim, H., Lee, H.-S., Park, M., Chung, B., and Hwang, S. (2016b). Automated hazardous area identification using laborers' actual and optimal routes. Automation in construction, 65, pp. 21-32. 10.1016/j.autcon.2016.01.006
9
Lu, Y., Li, Q., Zhou, Z., and Deng, Y. (2015). Ontology-based knowledge modeling for automated construction safety checking. Safety Science, 79, pp. 11-18. 10.1016/j.ssci.2015.05.008
10
Miller, J. J. (2013). Graph database applications and concepts with Neo4j. In Proceedings of the southern association for information systems conference, Atlanta, GA, USA, 2324(36).
11
Park, E. L., and Cho, S. (2014). KoNLPy: Korean natural language processing in Python. In Annual Conference on Human and Language Technology, pp. 133-136.
12
Rahman, M.M., Bobadilla, L., Mostafavi, A., Carmenate, T., and Zanlongo, S.A. (2018). An automated methodology for worker path generation and safety assessment in construction projects, IEEE Transactions on Automation Science and Engineering, 15(2), pp. 479-91. 10.1109/TASE.2016.2628898
13
Wang, H.-H., and Boukamp, F. (2011). Ontology-based representation and reasoning framework for supporting job hazard analysis. Journal Of Computing In Civil Engineering, 25(6), pp. 442-56. 10.1061/(ASCE)CP.1943-5487.0000125
14
Wang, N., Wang, P., and Zhang, B. (2010). An improved TF-IDF weights function based on information theory. In 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering, 3, pp. 439-441, IEEE. 10.1109/CCTAE.2010.5544382
15
Xiong, R., Song, Y., Li, H., and Wang, Y. (2019). Onsite video mining for construction hazards identification with visual relationships. Advanced Engineering Informatics, 42. 10.1016/j.aei.2019.100966
16
Yoo, W.J. (2022). Introduction to Deep Learning for Natural Language Processing, Wikidocs.
17
Zhang, S., Boukamp, F., and Teizer, J. (2015). Ontology-based semantic modeling of construction safety knowledge: Towards automated safety planning for job hazard analysis (JHA), Automation in construction, 52. 10.1016/j.autcon.2015.02.005
18
Zhang, Y., Jin, R., and Zhou, Z. H. (2010). Understanding bag-of-words model: a statistical framework. International journal of machine learning and cybernetics, 1(1), 43-52. 10.1007/s13042-010-0001-0
19
Zhong, B., and Li, Y. (2015). An ontological and semantic approach for the construction risk inferring and application. Journal of Intelligent & Robotic Systems, 79, pp. 449-63. 10.1007/s10846-014-0107-9
Information
  • Publisher :Korean Society of Automation and Robotics in Construction
  • Publisher(Ko) :(사)한국건설자동화·로보틱스학회
  • Journal Title :Journal of Construction Automation and Robotics
  • Journal Title(Ko) :건설자동화·로보틱스 논문집
  • Volume : 1
  • No :4
  • Pages :46-54
  • Received Date : 2022-12-11
  • Revised Date : 2022-12-20
  • Accepted Date : 2022-12-24
  • DOI :https://doi.org/10.55785/JCAR.1.4.46
Journal Informaiton Journal of Construction Automation and Robotics Journal of Construction Automation and Robotics
Online Submission
  • crossref crossmark
  • crossref cited-by
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close