[논문]건설사업 입찰 텍스트의 BIM 수행 난이도 추론을 위한 딥러닝 모델

김정수; 문현석; 박상미

doi:10.12652/ksce.2023.43.6.0851

건설사업 입찰 텍스트의 BIM 수행 난이도 추론을 위한 딥러닝 모델
A Deep Learning Model to Predict BIM Execution Difficulty Based on Bidding Texts in Construction Projects 원문보기

KSCE Journal of Civil and Environmental Engineering Research = 대한토목학회논문집, v.43 no.6, 2023년, pp.851 - 863

김정수 (한국건설기술연구원 구조연구본부) , 문현석 (한국건설기술연구원 미래스마트건설연구본부) , 박상미 (한국건설기술연구원 미래스마트건설연구본부)

초록
AI-Helper

일정 규모 이상의 공공 건설 프로젝트에 대한 BIM(Building Information Model) 적용이 의무화됨에 따라 입찰단계에서부터 BIM 요구사항에 대한 관련 절차 및 기술에 대한 폭넓은 이해가 요구되고 있다. 그러나 대부분의 중소 시공 및 엔지니어링 기업은 BIM 수행역량이 낮고 관련 기존 업무 프로세스의 BIM 적용에 대한 이해 높지 않아, 입찰 요구사항에 대한 인지가 어렵고 입찰단계의 합리적인 의사결정이 쉽지 않다. 따라서 본 연구는 BIM 입찰문서 용어를 포함한 형태소 분석기를 딥러닝 모델에 결합하여 입찰문서의 BIM 요구사항의 난이도 판별 방법을 제시한다. 제안된 딥러닝 모델의 매개변수 영향이 조사되었으며 예측 결과의 타당성이 검토되었다. 그 결과, 제안된 모델이 시험 데이터에 대해 F1-score 0.83의 성능을 가지며, 모델의 판별 결과 또한 실제 BIM 수행 난이도를 타당하게 반영하고 있음을 보였다.

Abstract ▼ AI-Helper

The mandatory use of BIM(Building Information Model) in larger Korean public construction projects necessitates participants to have a comprehensive understanding of the relevant procedures and technologies, especially during the bidding stage. However, most small and medium-sized construction and engineering companies possess limited BIM proficiency and understanding. This hampers their ability to recognize bidding requirements and make informed decisions. To address this challenge, our study introduces a method to gauge the complexity of BIM requirements in bidding documents. This is achieved by integrating a morphological analyzer, which encompasses BIM bidding terminology, with a deep learning model. We investigated the effects of the parameters in our proposed deep learning model and examined its predictive validity. The results revealed an F1-score of 0.83 for the test data, indicating that the model's predictions align closely with the actual BIM performance challenges.

주제어

표/그림 (14)

그림 Fig. 1. Comparison with of Tokenizers Performance for Complex Nouns: (a) Count of Suitable Tokenizers for each Complex Nouns to Short Noun Sequences, (b) Histogram of Processing Time for Tokenization
표 Table 1. Comparison between Token Sequence of BIM Bidding Keywords by Tokenizers
그림 Fig. 2. Samples of BIM Bidding Sentences and Distribution on Label of the Sentences: (a) Data Sample, (b) Data Distribution
그림 Fig. 3. Deep Learning Model for Predicting Level of BIM Bidding Sentences
표 Table 2. Case of Hyper-parameter for the Proposed Deep Learning Model
그림 Fig. 4. Effect of Hyper-parameter on the Model Metric: Batch Size 32: (a) Loss, (b) F1-score
그림 Fig. 5. Effect of Hyper-parameter on the Model Metric: Batch Size 64: (a) Loss, (b) F1-score
그림 Fig. 6. Effect of Hyper-parameter on the Model Metric: Batch Size 128: (a) Loss, (b) F1-score
그림 Fig. 7. Effect of Hyper-parameter on the Model Metric: Batch Size 256: (a) Loss, (b) F1-score
그림 Fig. 8. Change in Accuracy and Loss of the Present Model: (a) Training Data, (b) Validation Data
표 Table 4. Metric of the Present Model for Test Data
표 Table 5. Comparison with Metric of the Present and other RNN Models for Test Data
표 Table 3. Metric of the Present Model for Validation Data
표 Table 6. Sentences and Prediction Results of TP, TN, FP, FN Groups for Test Data

참고문헌 (26)

Akinosho, T. D., Oyedele, L. O., Bilal, M., Ajayi, A. O., Delgado,？M. D., Akinade, O. O. and Ahmed, A. A. (2020). "Deep learning？in the construction industry: A review of present status and future？innovation." Journal of Building Engineering, Elsevier, Vol. 32.？https://doi.org/10.1016/j.jobe.2020.101827.？

상세보기
Bae, S., Ham, S., Lee, I., Lee, G. P. and Kim, D. (2019). "Deep？learning based crack detection from tunnel cement concrete？lining." Journal of Korean Tunnelling and Underground Space？Association, KTA, Vol. 24, No. 6, pp. 583-598, https://doi.org/10.9711/KTAJ.2022.24.6.583 (in Korean).？

원문보기 상세보기
Cahuantzi, R., Chen, X. and Guttel, S. (2023). "A comparison of？LSTM and GRU networks for learning symbolic sequences."？Proceeding of Science and Information Conference, London,？UK, pp. 771-785, https://doi.org/10.1007/978-3-031-37963-5_53.？
Choi, S. J., Choi, S. W., Kim, J. H. and Lee, E. B. (2021). "AI and？text-mining applications for analyzing constractor's risk in？Invitation to Bid(ITB) and contracts for engineering procurement？and construction (EPC) projects." Energies, MDPI, Vol. 14, No.？15. https://doi.org/10.3390/en14154632.？

상세보기
Choi, S. W. and Lee, E. B. (2022). "Contractor's risk analysis of？engineering procurement and construction(EPC) contracts using？ontological semantic model and bi-long short-term memory？(LSTM) technology." Sustainability, MDPI, Vol. 14, No. 11.？https://doi.org/10.3390/su14116938.？

상세보기
Eom, S. H., Cha, G., Park, S. K., Park, S. and Park, J. (2023).？"Analysis of potential construction risk types in formal？documents using text mining." KSCE Journal of Civil and？Environmental Engineering Research, KSCE, Vol. 43, No. 1, pp.？91-98, https://doi.org/10.12652/Ksce.2023.43.1.0091 (in Korean).？

원문보기 상세보기
Kang, E. A., Kim, S. and Kim, S. (2022). "Quality control of？reinforced concrete work using deep-learning based on object？recognition." Journal of the Regional Association of Architectural？Institute of Korea, AIKRA, Vol. 24, No. 2, pp. 17-24 (in Korean).？
Kim, M. H. (2019). Application of computer vision based deep？learning technique for detecting safety helmet of construction？workers, Msc. thesis, Pukyong National University, Busan,？Korea (in Korean).？
Kim, S., Cha, G., Cho, M. and Park, S. (2022). "Text mining based？analysis of construction accident causes and risk factors."？Proceedings of the 2022 Spring Conference of the Korea？Academia-Industrial Cooperation Society, Jeju, South Korea, pp.？272-273 (in Korean).？
Kim, J., Lee, C. W., Park, S. H., Lee, J. H. and Hong, C. H. (2020).？"Development of fire detection model for underground utility？facilities using deep learning: Training data supplement and bias？optimization." Journal of the Korea Academia-Industrial？Cooperation Society, KAIS, Vol. 21, No. 12, pp. 320-330,？https://doi.org/10.5762/KAIS.2020.21.12.320 (in Korean).？

원문보기 상세보기
Kim, J., Park, S. and Hong, C. H. (2023). "A study on falling？detection of workers in the underground utility tunnel using dual？deep learning techniques." Journal of the Society of Disaster？Information, KOSDI, Vol. 19, No. 3, pp. 498-509, https://doi.org/10.15683/kosdi.2023.9.30.498 (in Korean).？

원문보기 상세보기
Kudo, T., Yamamoto, K. and Matsumoto, Y. (2004). "Applying？conditional random fields to Japanese morphological analysis."？Proceedings of the 2004 Conference on Empirical Methods in？Natural Language Processing, ACL, Barcelona, Spain, pp.？230-237.？
Lee, J. H. (2019). "Global research trend based on Natural？Language Processing of irregular text data in the construction？industry." Magazine of Construction Management, KICEM, Vol.？20, No. 2, pp. 62-65 (in Korean).？
Lee, K., Kang, S. and Shin, Y. (2022). "A study on the application？of object detection method in construction site through real case？analysis." Journal of the Society of Disaster Information, KOSDI,？Vol. 18, No. 2, pp. 269-279, https://doi.org/10.15683/KOSDI.2022.6.30.269 (in Korean).？

원문보기 상세보기
Lee, D., Yeon, J., Hwang, I. and Lee, S. (2010)."KKMA : A tool for？utilizing sejong corpus based on relational database." JKIISE？Transactions on Computing Practices, KIISE, Vol. 16, No. 11,？pp. 1046-1050 (in Korean).？
Lee, D. H., Yoon, G. H. and Kim, J. J. (2019). "Development of ITB？risk management model based on AI in bidding phase for oversea？EPC projects." The Journal of the Institute of Internet, Broadcasting？and Communication, IIBC, Vol. 19, No. 4, pp. 151-160,？https://doi.org/10.7236/JIIBC.2019.19.4.151 (in Korean).？

원문보기 상세보기
Moon, S., Chi, S. and Im, S. B. (2022). "Automated detection of？contractual risk clauses from construction specifications using？bidirectional encoder representations from transformers？(BERT)." Automation in Construction, Elsevier, Vol. 142,？104465, https://doi.org/10.1016/j.autcon.2022.104465.？

상세보기
Moon, S., Lee, G. and Chi, S. (2021a). "Semantic text-pairing for？relevant provision identification in construction specification？reviews." Automation in Construction, Elsevier, Vol. 128,？103780, https://doi.org/10.1016/j.autcon.2021.103780.？

상세보기
Moon, S., Lee, G., Chi, S. and Oh, H. (2021b). "Automated？construction specification review with named entity recognition？using natural language processing." Journal of Construction？Engineering and Management, ASCE, Vol. 147, No. 1.？https://doi.org/10.1061/(ASCE)CO.1943-7862.0001953.？

상세보기
Park, S. (2021). Development of visualization system for deep？learning-based progress comparison using the real image of？construction site and 4D model, Ph.D thesis, Gyeongsang？National University (in Korean).？
Park, E. J. and Cho, S. Z. (2014). "KoNLPy: Korean natural？language processing in Python." Proceedings of the 26th Annual？Conference on Human & Cognitive Language Technology,？KIISE, Kangwon, Korea, pp. 133-136 (in Korean).？
Park, K. and Kim, H. (2021). "Analysis of seasonal Importance of？construction hazards using text mining." KSCE Journal of Civil？and Environmental Engineering Research, KSCE, Vol. 41, No. 3,？pp. 305-316, https://doi.org/10.12652/Ksce.2021.41.3.0305 (in？Korean).？

원문보기 상세보기
Prabowo, Y. D., Warnars, H. L. H. S., Budiharto, W., Kistijantoro, A. I., Heryadi, Y. and Lukas (2018). "Lstm and simple rnn？comparison in the problem of sequence to sequence on？conversation data using Bahasa Indonesia." Proceedings of 2018？Indonesian Association for Pattern Recognition International？Conference, IEEE, Jakarta, Indonesia, pp. 51-56, https://doi.org/10.1109/INAPR.2018.8627029.？
Saitoh, K. (2018). Deep Learning from Scratch 2, Hanbit Media,？translated by Gaeapmapsi (in Korean).？
Shewalkar, A. N. (2018). Comparison of RNN, LSTM and GRU on？Speech Recognition Data, Msc. thesis, North Dakota State？University, North Dakota, USA.？
Wiliams, T. P. and Gong, J. (2014). "Predicting construction cost？overruns using text mining, numerical data and ensemble？classifiers." Automation in Construction, Elsevier, Vol. 43, pp.？23-29, https://doi.org/10.1016/j.autcon.2014.02.014.

상세보기

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증