TY - JOUR
T1 - EXPLORING THE USE OF NLP TO AUTO-ALIGN MASTER SCHEDULES WITH SUPERINTENDENT’S LOOK-AHEADS IN CONSTRUCTION PROJECTS
AU - Jung, Yoonhwa
AU - Golparvar-Fard, Mani
N1 - This material is in part based upon works supported by the National Science Foundation 1446765, 2020227. The opinions, findings, and conclusions or recommendations expressed are those of the authors and do not reflect the views of the NSF or industry collaborators.
This material is in part based upon works supported by the National Science Foundation1446765, 2020227. The opinions, findings, and conclusions or recommendations expressed are those of the authors and do not reflect the views of the NSF or industry collaborators.
PY - 2023
Y1 - 2023
N2 - In construction, there has always been a painful disconnect in reconciling parameters set in the master plan to what is actually happening in real-time on a project against the superintendent’s look-ahead. In the absence of an integrated solution, superintendents spend hours manually attempting to connect the master schedule with the look-ahead tasks written on trailer walls and sticky notes using papers or spreadsheets. This leads to frequent human error, poor communication between field and office and missing jobsite information created by the realities of weekly re-planning on-site. To address these inefficiencies, this paper explores the use of natural language processing (NLP) on both long-term (master) schedule and short-term (lookahead) plans to automatically learn and map their activities and tasks against one another. Using preliminary results from several commercial building projects, the potential of using an NLP seq2seq model as an Extractive and Abstractive Text Summarization technique is discussed in detail.
AB - In construction, there has always been a painful disconnect in reconciling parameters set in the master plan to what is actually happening in real-time on a project against the superintendent’s look-ahead. In the absence of an integrated solution, superintendents spend hours manually attempting to connect the master schedule with the look-ahead tasks written on trailer walls and sticky notes using papers or spreadsheets. This leads to frequent human error, poor communication between field and office and missing jobsite information created by the realities of weekly re-planning on-site. To address these inefficiencies, this paper explores the use of natural language processing (NLP) on both long-term (master) schedule and short-term (lookahead) plans to automatically learn and map their activities and tasks against one another. Using preliminary results from several commercial building projects, the potential of using an NLP seq2seq model as an Extractive and Abstractive Text Summarization technique is discussed in detail.
KW - Construction planning
KW - Lean construction
KW - Natural language processing
KW - Project control
KW - Scheduling
UR - http://www.scopus.com/inward/record.url?scp=85171578884&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171578884&partnerID=8YFLogxK
U2 - 10.14455/ISEC.2023.10(1).CON-30
DO - 10.14455/ISEC.2023.10(1).CON-30
M3 - Conference article
AN - SCOPUS:85171578884
SN - 2644-108X
VL - 10
SP - CON-30-1-CON-30-6
JO - Proceedings of International Structural Engineering and Construction
JF - Proceedings of International Structural Engineering and Construction
IS - 1
T2 - 12th International Structural Engineering and Construction Conference, ISEC-12 2023
Y2 - 14 August 2023 through 18 August 2023
ER -