TY - JOUR
T1 - Transformer machine learning language model for auto-alignment of long-term and short-term plans in construction
AU - Amer, Fouad
AU - Jung, Yoonhwa
AU - Golparvar-Fard, Mani
N1 - Funding Information:
This material is in part based upon works supported by the National Science Foundation [ 1446765, 2020227 ]. The support and help of construction companies in collecting schedule data and validating the system prototype is greatly appreciated. The opinions, findings, and conclusions or recommendations expressed are those of the authors and do not reflect the views of the NSF, or the companies mentioned above.
Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/12
Y1 - 2021/12
N2 - In construction, master schedules and look-ahead plans are created at different times (monthly vs. weekly), by different personas (planner vs. superintendent), with different software (scheduling solution vs. spreadsheet), and at different levels of granularity (milestones vs. production details). Their full-alignment is essential for project coordination, progress updating, and payment application reviews, and its absence may lead to costly litigation. This paper presents the first attempt to automate linking look-ahead planning tasks to master-schedule activities following an NLP-based multi-stage ranking formulation. Our model employs distance-based matching for candidate generation and a Transformer architecture for final matching.1 Validation results from real-world projects demonstrate that the method helps planners match look-ahead planning tasks to master schedule activities by presenting a list of top-five matches with a precision of 76.5%. We also show that the method helps superintendents create look-ahead plans from a master schedule by generating lists of tasks based on activity descriptions.
AB - In construction, master schedules and look-ahead plans are created at different times (monthly vs. weekly), by different personas (planner vs. superintendent), with different software (scheduling solution vs. spreadsheet), and at different levels of granularity (milestones vs. production details). Their full-alignment is essential for project coordination, progress updating, and payment application reviews, and its absence may lead to costly litigation. This paper presents the first attempt to automate linking look-ahead planning tasks to master-schedule activities following an NLP-based multi-stage ranking formulation. Our model employs distance-based matching for candidate generation and a Transformer architecture for final matching.1 Validation results from real-world projects demonstrate that the method helps planners match look-ahead planning tasks to master schedule activities by presenting a list of top-five matches with a precision of 76.5%. We also show that the method helps superintendents create look-ahead plans from a master schedule by generating lists of tasks based on activity descriptions.
KW - Artificial intelligence
KW - Construction planning
KW - Machine learning
KW - Natural language processing
KW - Project controls
UR - http://www.scopus.com/inward/record.url?scp=85115034423&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115034423&partnerID=8YFLogxK
U2 - 10.1016/j.autcon.2021.103929
DO - 10.1016/j.autcon.2021.103929
M3 - Article
AN - SCOPUS:85115034423
SN - 0926-5805
VL - 132
JO - Automation in Construction
JF - Automation in Construction
M1 - 103929
ER -