Utilizing Large Language Models to Illustrate Constraints for Construction Planning

• Published in: Buildings (Basel) Vol. 14; no. 8; p. 2511
• Main Authors: He, Chuanni, Yu, Bei, Liu, Min, Guo, Lu, Tian, Li, Huang, Jianfeng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2024
• Subjects: Artificial intelligence; Automation; bidirectional encoder representations from transformers (BERT) classification; Classification; Computational linguistics; constraint discussion; Constraints; Construction industry; Construction planning; Critical path; Decision making; general pretrained transformer (GPT); Language; Language processing; Large language models; Managers; Meeting planners; Meetings; Methods; Natural language interfaces; Natural language processing; Onsite; planning meeting; Production planning; Project management; Project planning; Root cause analysis; Stakeholders; Usability; China
• ISSN: 2075-5309; 2075-5309
• DOI: 10.3390/buildings14082511

Effective construction project planning relies on addressing constraints related to materials, labor, equipment, and others. Planning meetings are typical venues for stakeholders to identify, communicate, and remove constraints. However, a critical gap exists in lacking an automated approach to identify, classify, analyze, and track constraint discussions during onsite planning meetings. Therefore, this research aims to 1. develop a natural language processing model to classify constraints in meeting discussions; 2. uncover the discussion patterns of managers and foremen regarding various constraints; and 3. extract the root causes for constraints, evaluate their impacts, and prepare managers to develop practical solutions for constraint removal. This research collected meeting transcripts from 94 onsite planning meetings of a building project, spanning 263,836 words. Next, this research leveraged a general pretrained transformer (GPT) to segment discussion dialogs into topics. A Bidirectional Encoder Representations from Transformers (BERT)-based model was developed to categorize constraint types for each topic. The constraint patterns among meeting attendees were assessed. Furthermore, a GPT-based tool was devised to track root causes, impacts, and solutions for various constraints. Test results revealed an 8.8% improvement in constraint classification accuracy compared with the traditional classification model. An occupational characteristic in constraint discussion was observed in that the management team tended to balance their focus on various constraints, while foremen concentrated on more practical issues. This research contributes to the body of knowledge by leveraging language models to analyze construction planning meetings. The findings facilitate project managers in establishing constraint logs for diagnosing and prognosticating planning issues.