Tags:cost estimation, Industry Foundation Classes (IFC), Large Language Models (LLM), Natural Language Processing (NLP), prompt engineering and Structured Query Language (SQL)
Abstract:
Effective cost estimation for tendering plays a critical role in the building construction process, enabling efficient investment management and ensuring successful execution of the construction phase. The current practice involves the classification of building items, extracting all the quantities of the latter, collecting pricing information from construction priced list documents and manually relate these data to the building items. The objective of this paper is to support cost estimation activity by developing a tool that automates the process of assigning a cost domain description to a IFC-based BIM building objects, in such a way as to minimize the human error when manually performing this activity and speed up the process. To handle the textual data involved, the authors introduce a prompt-based framework, testing Mistral-7b language model for querying cost domain description with data in IFC format, which represent two domains characterized by different semantic.
LLM Based Automatic Relation Between Cost Domain Descriptions and IFC Objects