Information requirement analysis for establishing intelligent natural language query interfaces in BIM-based construction projects
), Abstract
Emerging artificial intelligence (AI)-based natural language interface (NLI) systems show significant potential for enabling stakeholders to efficiently retrieve complicated building information models (BIM). Previous studies have shown many technical pathways, but they have not investigated which information entities in complex BIM schemas and constraint types were most important for NLI-based data querying. This study investigates the information requirements for NLI-based BIM model retrieval. It begins with a survey of existing BIM query languages (BIMQLs) and software applications to identify popular information entities and constraints. We then recruited ten practitioners to create 200 queries and analyzed them to refine the information scope (IS) for NLI applications. Finally, we tested 14 selected queries via the NLI approach and other methods, revealing the types of queries that NLIs could better manage. This study identifies the most important information entities, constraint types, question forms, and condition combinations to develop intelligent NLI systems in BIM-based construction projects. The findings lay a crucial foundation for the advancement of AI-based NLIs by offering a definite IS, which can be used to generate training datasets or prompts for large language models.
Keywords
References
W. Mazairac, J. Beetz. BIMQL—An open query language for building information models. Adv Eng Informatics, 2013, 27: 444–456.
M. Venugopal, C. M. Eastman, R. Sacks, et al. Semantics of model views for information exchanges using the industry foundation class schema. Adv Eng Informatics, 2012, 26: 411–428.
C. Preidel, S. Daum, A. Borrmann. Data retrieval from building information models based on visual programming. Vis Eng, 2017, 5: 18.
M. B. Hoy. Alexa, Siri, Cortana, and more: An introduction to voice assistants. Med Ref Serv Q, 2018, 37: 81–88.
B. D. Lund, T. Wang. Chatting about ChatGPT: How may AI and GPT impact academia and libraries? Libr Hi Tech News, 2023, 40: 26–29.
J. R. Lin, Z. Z. Hu, J. P. Zhang, et al. A natural-language-based approach to intelligent data retrieval and representation for cloud BIM. Comput Civ Infrastruct Eng, 2016, 31: 18–33.
S. Shin, R. R. A. Issa. BIMASR: Framework for voice-based BIM information retrieval. J Constr Eng Manage, 2021, 147: 04021124.
N. Wang, R. R. A. Issa, C. J. Anumba. NLP-based query-answering system for information extraction from building information models. J Comput Civ Eng, 2022, 36: 3.
P. Pauwels, W. Terkaj. EXPRESS to OWL for construction industry: Towards a recommendable and usable ifcOWL ontology. Autom Constr, 2016, 63: 100–133.
S. Daum, A. Borrmann. Processing of topological BIM queries using boundary representation based methods. Adv Eng Informatics, 2014, 28: 272–286.
M. T. Yin, L. Tang, C. Webster, et al. A deep natural language processing-based method for ontology learning of project-specific properties from building information models. Comput Civ Infrastruct Eng, 2024, 39: 20–45.
J. J. Chen, W. S. Lu, D. H. Liu. Built environment defect mapping, modeling, and management (D3M): A BIM-based integrated framework. J Intell Constr, 2024, 2: 9180008.
C. Zhang, J. Beetz, B. de Vries. BimSPARQL: Domain-specific functional SPARQL extensions for querying RDF building data. Semant Web, 2018, 9: 829–855.
T. M. de Farias, A. Roxin, C. Nicolle. A rule-based methodology to extract building model views. Autom Constr, 2018, 92: 214–229.
M. M. Burnett, D. W. McIntyre. Visual programming. Computer, 1995, 28: 14–16.
C. Preidel, A. Borrmann. Towards code compliance checking on the basis of a visual programming language. J Inf Technol Constr, 2016, 21: 402–421.
S. F. Wu, Q. Y. Shen, Y. C. Deng, et al. Natural-language-based intelligent retrieval engine for BIM object database. Comput Ind, 2019, 108: 73–88.
F. Elghaish, J. K. Chauhan, S. Matarneh, et al. Artificial intelligence-based voice assistant for BIM data management. Autom Constr, 2022, 140: 104320.
J. Wang, X. N. Gao, X. P. Zhou, et al. Multi-scale information retrieval for BIM using hierarchical structure modelling and natural language processing. J Inf Technol Constr, 2021, 26: 409–426.
M. T. Yin, L. Tang, C. Webster, et al. An ontology-aided, natural language-based approach for multi-constraint BIM model querying. J Build Eng, 2023, 76: 107066.
M. Shahinmoghadam, S. E. Kahou, A. Motamedi. Neural semantic tagging for natural language-based search in building information models: Implications for practice. Comput Ind, 2024, 155: 104063.
M. T. Yin, L. Tang, C. Webster, et al. Two-stage text-to-BIMQL semantic parsing for building information model extraction using graph neural networks. Autom Constr, 2023, 152: 104902.
N. Wang, R. R. A. Issa, C. J. Anumba. Transfer learning-based query classification for intelligent building information spoken dialogue. Autom Constr, 2022, 141: 104403.
J. W. Zheng, M. Fischer. Dynamic prompt-based virtual assistant framework for BIM information search. Autom Constr, 2023, 155: 105067.
S. Lockley, C. Benghi, M. Černý. Xbim. Essentials: A library for interoperable building information applications. J Open Source Softw, 2017, 2: 473.
S. Firoz, S. K. Rao. Modelling concept of sustainable steel building by Tekla software. Int J Eng Res Dev, 2012, 1: 18–24.
I. Motawa. Spoken dialogue BIM systems—An application of big data in construction. Facilities, 2017, 35: 787–800.
W. Solihin, C. Eastman, Y. C. Lee, et al. A simplified relational database schema for transformation of BIM data into a query-efficient and spatially enabled database. Autom Constr, 2017, 84: 367–383.
W. Solihin, J. Dimyadi, Y. C. Lee, et al. Simplified schema queries for supporting BIM-based rule-checking applications. Autom Constr, 2020, 117: 103248.
M. P. Nepal, S. Staub-French, R. Pottinger, et al. Ontology-based feature modeling for construction information extraction from a building information model. J Comput Civ Eng, 2013, 27: 555–569.
L. Zhang, R. R. A. Issa. Ontology-based partial building information model extraction. J Comput Civ Eng, 2013, 27: 576–584.
D. M. Guo, E. Onstein, A. D. La Rosa. An approach of automatic sparql generation for BIM data extraction. Appl Sci, 2020, 10: 8794.
M. Niknam, S. Karshenas. A shared ontology approach to semantic representation of BIM data. Autom Constr, 2017, 80: 22–36.
R. N. An, P. Lin, Z. C. Li, et al. Intelligent ventilation-on-demand control system for the construction of underground tunnel complex. J Intell Constr, 2024, 2: 9180032.
B. Liu, Q. Han, C. Q. Fu, et al. Development and engineering application of intelligent management and control platform for the shield tunneling construction close to risk sources. J Intell Constr, 2024, 2: 9180018.
D. Saha, A. Floratou, K. Sankaranarayanan, et al. ATHENA : An ontology-driven system for natural language querying over relational data stores. Proc VLDB Endow, 2016, 9: 1209–1220.
京公网安备11010802044758号