A Hybrid LLM–Knowledge Graph Architecture for Information Retrieval in Smart Buildings
DOI:
https://doi.org/10.7250/csimq.2026-46.05Keywords:
Smart Building, Building Information Modeling, Internet of Things, Hybrid Artificial Intelligence, Knowledge Graphs, Labeled Property Graph, Large Language ModelAbstract
The Smart Building paradigm promises a future where buildings are intelligent, adaptive, and sustainable, offering real-time information retrieval that supports decision-making to enhance energy efficiency, occupant comfort, and security. However, achieving this paradigm is highly complex, one major reason being the seamless integration of (a) physical and functional representations of buildings (i.e., Building Information Modeling) and (b) real-time IoT (i.e., Internet of Things) data. To address this challenge, we propose a hybrid LLM–Knowledge Graph approach in which, on the one hand, a knowledge graph retains the buildings’ knowledge structures and a time-series database stores IoT data. On the other hand, a Large Language Model (LLM) serves as a mediator between a facility manager and the knowledge graph and IoT data, facilitating data-driven decision-making processes. Adopting the Design Science Research (DSR) methodology, we executed two distinct iterations within the implementation phase to investigate contrasting knowledge representation paradigms: Resource Description Framework (RDF) and Labeled Property Graph (LPG). Each iteration was evaluated to assess the effectiveness of the corresponding systems. Finally, we compared the RDFand LPG-based implementations of the proposed architecture and drew insights.
References
X. Huang, Y. Liu, L. Huang, E. Onstein, and C. Merschbrock, “BIM and IoT data fusion: The data process model perspective,” Automation in Construction, vol. 149, 2023. Available: https://doi.org/10.1016/j.autcon.2023.104792
M. Jia, A. Komeily, Y. Wang, and R. S. Srinivasan, “Adopting Internet of Things for the development of smart buildings: A review of enabling technologies and applications,” Automation in Construction, vol. 101, pp. 111–126, 2019. Available: https://doi.org/10.1016/j.autcon.2019.01.023
L. Chamari, E. Petrova, and P. Pauwels, “A web-based approach to BMS, BIM and IoT integration: a case study,” CLIMA 2022 Conference, 2022. Available: https://proceedings.open.tudelft.nl/clima2022/article/view/228
M. Callisto De Donato, E. Laurenzi, and D. Porumboiu, “A hybrid artificial intelligence to support information retrieval in smart buildings,” in Joint Proceedings of the BIR 2025 Workshops and Doctoral Consortium, vol. 4034, CEUR-WS.org, 2025, pp. 157–169. Available: https://ceur-ws.org/Vol-4034/paper79.pdf
A. Hevner and S. Chatterjee, “Design Science Research in Information Systems,” in Design Research in Information Systems. Integrated Series in Information Systems, vol. 22, 2010, pp. 9–22. Available: https://doi.org/10.1007/978-1-4419-5653-8_2
E. Laurenzi, J. Allan, N. Campos, and S. Stoller, “An Ontology-Based Meta-modelling Approach for Semantic-Driven Building Management Systems,” in Advanced Information Systems Engineering Workshops. CAiSE 2024. Lecture Notes in Business Information Processing, vol 521, 2024, pp. 200–211. Available: https://doi.org/10.1007/978-3-031-61003-5_18
B. Pang, J. Shi, L. Jiang, and Z. Pan, “A Semantic Approach to Dynamic Path Planning for Fire Evacuation through BIM and IoT Data Integration,” Advances in Civil Engineering, vol. 2024, 2024. Available: https://onlinelibrary.wiley.com/doi/10.1155/2024/8839865
L. Chamari, E. Petrova, and P. Pauwels, “An End-to-End Implementation of a Service-Oriented Architecture for Data-Driven Smart Buildings,” IEEE Access, vol. 11, pp. 117261–117281, 2023. Available: https://doi.org/10.1109/ACCESS.2023.3325767
J. Bjørnskov and M. Jradi, “An ontology-based innovative energy modeling framework for scalable and adaptable building digital twins,” Energy and Buildings, vol. 292, article 113146, 2023. Available: https://doi.org/10.1016/j.enbuild.2023.113146
M. Shahinmoghadam and A. Motamedi, “An Ontology-Based Mediation Framework for Integrating Federated Sources of BIM and IoT Data,” in Proceedings of the 18th International Conference on Computing in Civil and Building Engineering. ICCCBE 2020. Lecture Notes in Civil Engineering, vol. 98, pp. 907–923, 2020. Available: https://doi.org/10.1007/978-3-030-51295-8_63
K. Janowicz, M. H. Rasmussen, M. Lefrançois, G. F. Schneider, and P. Pauwels, “BOT: The building topology ontology of the W3C linked building data group,” Semantic Web: – Interoperability, Usability, Applicability, vol. 12, no. 1, pp. 143–161, 2020. Available: https://doi.org/10.3233/SW-200385
A. J. Donkers, D. Yang, B. de Vries, and N. H. Baken, “Real-time building performance monitoring using semantic digital twins,” in 9th Linked Data in Architecture and Construction Workshop, LDAC 2021, vol. 3081, CEUR-WS. org, 2021, pp. 55–66. Available: https://ceur-ws.org/Vol-3081/05paper.pdf
F. Lygerakis, N. Kampelis, and D. Kolokotsa, “Knowledge Graphs’ Ontologies and Applications for Energy Efficiency in Buildings: A Review,” Energies, vol. 15, no. 20, 2022. Available: https://doi.org/10.3390/en15207520
A. Donkers, D. Yang, B. de Vries, and N. Baken, “Semantic Web Technologies for Indoor Environmental Quality: A Review and Ontology Design,” Buildings, vol. 12, no. 10, article 1522, 2022. Available: https://doi.org/10.3390/buildings12101522
D. D. Eneyew, M. A. Capretz, and G. T. Bitsuamlak, “Toward Smart-Building Digital Twins: BIM and IoT Data Integration,” IEEE Access, vol. 10, pp. 130487–130506, 2022. Available: https://doi.org/10.1109/ACCESS.2022.3229370
K. El Mokhtari, I. Panushev, and J. J. McArthur, “Development of a Cognitive Digital Twin for Building Management and Operations,” Frontiers in Built Environment, vol. 8, pp. 1–18, 2022. Available: https://doi.org/10.3389/fbuil.2022.856873
C. Ramonell, R. Chacón, and H. Posada, “Knowledge graph-based data integration system for digital twins of built assets,” Automation in Construction, vol. 156, 2023. Available: https://doi.org/10.1016/j.autcon.2023.105109
J. Shi, Z. Pan, L. Jiang, and X. Zhai, “An ontology-based methodology to establish city information model of digital twin city by merging BIM, GIS and IoT,” Advanced Engineering Informatics, vol. 57, 2022, article 102114, 2023. Available: https://doi.org/10.1016/j.aei.2023.102114
I. Fatokun, A. R. N. Sheela, T. Mecharnia, M. Lefrançois, V. Charpenay, F. Badeig, and A. Zimmermann, “Modular Knowledge integration for Smart Building Digital Twins,” in Proceedings of the 11th Linked Data in Architecture and Construction Workshop, vol. 3633, CEUR-WS.org, pp. 123–138, 2023. Available: https://ceur-ws.org/Vol-3633/paper10.pdf
C. Schmid, S. Acero Gonzalez, S. Stoller, W. Willuhn, E. Laurenzi, and J. Allan, “Continuous calculation of key performance indicators for buildings through an application layer connected to a knowledge graph,” in LDAC 2025 Linked Data in Architecture and Construction, vol. 4113, CEUR-WS.org, 2025, pp. 108–121. Available: https://ceur-ws.org/Vol-4113/paper8.pdf
A. J. A. Donkers, D. Yang, and N. Baken, “Linked data for smart homes: Comparing RDF and labeled property graphs,” in LDAC 2020 Linked Data in Architecture and Construction, vol. 2636, CEUR-WS.org, 2020, pp. 23–36. Available: http://ceur-ws.org/Vol-2636/02paper.pdf
A. d’Avila Garcez and L. C. Lamb, “Neurosymbolic AI: the 3rd wave,” Artificial Intelligence Review, vol. 56, no. 11, pp. 12387–12406, 2023. Available: https://doi.org/10.1007/s10462-023-10448-w
R. Buchmann, J. Eder, H.-G. Fill, U. Frank, D. Karagiannis, E. Laurenzi, J. Mylopoulos, D. Plexousakis, and M. Y. Santos, “Large language models: Expectations for semantics-driven systems engineering,” Data & Knowledge Engineering, vol. 152, article 102324, 2024. Available: https://doi.org/10.1016/j.datak.2024.102324
G. F. Schneider and M. H. Rasmussen, “TechnicalBuildingSystems/OpenSmartHomeData: First release of Open Smart Home Data Set,” 2018. Available: https://doi.org/10.5281/zenodo.1244602
G. Schneider, M. Rasmussen, P. Bonsma, J. Oraskari, and P. Pauwels, “Linked building data for modular building information modelling of a smart home,” in eWork and eBusiness in Architecture, Engineering and Construction, 2018, pp. 407–414.
N. Noy and D. McGuinness, “Ontology development 101: A guide to creating your first ontology,” Knowledge Systems Laboratory, vol. 32, 2001.
P. Dhameniya and R. Yadav, “12 - knowledge graph-based question answering (KG-QA) using natural language processing,” in Knowledge Graph-Based Methods for Automated Driving, 2025, pp. 227–249. Available: https://doi.org/10.1016/B978-0-443-30040-0.00012-6
P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. Available: https://proceedings.neurips.cc/paper_files/paper/2020/file/6b493230205f780e1bc26945df7481e5-Paper.pdf
A. Gupta, S. Tyagi, N. Panwar, S. Sachdeva, and U. Saxena, “NoSQL databases: Critical analysis and comparison,” in 2017 International Conference on Computing and Communication Technologies for Smart Nation (IC3TSN). IEEE, 2017, pp. 293–299. Available: https://doi.org/10.1109/IC3TSN.2017.8284494
S. Tang, D. R. Shelden, C. M. Eastman, P. Pishdad-Bozorgi, and X. Gao, “A review of building information modeling (BIM) and the internet of things (IoT) devices integration: Present status and future trends,” Automation in Construction, vol. 101, pp. 127–139, 2019. Available: https://doi.org/10.1016/j.autcon.2019.01.020
B. Shah, P. M. Jat, and K. Sashidhar, “Performance study of time series databases,” arXiv preprint arXiv:2208.13982, 2022. Available: https://arxiv.org/abs/2208.13982
S. Munir and A. Aldini, “Towards evaluating large language models for graph query generation,” arXiv preprint arXiv:2411.08449, 2024. Available: https://arxiv.org/abs/2411.08449
P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha, “A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications,” 2025. Available: https://arxiv.org/abs/2402.07927
K. Rabuzin, M. Cerjan, and S. Križanić, “Supporting data types in Neo4j,” in New Trends in Database and Information Systems. ADBIS 2022. Communications in Computer and Information Science, vol. 1652, 2022, pp. 459–466. Available: https://doi.org/10.1007/978-3-031-15743-1_42
M. Callisto De Donato, F. Corradini, F. Fornari, B. Re, and M. Romagnoli, “Enabling 3D simulation in ThingsBoard: A first step towards a digital twin platform,” in Enterprise Design, Operations, and Computing. EDOC 2023 Workshops. EDOC 2023. Lecture Notes in Business Information Processing, vol. 498, 2024, pp. 325–330. Available: https://doi.org/10.1007/978-3-031-54712-6_20
M. Callisto De Donato, F. Corradini, F. Fornari, and B. Re, “SAFE: An ICT platform for supporting monitoring, localization, and rescue operations in case of earthquake,” Internet of Things, vol. 27, article 101273, 2024. Available: https://doi.org/10.1016/j.iot.2024.101273
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Emanuele Laurenzi, Massimo Callisto De Donato, Daniele Porumboiu (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
