Information technologies and computer sciences

Technology for Developing a Recommendation Chatbot Based on Large Language Models for IoT System Design

Authors

D. V. Honcharenko
Vinnytsia National Technical University ROR
V. B. Mokin
Vinnytsia National Technical University ROR
DOI https://doi.org/10.31649/1997-9266-2025-179-2-147-156

Keywords

Internet of Things (IoT) large language models (LLM) recommendation chatbot LPWAN, system design IT infrastructure PFD diagrams information technology information system architecture technical support

Abstract

Modern development of information technologies, particularly the Internet of Things (IoT), opens new opportunities for automating the design of systems operating on low-power wide-area networks (LPWAN). This requires novel approaches to developing the architecture of such systems and selecting technological solutions that account for the specific conditions of their use. The study utilized large language models (LLM) to create a chatbot that provides recommendations. The model was trained on a large dataset collected from scientific articles and technical documents related to LPWAN. Additionally, automated generation of structured materials for system design was implemented, considering the specific features of such networks. Main results include highly detailed and formalized stages of the developed technology, which enables the automatic formation of IoT system architectures and corresponding process flow diagrams (PFDs) based on user-provided textual descriptions. Key LPWAN characteristics and constraints, such as low power consumption, extensive but not unlimited coverage, and limited bandwidth, were taken into account. This is crucial for building efficient and scalable solutions. An approach to adapting the language model to specialized LPWAN terminology and context was developed. Techniques for dataset augmentation were described, leveraging specialized libraries and methods. As a result, the chatbot can provide accurate and professional advice, valuable for technical specialists. For instance, it suggests optimal data transmission methods under constraints on message size or transmission frequency. The quality of responses to complex technical questions has significantly improved compared to baseline model versions. Additionally, automated graphical visualization of data flows in the form of PFDs was implemented, facilitating understanding of system structure and processes. This enhances analysis and decision-making. Future research prospects involve refining the technology by expanding the knowledge base with up-to-date data and adapting it to other IoT protocols to ensure broader applicability and functionality.

666 102

How to Cite

[1]
“Technology for Developing a Recommendation Chatbot Based on Large Language Models for IoT System Design”, Вісник ВПІ, no. 2, pp. 147–156, Apr. 2025, doi: 10.31649/1997-9266-2025-179-2-147-156.

Author Biographies

D. V. Honcharenko, Vinnytsia National Technical University

Post-Graduate Student of the Chair of System Analysis and Information Technologies

V. B. Mokin, Vinnytsia National Technical University

Dr. Sc. (Eng.), Professor, Head of the Chair of System Analysis and Information Technologies

References

X. Wang, H. Hu, Y. Wang, and Z. Wang, “IoT Real-Time Production Monitoring and Automated Process Transformation in Smart Manufacturing,” J. Organizational End User Comput., vol. 36, no. 1, pp. 1-25, Jan. 2024.
S. Khemakhem, and L. Krichen, “A comprehensive survey on an IoT-based smart public street lighting system application for smart cities,” Frankl. Open, p. 100142, Aug. 2024.
M. T. Kuska, M. Wahabzada, and S. Paulus, “AI for crop production – Where can large language models (LLMs) provide substantial value?” Comput. Electron. Agriculture, vol. 221, pp. 108924, June. 2024.
M. Giudici, L. Padalino, G. Paolino, I. Paratici, A. I. Pascu, and F. Garzotto, “Designing Home Automation Routines Using an LLM-Based Chatbot,” Designs, vol. 8, no. 3, pp. 43, May. 2024.
M. Giuffrè, et al., “Systematic review: The use of large language models as medical chatbots in digestive diseases,” Alimentary Pharmacol. & Therapeutics, May. 2024.
H. Vu-Ngoc, et al., “Quality of flow diagram in systematic review and/or meta-analysis,” PLOS ONE, vol. 13, no. 6, June. 2018, рр. 1-13, № e0195955.
M. Kamble, H. Patel, S. Shinde, and P. More, “Technical Review of Performance Parameters of Long-Range IoT Protocols,” Int. J. Ingenious Res., Invention Develop., vol. 4, no. 1, pp. 50-61, 2025.
J. P. Becoña, M. Grané, M. Miguez, and A. Arnaud, “LoRa, Sigfox, and NB-IoT: An Empirical Comparison for IoT LPWAN Technologies in the Agribusiness,” IEEE Embedded Syst. Lett., p. 1, 2024.
T. Kang, “Training data and fine-tuning process for developing LLM-based BIM domain knowledge model,” J. Korea Academia-Ind. cooperation Soc., vol. 25, no. 11, pp. 177-185, 2024.
“GitHub — e-p-armstrong/augmentoolkit: Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers,” GitHub. [Electronic resource]. Available: https://github.com/e-p-armstrong/augmentoolkit .
“meta-llama/Meta-Llama-3-8B Hugging Face,” Hugging Face – The AI community building the future. [Electronic resource]. Available: https://huggingface.co/meta-llama/Meta-Llama-3-8B .
D. M. Anisuzzaman, J. G. Malins, P. A. Friedman, and Z. I. Attia, “Fine-Tuning LLMs for Specialized Use Cases,” Mayo Clinic Proc.: Digit. Health, Nov. 2024.
X. Wang, and L. Aitchison, “How to set AdamW's weight decay as you scale model and dataset size,” arXiv preprint, arXiv:2405.136982, 2025.
“GitHub — mermaid-js/mermaid: Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown,” GitHub. [Electronic resource]. Available: https://github.com/mermaid-js/mermaid .

Most read articles by the same author(s)

1 2 3 4 5 6 7 > >>