AI-Driven Conversational Interface for Enhancing Industrial Data Accessibility in Warehouse Management Systems

Thaninrath Witoontharaphong; Manussawee Nokkaew; Chayada Surawanitkun; Kanda Sorn-In; Nongram Mueanrit; Woramat Chanapha; Satit Kravenkit; Thalerngsak Wiangwiset; Apirat Siritaratiwat

doi:10.37936/ecti-eec.2026243.262941

Authors

Thaninrath Witoontharaphong Center of Multidisciplinary Innovation Network Talent (MINT Center), Faculty of Interdisciplinary Studies, Khon Kaen University
Manussawee Nokkaew -
Chayada Surawanitkun Center of Multidisciplinary Innovation Network Talent (MINT Center), Faculty of Interdisciplinary Studies, Khon Kaen University
Kanda Sorn-In Center of Multidisciplinary Innovation Network Talent (MINT Center), Faculty of Interdisciplinary Studies, Khon Kaen University
Nongram Mueanrit Center of Multidisciplinary Innovation Network Talent (MINT Center), Faculty of Interdisciplinary Studies, Khon Kaen University
Woramat Chanapha Center of Multidisciplinary Innovation Network Talent (MINT Center), Faculty of Interdisciplinary Studies, Khon Kaen University
Satit Kravenkit Department of Computer Science, College of Computing, Khon Kaen University
Thalerngsak Wiangwiset Central Maintenance Sector, National Telecom Public Company Limited, Khon Kaen
Apirat Siritaratiwat Department of IoT and Information Engineering, Faculty of Engineering, King Mongkut’s Institute of Technology, Ladkrabang

DOI:

https://doi.org/10.37936/ecti-eec.2026243.262941

Keywords:

Natural Language Processing, WangchanBERTa, Warehouse Management System, Artificial Intelligence, Industry 5.0, Smart Factory

Abstract

AI-powered conversational interface designed to enhance industrial data accessibility in Warehouse Management Systems (WMS). The system addresses the challenge of enabling non-technical users to retrieve complex warehouse data without requiring SQL knowledge or database expertise, supporting data-driven decision-making in manufacturing operations. Our approach employs WangchanBERTa, a pre-trained Thai language model, for Natural Language Processing to interpret user intents and extract relevant entities from Thai questions. The system then converts natural language queries into SQL commands using Natural Language to SQL (NL2SQL) techniques to retrieve information from WMS databases. The proposed architecture consists of five key components, and the system's effectiveness is evaluated through implementation in a footwear manufacturing facility, where sample queries regarding inventory, stock levels, and operational metrics are tested.

Experimental results show the Intent Classification model achieves a Macro F1-Score of 87.84% and an Accuracy of 94.01%, demonstrating robust performance across multiple intent categories. System generates correct SQL queries for common warehouse queries, including product color, quantity, and stock availability. While certain complex intents exhibit lower accuracy due to contextual ambiguity and limited training data. This research provides a replicable framework to be extended to other industrial domains, thereby enhancing operational efficiency and human-AI collaboration in Industry 5.0.

Downloads

Download data is not yet available.

References

S. Ali and Y. Xie, "The impact of Industry 4.0 on organizational performance: The case of Pakistan's retail industry," European Journal of Management Studies, vol. 26, no. 2/3, pp. 63-86, 2021.

N. A. Andrew, O. O. Peter, O. M. Adeleye, O. O. James, K. Maurice, and O. Dabira, "The role of artificial intelligence in Industry 5.0: Enhancing human-machine collaboration," World, vol. 24, no. 2, pp. 380-400, 2024.

N. Ghobakhloo, “Industry 4.0, digitalization, and opportunities for sustainability,” Journal of Cleaner Production, vol. 252, p. 119869, 2020.

A. Jarašūnienė, K. Čižiūnienė, and A. Čereška, "Research on impact of IoT on warehouse management," Sensors, vol. 23, no. 4, p. 2213, 2023.

F. Krause, H. Paulheim, E. Kiesling, K. Kurniawan, M. C. Leva, H. D. Estrada-Lugo, and B. A. Moser, "Managing human-AI collaborations within Industry 5.0 scenarios via knowledge graphs: Key challenges and lessons learned," Frontiers in Artificial Intelligence, vol. 7, p. 1247712, 2024.

P. M. Mah, I. Skalna, and J. Muzam, "Natural language processing and artificial intelligence for enterprise management in the era of Industry 4.0," Applied Sciences, vol. 12, no. 18, p. 9207, 2022.

M. Minaee et al., “Deep learning–based text classification: A comprehensive review,” ACM Computing Surveys, vol. 54, no. 3, pp. 1–40, 2021.

G. Caldarini, S. Jaf, and K. McGarry, "A literature survey of recent advances in chatbots," Information, vol. 13, no. 1, p. 41, 2022.

L. Lowphansirikul, C. Polpanumas, N. Jantrakulchai, and S. Nutanong, "Wangchanberta: Pretraining transformer-based Thai language models," arXiv preprint arXiv:2101.09635, 2021.

M. A. Ardanta, A. Fauzi, P. Patimah, F. Khadijah, S. R. Yunandi, and A. M. Ghowe, "Human-AI collaboration in supply chain Industry 5.0 to build a human-centered autonomous ecosystem," Siber International Journal of Digital Business (SIJDB), vol. 2, no. 4, pp. 357-368, 2025.

Pournader, M., Ghaderi, H., Hassanzadegan, A., & Fahimnia, B. (2021). Artificial intelligence applications in supply chain management. International Journal of Production Economics, 241, 108250.

E. Vann Yaroson, A. Abadie, and M. Roux, "Human-artificial intelligence collaboration in supply chain outcomes: The mediating role of responsible artificial intelligence," Annals of Operations Research, pp. 1-35, 2025.

Y. Zhang, R. Y. Lau, J. David Xu, Y. Rao, and Y. Li, "Business chatbots with deep learning technologies: State-of-the-art, taxonomies, and future research directions," Artificial Intelligence Review, vol. 57, no. 5, p. 113, 2024.

Zulqarnain, M., Ghazali, R., Hassim, Y. M. M., & Rehan, M. (2020). A comparative review on deep learning models for text classification. Indones. J. Electr. Eng. Comput. Sci, 19(1), 325-335.

K. Majhadi and M. Machkour, "Chat-SQL: Natural language text to SQL queries based on deep learning techniques," Journal of Theoretical and Applied Information Technology, vol. 102, no. 12, pp. 5052-5061, 2024.

Liu, X., Shen, S., Li, B., Ma, P., Jiang, R., Zhang, Y., ... & Luo, Y. (2025). A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?. IEEE Transactions on Knowledge and Data Engineering.

Dihingia, H., Ahmed, S., Borah, D., Gupta, S., Phukan, K., & Muchahari, M. K. (2021, December). Chatbot implementation in customer service industry through deep neural networks. In 2021 International Conference on Computational Performance Evaluation (ComPE) (pp. 193-198). IEEE.

T. Scholak, N. Schucher, and D. Bahdanau, "PICARD: Parsing incrementally for constrained auto-regressive decoding from language models," arXiv preprint arXiv:2109.05093, 2021.

R. G. Richey Jr., S. Chowdhury, B. Davis‐Sramek, M. Giannakis, and Y. K. Dwivedi, "Artificial intelligence in logistics and supply chain management: A primer and roadmap for research," Journal of Business Logistics, vol. 44, no. 4, pp. 532-549, 2023.

M. Verma, "Integration of AI-based chatbot (ChatGPT) and supply chain management solution to enhance tracking and queries response," International Journal for Science and Advance Research in Technology, vol. 6, pp. 16-20, 2023.

P. Wongpraomas, C. Soomlek, W. Sirisangtragul, and P. Seresangtakul, "Thai question-answering system using pattern-matching approach," in Proc. 2022 1st Int. Conf. Technology Innovation and Its Applications (ICTIIA), 2022, pp. 1-5.

P. Harnmetta and T. Samanchuen, "Sentiment analysis of Thai stock reviews using transformer models," in Proc. 2022 19th Int. Joint Conf. Computer Science and Software Engineering (JCSSE), 2022, pp. 1-6.

M. Nokkaew, K. Nongpong, T. Yeophantong, P. Ploykitikoon, W. Arjharn, A. Siritaratiwat, and C. Surawanitkun, "Analyzing online public opinion on Thailand-China high-speed train and Laos-China railway mega-projects using advanced machine learning for sentiment analysis," Social Network Analysis and Mining, vol. 14, no. 1, p. 15, 2023.

H. Jeong and B. Zou, "Linear classifier models for binary classification," Variance, vol. 18, 2025.

Y. C. Lin, S. A. Chen, J. J. Liu, and C. J. Lin, "Linear classifier: An often-forgotten baseline for text classification," arXiv preprint arXiv:2306.07111, 2023.

S. Agrawal, S. K. Jain, S. Sharma, and A. Khatri, "COVID-19 public opinion: A Twitter healthcare data processing using machine learning methodologies," International Journal of Environmental Research and Public Health, vol. 20, no. 1, p. 432, 2022.

M. Nokkaew, K. Nongpong, T. Yeophantong, P. Ploykitikoon, W. Arjharn, D. Phonak, and C. Surawanitkun, "Hidden emotional trends on social media regarding the Thailand–China high-speed railway project: A deep learning approach with ChatGPT integration," Social Network Analysis and Mining, vol. 14, no. 1, p. 175, 2024.

Tharwat, A. Classification assessment methods: a detailed tutorial. Appl Comput Inform. 2020; 17: 168–92.

A. K. Sharma and R. Kumar, "IoT malware detection and mitigation in AMQP simulated environment," ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 18, no. 4, pp. 469-480, 2024.

R. Tanawongsuwan, S. Phongsuphap, and P. Mongkolwat, "Evaluating trust in CNN transfer learning with flower image classification via heatmap-based XAI," ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 19, no. 3, pp. 392-405, 2025.