Leveraging Large Language Models for Natural Language Interface in ERP Systems: A Case Study in User Productivity and Cognitive Load
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I4P113Keywords:
ERP system, Large Language Model, Natural Language Interface, Cognitive Load, User Productivity, Human Computer InteractionAbstract
The Enterprise Resource Planning (ERP) systems are complex and time-consuming to learn, making them difficult for users. Large Language Models (LLMs) have introduced Natural Language Interfaces (NLIs), allowing users to interact with ERP systems in a conversational way. This paper examines the design, implementation, and testing of a Natural Language Interface (NLI) using LLM within a cloud-based ERP solution. The study found that the LLM-powered interface reduced task completion time by 28% and reduced cognitive workload across all dimensions. Respondents expressed increased confidence in performing ERP-related tasks compared to traditional navigation methods. LLM-powered interfaces can make ERP easier to use, reduce training requirements, and accelerate digital adoption in business settings. The paper also contributes real-world data to understanding human-AI interaction and serves as a design guide for implementing LLM-based NLIs in mission-critical business systems
Downloads
References
[1] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
[2] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019, June). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers) (pp. 4171-4186).
[3] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
[4] Schmidhuber, J., & Hochreiter, S. (1997). Long short-term memory. Neural Comput, 9(8), 1735-1780.
[5] Werbos, P. J. (2002). Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10), 1550-1560.
[6] Hearst, M. A. (1997). Text tiling: Segmenting text into multi-paragraph subtopic passages. Computational linguistics, 23(1), 33-64.
[7] Graves, A. (2012). Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711.
[8] Miller, R. B. (1968, December). Response time in man-computer conversational transactions. In Proceedings of the December 9-11, 1968, fall joint computer conference, part I (pp. 267-277).
[9] Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive science, 12(2), 257-285.
[10] Mayer, R. E. (2005). Cognitive theory of multimedia learning. The Cambridge handbook of multimedia learning, 41(1), 31-48.
[11] Nielsen, J. (1994). Usability engineering. Morgan Kaufmann.
[12] Sears, A., & Jacko, J. A. (Eds.). (2009). Human-computer interaction: Development process. CRC Press.
[13] Card, S. K., Mackinlay, J., & Shneiderman, B. (Eds.). (1999). Readings in information visualization: using vision to think. Morgan Kaufmann.
[14] Al-Mashari, M. (2003). Enterprise resource planning (ERP) systems: a research agenda. Industrial Management & Data Systems, 103(1), 22-27.
[15] Nielsen, J., & Landauer, T. K. (1993, May). A mathematical model of the finding of usability problems. In Proceedings of the INTERACT'93 and CHI'93 conference on Human factors in computing systems (pp. 206-213).
[16] Chalmers, P. A. (2003). The role of cognitive theory in human–computer interface. Computers in human behavior, 19(5), 593-607.
[17] Zhao, J. X., Xie, Y., Kawaguchi, K., He, J., & Xie, M. Q. (2023). Automatic model selection with large language models for reasoning. arXiv preprint arXiv:2305.14333.
[18] Ravindra, V., & Castellini, C. (2014). A comparative analysis of three non-invasive human-machine interfaces for the disabled. Frontiers in neurorobotics, 8, 24.
[19] Zhang, S., & Le Duigou, J. (2022, June). Implementing vocal natural language interface to enterprise resource planning system. In International Joint Conference on Mechanics, Design Engineering & Advanced Manufacturing (pp. 399-409). Cham: Springer International Publishing.
[20] Al Siyabi, W. S. A., & Al Minje, Y. (2021, August). A conceptual review on integration of cognitive load theory and human-computer interaction. In 2021 International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM) (pp. 667-672). IEEE.
