Natural Language Interfaces for Enterprise Resource Planning: A Deep Learning Approach for Conversational SAP Systems
Keywords:
Natural Language Processing, SAP, Enterprise Resource Planning, Conversational AI, Deep Learning, Human-Computer InteractionAbstract
Enterprise Resource Planning (ERP) systems like SAP have traditionally relied on structured user interfaces that require extensive training and domain expertise. With the rise of natural language processing (NLP), there is increasing potential to design conversational agents that enable intuitive access to ERP functionalities using natural language. This paper proposes a deep learning-based approach to developing Natural Language Interfaces (NLIs) for SAP systems. It evaluates architecture designs, model performance, usability metrics, and outlines challenges in integrating such systems into complex enterprise workflows. We demonstrate that transformer-based NLP models, when integrated with ERP backend logic, can significantly enhance user experience and reduce training time.
References
Androutsopoulos, I., Ritchie, G. D., & Thanisch, P. (1995). Natural language interfaces to databases – An introduction. Natural Language Engineering, 1(1), 29–81.
Uppuluri, V. (2019). The Role of Natural Language Processing (NLP) in Business Intelligence (BI) for Clinical Decision Support. ISCSITR-International Journal of Business Intelligence (ISCSITR-IJBI), 1(2), 1–21. https://doi.org/10.63397/ISCSITR-IJBI_2019_01_02_001
Berant, J., Chou, A., Frostig, R., & Liang, P. (2013). Semantic parsing on Freebase from question-answer pairs. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1533–1544.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Dong, L., & Lapata, M. (2016). Language to logical form with neural attention. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 33–43.
Potla, R.B. (2021). Value-Stream-Aligned Order-to-Cash in SAP S/4HANA: Lead-Time Compression with ATP/BOP and aTO/Pegging Strategies. Journal of Computer Science and Technology Studies, 3(1), 18–26. https://doi.org/10.32996/jcsts
Potla, R.B. (2021). Value-Stream-Aligned Order-to-Cash in SAP S/4HANA: Lead-Time Compression with ATP/BOP and aTO/Pegging Strategies. Journal of Computer Science and Technology Studies, 3(1), 18–26. https://doi.org/10.32996/jcsts
Fuchs, F., et al. (2017). Conversational interfaces for enterprise resource planning systems. Proceedings of the 13th International Conference on Wirtschaftsinformatik, 1357–1371.
Krishnan, A., et al. (2019). ERP Assistants: Intelligent agents for enterprise workflows. Proceedings of the 2019 AAAI Workshop on Intelligent Conversational Interfaces, 22–29.
Li, F., & Jagadish, H. V. (2014). Constructing an interactive natural language interface for relational databases. Proceedings of the VLDB Endowment, 8(1), 73–84.
Popescu, A. M., Etzioni, O., & Kautz, H. (2003). Towards a theory of natural language interfaces to databases. Proceedings of the 8th International Conference on Intelligent User Interfaces, 149–157.
Uppuluri, V. (2019). The Role of Natural Language Processing (NLP) in Business Intelligence (BI) for Clinical Decision Support. ISCSITR-International Journal of Business Intelligence (ISCSITR-IJBI), 1(2), 1–21. https://doi.org/10.63397/ISCSITR-IJBI_2019_01_02_001
Tang, L., et al. (2019). A conversational interface for business process automation. Proceedings of the 2019 IEEE International Conference on Services Computing, 162–169.
Yu, T., et al. (2018). Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 3911–3921.
