AI-Driven ChatBot for INGRES: An Intelligent Virtual Assistant for India's Groundwater Resource Estimation System

Main Article Content

Meenal Joshi

Abstract

Basically, every year India checks itself out many groundwater stuff which is called INGRES. It's like GIS web platform which was built-up by CGWB and IIT Hyderabad for the ministry of Jal Shakti department. Even though it's got a humongous database, tackling how you get the info you need is still a pain to researchers, policy makers, and regular folks. So, in this paper we're suggesting an AI powered chatbot but it will plug right into INGRES. It allows you to ask questions in pure languages while giving you the ability to question in real time data past data and realistic instant pop out graph and even certain Indian languages. The tech behind the bot is based on top-tier NLP tools such as Sentence Transformers and Google Generative AI which is able to catch what you are asking for, along with pulling out the right data from the INGRES DB. The entire thing is running on a Fast API (back end), React/Next.js (front end) and a PostgreSQL database with GIS extensions, which is also containerized within Docker and stack on the cloud. This should make accessing ground water info way easier and help everyone from scientist to policy makers to make smarter decisions for water sustainability

Article Details

Section

Articles

Author Biography

Meenal Joshi

Department of CSE

Geetanjali Institute of Technical Studies

Udaipur, Rajasthan, India

References

[1] P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, “SQuAD: 100,000+ Questions for Machine Comprehension of Text,” in Proc. EMNLP, 2016, pp. 2383–2392.

[2] Z. Chen, X. Chang, Y. Park, J. Park, and X. Ren, “NLPGIS: Natural Language Interface to Geospatial Query Systems,” in Proc. ACM SIGSPATIAL, 2021, pp. 1–10.

[3] Ajay Maru, Ajay Kumar Sharma, Mayank Patel, “Hybrid Machine Learning Classification Technique for Improve Accuracy of Heart”, Proceedings of the Sixth International Conference on Inventive Computation Technologies [ICICT 2021], 2021, IEEE Xplore Part Number: CFP21F70-ART; ISBN: 978-1-7281-8501-9, pp. 1107-1110

[4] A. Kunchukuttan, P. Mehta, and P. Bhattacharyya, “The IIT Bombay English-Hindi Parallel Corpus,” in Proc. LREC, 2018. [Online]. Available: http://www.cfilt.iitb.ac.in

[5] T. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1877–1901.

[6] P. Trivedi, M. Sharma, and A. Verma, “Impact of Conversational AI in Resolving Citizen Queries in E-Governance Portal,” International Journal of e-Government Research, vol. 17, no. 3, pp. 45–62, 2021.

[7] Central Ground Water Board (CGWB), “Dynamic Ground Water Resources of India,” Ministry of Jal Shakti, Govt. of India. [Online]. Available: https://cgwb.gov.in

[8] Sharma, A., M. Patel, and M. Tiwari. "A comparative study to detect fraud financial statement using data mining and machine learning algorithms." International Research Journal of Engineering and Technology (IRJET) 6.8 (2019): 1492-1495.

[9] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” in Proc. EMNLP, 2019, pp. 3982–3992.

[10] Google DeepMind, “Gemini: A Family of Powerful Multimodal Models,” Technical Report, 2023. [Online]. Available: https://deepmind.google/technologies/gemini