AI-Based Farmer Query Support and Advisory System

Abstract

Agriculture plays a vital role in ensuring food security and supporting the livelihoods of millions of farmers worldwide. However, farmers often face difficulties in obtaining timely and accurate agricultural guidance related to crop diseases, pest management, soil fertility, weather conditions, and fertilizer usage. Traditional agricultural advisory systems usually depend on physical visits to experts or agricultural offices, which can be time-consuming and inaccessible for farmers in remote areas. Consequently, there is a growing need for a digital platform that can provide instant agricultural support and reliable information. Artificial Intelligence has emerged as a powerful technology that can improve decision-making in agriculture by analyzing farmer queries and delivering relevant solutions in real time. The AI Based Farmer Query Support and Advisory System is designed as an intelligent web-based platform that assists farmers by answering their agricultural questions through an interactive chatbot interface. The system uses Artificial Intelligence and Natural Language Processing to understand farmer queries and generate appropriate responses based on agricultural knowledge and expert recommendations. The platform was developed using modern web technologies such as Next.js and Express.js to provide a responsive and user-friendly interface. Farmers can submit queries related to crops, fertilizers, pest control, soil health, and livestock management, and the system processes the input using an AI model to generate meaningful and practical suggestions. By providing quick access to agricultural knowledge, this system helps bridge the gap between farmers and agricultural experts. Overall, the proposed system improves accessibility to agricultural information, supports better decision-making, and promotes sustainable farming practices through the use of intelligent digital technologies.

Introduction

Agriculture is vital for economic development and food security, especially in developing countries. However, farmers face challenges such as crop diseases, pests, soil issues, weather changes, and limited access to expert guidance. Traditional advisory systems are often slow, inaccessible, or not interactive, particularly for rural farmers. To address these limitations, the proposed AI-Based Farmer Query Support and Advisory System uses Artificial Intelligence (AI) and Natural Language Processing (NLP) to provide real-time agricultural guidance through a web-based chatbot platform.

The system allows farmers to ask questions related to crops, fertilizers, pest control, irrigation, and farming practices. It processes queries using NLP, retrieves relevant information from an agricultural knowledge base, and generates accurate responses instantly. The platform is built using modern web technologies and designed to be user-friendly and accessible to farmers with limited digital skills.

The literature review highlights growing research in AI-based agricultural advisory systems, including RAG models, chatbots, and multi-agent frameworks. Compared to traditional systems, the proposed solution offers faster responses, personalized recommendations, and improved accessibility.

The system architecture includes modules for user interaction, query processing, AI analysis, knowledge retrieval, and response generation. Testing results show that the system effectively interprets queries, provides accurate recommendations, operates efficiently, and delivers real-time support with an overall user-friendly experience.

Conclusion

The development of the AI-Based Farmer Query Support and Advisory System successfully demonstrated an efficient and accessible solution for providing agricultural guidance to farmers. By integrating artificial intelligence, natural language processing, and a web-based interface, the system enables farmers to submit queries and receive instant recommendations related to crop management, pest control, fertilizers, irrigation, and other agricultural practices. This approach helps farmers obtain reliable information quickly, improving decision-making and reducing their dependency on manual advisory services. The user-friendly design of the system allows farmers to easily interact with the platform through a simple web interface. The integration of an AI processing module with an agricultural knowledge base ensures that relevant and meaningful responses are generated for different types of farming queries. This makes the system suitable for farmers with varying levels of technical knowledge and improves the accessibility of agricultural information. Furthermore, the modular architecture of the system allows for future enhancements, such as multilingual support, voice-based query input, and integration with weather or market data. These improvements can further enhance the effectiveness of the advisory system and expand its usability for a wider farming community. Overall, this project demonstrates the potential of AI-driven digital advisory systems to transform agricultural knowledge delivery. By providing quick access to farming information and recommendations, the proposed system can support farmers in improving productivity, managing crop-related issues and adopting better agricultural practices for sustainable farming.

References

[1] Sawant, R. Nair, and S. Hariharan, “Empowering farmers with artificial intelligence: A retrieval-augmented generation based large language model advisory framework,” 2026. [2] S. Sultana, M. Rahman, and T. Hossain, “AI driven smart agriculture advisory system,” 2026. [3] Y. Zhang, L. Chen, and S. Park, “Generative AI and chatbot-based advisory in agricultural extension,” 2026. [4] J. Miller, R. Gupta, and A. Thompson, “AI AgriBench: Benchmarking advisory accuracy and trustworthiness,” 2026. [5] R. Cantonjos and P. Biswas, “AgroAskAI: A multi-agentic AI framework for supporting smallholder farmers’ enquiries globally,” 2025. [6] D. Johnson, H. Patel, and R. Singh, “AI-powered smart farming advisor for precision agriculture,” 2026. [7] M. Arefin, “AGRO AI: Personalized real-time advisory and monitoring for farmers,” 2026. [8] R. Sharma, S. Mehta, and P. Verma, “AI and data-driven agricultural advisory services: Global adoption patterns and extension efficiency,” 2025. [9] K. Reddy, “Agri Assist: An AI integrated farmer assistant,” 2025. [10] S. Ahmed and M. Rahman, “AI agricultural chatbot (Agri-bot),” 2025. [11] R. Verma and K. Patel, “AI chatbot for farmers: Transforming agriculture productivity,” 2025. [12] J. Lee and H. Kim, “Conversational AI for farmers,” 2025. [13] A. Singh and N. Gupta, “Farmers assistance using AI chatbot,” 2025. [14] S. Das and P. Chatterjee, “Agri-friendly conversational AI chatbot using open models,” 2025.

Copyright

Copyright © 2026 Mr. S. Manoj Kumar, Mr. C. Devaraj, Mrs. B. Nanthini . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.