AI Chatbot for College Queries

Abstract

This project focuses on developing and deploying an AI-driven chatbot using Dialogflow to assist with college-related inquiries, seamlessly integrated into the institution’s website. Designed to efficiently handle questions about admissions, academic programs, faculty details, campus facilities, examination schedules, and general policies, the chatbot delivers quick and precise responses. By providing instant support around the clock, it enhances the accessibility of information while reducing the administrative burden.Powered by Natural Language Processing (NLP) through Dialogflow, the chatbot interprets user inputs in natural language and generates relevant responses. Integration with FastAPI and MySQL ensures real-time data retrieval from the backend, ensuring reliability and efficiency. This system enhances user experience by offering consistent and accurate information on topics such as course structures, faculty contact details, tuition fees, hostel accommodations, and campus resources all without requiring human intervention. Furthermore, it contributes to better information management by improving transparency and efficiency in communication, reinforcing the institution’s digital presence with a modern, AI-powered solution. Future enhancements may include machine learning-driven improvements for deeper contextual understanding, multilingual support, and integration with student portals for personalized services. Overall, this project highlights the transformative role of AI in education, offering a scalable and cost-effective approach to streamlined information dissemination.

Introduction

Overview

The AI Chatbot for College Queries is designed to streamline access to academic and administrative information in educational institutions. It addresses common issues students and faculty face—such as navigating websites or waiting for assistance—by offering a conversational, AI-powered interface that delivers real-time, accurate responses using Natural Language Processing (NLP) and machine learning.

Key Features

• Real-time query resolution using Google Dialogflow.

• Role-based access for secure information retrieval by students and faculty.

• FastAPI backend integrated with a MySQL database for dynamic data handling.

• Authentication using JWT (JSON Web Tokens) for security.

• Access to academic records, attendance, admission details, faculty info, and more.

• 24/7 availability via the college website.

System Architecture

The chatbot uses a three-tier system:

1. Frontend Interface – Embedded chatbot on the college website for user interaction.

2. Dialogflow NLP Engine – Understands and classifies user queries.

3. FastAPI + MySQL Backend – Executes authenticated queries and returns data securely.

Methodology

• Intent Recognition via Dialogflow.

• Query Handling by FastAPI backend.

• Secure Data Access with JWT authentication.

• Optimized Database Queries ensure fast performance under load.

• Continuous Learning via ML-based intent refinement.

Performance & Results

• Achieved 99–100% accuracy across various queries (admission, hostel, faculty, course info).

• Handled high concurrent loads with minimal latency.

• Greatly reduced administrative workload.

• Consistently outperformed traditional/manual systems in speed, accuracy, and scalability.

Comparison to Existing Systems

Conclusion

The development and implementation of the AI Chatbot for College Queries mark a significant achievement in automating student, faculty, and general administrative inquiries. By retrieving accurate information from the backend database, the chatbot enhances accessibility, efficiency, and user convenience while reducing administrative workload. A key advantage of this chatbot is its ability to automate frequent queries, ensuring instant access to essential information such as course offerings, faculty details, and fee structures. This minimizes the need for manual intervention, allowing college staff to focus on more complex tasks. Future enhancements could include: • Advanced machine learning for improved intent recognition and contextual understanding. • Sentiment analysis to better interpret user emotions and provide appropriate responses. • Multi-language support for a more inclusive user experience. • Integration with student portals and college management systems to streamline processes like attendance tracking and fee inquiries. Overall, the AI Chatbot lays a strong foundation for innovation in educational technology. By automating routine tasks and delivering instant, accurate responses, it presents a scalable, cost-effective solution that enhances efficiency and user experience in educational institutions.

References

[1] Sah, Ajay (2023). Building a Chatbot using Dialogflow: A Proof-of-Concept Demonstration. [2] Humayun Kabir Shaon (2020). DEVELOPMENT OF A CLOUD BASED IN TERACTIVE QUERY REPLY SYSTEM FOR AN ENTERPRISE: A CASE STUDY [3] Dr. (Mrs). Archana Dehankar, Shyamal Kirpan, Abhayraj Jha, Gitesh Thosare, Adarsh Bhaisare, Sumit Mankar (2022). AI CHATBOT USING DIALOGFLOW [4] Pica Salsabila Atmauswan, Akibu Mahmoud Abdullahi (2022). INTELLI GENT CHATBOT FOR UNIVERSITY INFORMATION SYSTEM USING NATURAL LANGUAGE APPROACH [5] Meennapa Rukhiran, Paniti Netinant (2022). Automated information retrieval and services of graduate school using chatbot system [6] Bhagwat, V. A. (2018). Deep learning for chatbots. [7] Biswas, M., Biswas, M., 2018. IBM Watson Chatbots. Beginning AI Bot Frameworks: Getting Started with Bot Development, pp.101-137. [8] Bradesko, L., and Mladenic, D. (2012, October). A survey of chatbot systems through a loebner prize competition. In Proceedings of Slovenian language technologies society eighth conference of language technologies (Vol. 2, pp. 34-37). Sn. [9] Canonico, M., De Russis, L. (2018). A comparison and critique of natural language understanding tools. Cloud Computing, 2018, 120. [10] Chizhik, A. and Zherebtsova, Y., 2020. Challenges of Building an Intelligent Chatbot. In IMS (pp. 277-287) [11] Manal M. A. Abdelmoiz, Mohamed M. M. Mostafaand Taysir H. A. Soliman (2024). Developing an Educational Chatbot for Scientific Data Management Course Using DialogFlow [12] Pedro Filipe Oliveira and Paulo Matos (2023). Introducing a Chatbot to the Web Portal of a Higher Education Institution to Enhance Student Interaction [13] Muhammad Shahroze Ali; Farooque Azam; Aon Safdar; Muhammad Waseem Anwar (2022). Intelligent Agents in Educational Institutions: NEdBOT – NLP-based Chatbot for Administrative Support Using DialogFlow [14] Rohit Debbarmaa , Ankkita Arora, Bishwanath Paulc, Mannem Yashwanth Choudary, Ramagiri Maheswaracharie(2024). Enhancing Student Query Support with Dialogflow Based Faq Chatbot [15] Oghenetega Erekata, Ambrose Azeta, Sanjay Misra, Modupe Odusami & Ravin Ahuja (2021). Development of a Text and Speech Enabled Conversational Agent for Students’ Activities Planning Using Dialog Flow

Copyright

Copyright © 2025 Safwa Samad, Mohammed Hashim O A, Anjali N B, Adwaith Nidheesh, Dr. L. C. Manikandan. 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.