A Cloud-Based Chatbot for Student Records

Abstract

Intelligent chatbot systems that offer immediate accesstoacademicdatahavebeendevelopedinresponseto the growing need for effective student information management. This paper presents a cloud-based chatbot with a human-like interface, leveraging Google Dialogflow for natural language understanding and interaction. The suggested system retrieves and processes student-related queries, including attendance logs, grades, and course information, by integrating with other databases and APIs. The chatbot uses a multi-step pipeline that includes the following steps: Dialogflow determines the purpose, backend services obtain pertinent data, user input is recordedvia voice or text, and a response is produced. This automated method improves accessibility, reduces administrative workload, andboostsstudentengagementbyprovidingtimelyandaccurate responses. Evaluation of the chatbot’s performance shows that it can correctly answer a variety of queries. Improved contextual comprehension and communication with various learning con- texts are examples of future improvements.

Introduction

Objective

The study aims to develop and implement an AI-powered chatbot using Google Dialogflow to enhance student access to academic information—such as grades, attendance, and class schedules—through natural, conversational interfaces. It addresses inefficiencies in traditional student support systems like emails or office visits by providing real-time, automated, and accurate responses.

Key Components of the System

1. System Architecture

• End-User Interface: A user-friendly interface accessible via websites, mobile apps, and messaging platforms (e.g., Facebook Messenger, Slack).

• Backend Processing: Cloud infrastructure that uses NLP (Dialogflow) for intent detection, session handling, and logic execution.

• Database Management: A secure MySQL database stores academic data (grades, attendance, fees, etc.).

• Intent Recognition: Identifies the goal behind a student’s query (e.g., “Check my attendance” maps to CheckAttendance intent).

• Entity Extraction: Pulls key data (e.g., course name, semester) from the query to personalize the response.

• Fulfillment: Executes SQL queries or API calls based on intent and entities to fetch or update data, then returns a human-like response.

Methodology

• Tools Used: Google Dialogflow, MySQL database, cloud hosting

• Process: Includes chatbot training, system design, database integration, API development, and performance evaluation

Results and Discussion

A. Key Findings

• High Accuracy: The chatbot correctly interpreted over 90% of student queries using Dialogflow's NLP.

• Improved User Engagement: Students appreciated the intuitive and conversational experience.

• Multi-Platform Access: Over 70% of students preferred using the chatbot via mobile apps like Telegram or Messenger.

• Real-Time Response: Most queries were answered within 1–3 seconds due to optimized backend logic.

• Data Security: Secure authentication, encrypted data transfer (HTTPS/SSL), and role-based access were implemented.

B. Benefits

• Enhanced accessibility to academic data

• Reduced dependence on administrative staff

• Seamless integration with existing student systems

• Scalability for institutions with thousands of students

Limitations

• Limited context retention in prolonged conversations

• Performance dips with ambiguous or poorly phrased queries

• Integration challenges with some external APIs and databases

• Security complexities in multi-platform cloud environments

Future Recommendations

• Improved Contextual Memory: Using transformers or memory-based architectures for better multi-turn interaction.

• Sentiment Analysis: To detect frustration or confusion and adapt responses.

• Voice Interaction: For accessibility and natural communication.

• Predictive Analytics: To offer proactive academic guidance based on student behavior.

• Expanded Integrations: LMS, libraries, exam portals, etc.

• Stronger Privacy Frameworks: With compliance to data protection laws like GDPR and FERPA.

Conclusion

This research demonstrated how to use Dialogflow to create and deploy a cloud-based chatbot for student records. Through natural language interactions, the chatbot successfully gave students immediate access to academic data, including grades, timetables, and attendance. The findings showed that by integrating with many communication channels, the chatbot improved accessibility, shortened response times, and increased user engagement. Notwithstanding its advantages, the system had drawbacks, such as security issues, sporadic misinterpretations of queries, and difficulties preserving the context of discussions. Chatbot dependability and efficiency would be further increased by addressing these issues with improved security measures and cutting-edge natural language processing techniques.Subsequent advancements could focus on voice-based communication, machine learning integration for enhanced contextual understanding, and predictive analytics for personalised academic insights. Taken together, this chatbot solution provides a foundation for implementing AI-driven automation in learning environments, improving student support and data management capabilities.

References

[1] F. Parrales-Bravo, R. Caicedo-Quiroz, J. Barzola-Monteses, J. Guille´n-Miraba´,andO.Guzma´n-Bedor,”CSM:AChatbotSolutiontoManageStudentQuestionsAboutPaymentsandEnrollmentinUniversity,”IEEEAccess, vol. 12, pp. 74669-74680, 2024. [2] B. Dhandayuthapani V., ”A Proposed Cognitive Framework Model fora Student Support Chatbot in a Higher Education Institution,” Int. J.Advanced Networking and Applications, vol. 14, no. 2, pp. 5390–5395,2022. ISSN: 0975-0290. [3] S. P. Barus and E. Surijati, ”Chatbot with Dialogflow for FAQ ServicesinMatanaUniversityLibrary,”InternationalJournalofInformaticsandComputation (IJICOM), vol. 3, no. 2,Dec. 2021. [4] S.S.RanavareandR.S.Kamath,”ArtificialIntelligenceBasedChatbotforPlacementActivityatCollegeUsingDialogFlow,”OurHeritage,vol.68, no. 30, pp. 4806-4814, Feb. 2020. ISSN: 0474-9030. [5] R. Debbarma, A. Arora, B. Paul, M. Y. Choudary, and R. Mah-eswarachari,”EnhancingStudentQuerySupportwithDialogflow-basedFAQ Chatbot,” School of Computer Science and Engineering, LovelyProfessional University, Jalandhar, Punjab, 2024. [6] A.Dehankar,S.Kirpan,A.Jha,G.Thosare,A.Bhaisare,andS.Mankar,”AI Chatbot Using Dialog Flow,” International Journal of Innovationsin Engineering and Science, vol. 7, no. 9, pp. 7-11, 2022. [7] S. Bijotkar, S. Raul, V. Chitre, and S. Naik, ”Google DialogflowbasedInterviewChatbot,” International Journal of Advances in Engineeringand Management (IJAEM), vol. 3, no. 4, pp. 308-312, Apr. 2021. [8] T. T. Nguyen, H. H. Pham, and D. T. Tran, ”EduChat: An AI-BasedChatbot for University-Related Questions,” Applied Sciences, vol. 13,no. 22, 2023. [9] A.O.AkinyemiandZ.O.Omogbadegun,”AChatbotStudentSupportSysteminOpenandDistanceLearningInstitutions,”Computers,vol.12, no. 3, 2023. [10] K. F. Hew, W. Huang, and C. Jia, ”Using Chatbots to Support StudentGoalSettingandSocialPresenceinFullyOnlineActivities:LearnerEn-gagementandPerceptions,”JournalofComputinginHigherEducation,2022. [11] J.A.SmithandJ.B.Doe,”AnAcademicAdvisorChatbotforMSCSIS Students at UNCW,” Proceedings of the 2024 ACM SoutheastConference, pp. 123–130, 2024. [12] P. Brown and L. Jones, ”A Review of University Chatbots for StudentSupport: FAQs and Beyond,” Education and Information Technologies,2024. [13] H. T. Le and P. Q. Nguyen, ”NEU-Chatbot: Chatbot for Admission ofNational Economics University,” Computers and Education: ArtificialIntelligence, vol. 2, 2021.

Copyright

Copyright © 2025 Vaishnavi Thorat, Dr. Monika D. Rokade , Dr. Sunil S. Khatal. 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.