Query-Web AI Integrated Platform for Educational Resource Management and Intelligent Answer Support

Abstract

The growing digitization trend in higher education has led to an increased need for a centralized, scalable, and intelligent academic management system that can handle the integration of resource distribution, analytics, and automated support services. This paper provides a comprehensive review and architectural analysis of QueryWeb, an AI-driven educational resource management system integrated with a conversational chatbot built using the Rasa framework. QueryWeb is a role-based, web-supported system designed to centralize academic resources, automate the distribution of structured content, and offer intelligent model answer support to students. The system uses standard web technologies such as PHP, MySQL, HTML, CSS, and JavaScript, along with AI-driven query processing techniques to provide efficient and accurate results. The system uses a centralized database design to manage users, topics, resources, and download history with strict authentication and access control for students, faculty, and administrators. The proposed architecture focuses on scalability, digital resource organization, and analytics for monitoring user engagement and resource usage. The system provides data-driven academic and institutional decision support by tracking interaction logs and usage history. Comparison with manual systems shows improvements in accessibility, administrative convenience, response time, and overall system transparency.

Introduction

The text introduces QueryWeb, an integrated educational resource management and AI-powered query support system designed to overcome inefficiencies in traditional academic systems. Conventional methods (emails, messaging apps, and scattered portals) lead to poor content organization, limited accessibility, lack of tracking, and increased administrative workload.

QueryWeb leverages Artificial Intelligence (AI) and Learning Management System (LMS) concepts to centralize academic resources, automate query handling through a chatbot, and provide analytics for data-driven decision-making. It offers features such as role-based authentication, download tracking, and modular scalability.

The system architecture follows a three-tier design:

• Presentation Layer: User interface built with HTML, CSS, and JavaScript.

• Application Layer: Handles logic, authentication, and chatbot integration using PHP and Rasa.

• Database Layer: MySQL database for storing users, resources, and activity logs.

The system workflow includes user login, role-based access (student, faculty, admin), resource upload/download, chatbot-based query resolution, and analytics tracking.

Compared to traditional systems, QueryWeb provides:

• Centralized storage instead of scattered resources,

• AI-based instant query responses instead of manual replies,

• Structured analytics instead of no monitoring,

• Secure role-based access instead of basic login systems,

• Better scalability and flexibility.

The methodology involves:

• Storing structured academic data in a database,

• Training an AI chatbot using intent classification, entity recognition, and context tracking,

• Implementing decision logic to match user queries with relevant resources or responses,

• Logging all interactions for analytics and performance monitoring.

Results show that QueryWeb significantly improves:

• Query response time (instant vs manual),

• Resource accessibility,

• Student engagement (tracked via analytics),

• Learning history management,

• Efficiency and accuracy of academic support.

Advantages include:

• Centralized repository,

• AI-driven academic assistance,

• Learning behavior tracking,

• Secure multi-role access,

• Scalable architecture.

Applications extend to colleges, universities, coaching centers, online learning platforms, and training organizations.

Conclusion

This review has concluded that QueryWeb is a successful attempt at integrating centralized educational resource management systems and AI-based intelligent answer support systems under a unified and scalable digital platform, as its architectural design, chatbot-based intelligent answer support, role-based authentication, and analytics-based monitoring mechanisms are all well-suited to current academic technology paradigms, as validated by relevant research-based mapping. Thus, QueryWeb, when compared to traditional academic systems, provides better resource accessibility, query answer support, and engagement tracking, making its three-tiered architectural design more scalable, maintainable, and adaptable to current educational institutions, while its centralized control and analytics-based monitoring mechanisms improve its operational efficiency. Thus, QueryWeb is a modern solution for current academic systems, reducing operational complexities, providing smart academic support, and making it a suitable solution for smart campuses and smart learning environments.

References

REFERENCES [1] Labadze, L., Grigolia, M. & Machaidze, L. Role of AI chatbots in education: systematic literature review. Int J Educ TechnolHighEduc 20,56(2023).https://doi.org/10.1186/s41239-023-00426-1 [2] Kuhail, M.A., Alturki, N., Alramlawi, S. et al. Interacting with educational chatbots: A systematic review. Educ Inf Technol 28, 973–1018 (2023). https://doi.org/10.1007/s10639-022-11177-3 [3] S. Winkler & M. Söllner, “Unleashing the potential of chatbotsineducation,”PACIS,2018.https://ijte.net/index.php/ijte/article/view/1470 [4] Huang, W., Jiang, J., King, R.B. et al. Chatbots and student motivation: a scoping review. Int J Educ Technol High Educ 22, 26 (2025). https://doi.org/10.1186/s41239-025-00524-2 [5] Engeness, I., Nohr, M., Fossland, T. (2026). AI Chatbots for Educators: Transforming Online Learning in Higher Education. In: Hamonic, E., Sharrock, R. (eds) Digital Education: Shaping Sustainable Lifelong Learning for All in the Era of AI. EMOOCS 2025. Lecture Notes in Computer Science, vol 15733. Springer, Cham. https://doi.org/10.1007/978-3-032-00056-9_18. [6] T. Bocklisch et al., “Rasa: Open source language understanding and dialogue management,” arXiv, 2017. https://doi.org/10.48550/arXiv.1712.05181 [7] Bibauw, S., François, T., & Desmet, P. (2019). Discussing with a computer to practice a foreign language: research synthesis and conceptual framework of dialogue-based CALL. Computer Assisted Language Learning, 32(8), 827–877. https://doi.org/10.1080/09588221.2018.1535508 [8] R. Nkambou, J. Bourdeau, and R. Mizoguchi, Advances in Intelligent Tutoring Systems, Springer, Berlin, Heidelberg, 2010. DOI: https://doi.org/10.1007/978-3-642-14363-2 [9] Coates, H., James, R., & Baldwin, G. (2005). A critical examination of the effects of learning management systems on university teaching and learning. Tertiary Education and Management, 11(1),19.36.:https://doi.org/10.1080/13583883.2005.9967137 [10] G. Siemens and R. S. J. d. Baker, “Learning Analytics and Educational Data Mining: Towards Communication and Collaboration,” in Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (LAK ’12),2012,pp.252254.https://doi.org/10.1145/2330601.2330661 : [11] P. Dillenbourg, “Virtual Learning Environments,” in Learning in the New Millennium: Building New Education Strategies for Schools, EUN Conference 2000, Workshop on VirtualLearningEnvironments,Geneva,2000.: https://tecfa.unige.ch/tecfa/publicat/dil-papers-2/Dil.7.5.18.pdf [12] J. Hirschberg and C. D. Manning, “Advances in natural language processing,” Science, vol. 349, no. 6245, pp. 261–266, 2015. https://doi.org/10.1126/science.aaa8685 [13] R. S. Sandhu, E. J. Coyne, H. L. Feinstein, and C. E. Youman,“Role-Based Access ControlModels,IEEE Computer, vol.29, no. 2, pp.38–47,1996. https://doi.org/10.1109/2.485845 [14] S. Dawson, D. Gaševi?, G. Siemens, and S. Joksimovic, “Analytics for institutional decision making,” Journal of LearningAnalytics,2014:https://dblp.org/rec/conf/lak/DawsonGSJ14 [15] I. Sommerville, Software Engineering, 10th ed., Pearson, 2015.https://www.pearson.com/en-us/subject-catalog/p/softwareengineering/P200000003258/9780133943030 [16] T. Erl, Service-Oriented Architecture: Concepts, Technology, and Design, Upper Saddle River, NJ, USA: Prentice Hall, 2005. https://www.thomaserl.com/book/service-oriented-architecture-concepts-technology-and-design/overview/ [17] M. Graf and K. List, “An evaluation of open source e-learning platforms stressing adaptation issues,” International Journal of Learning Technology, vol. 2, no. 2/3, pp. 201–222, 2005 https://doi.org/10.1504/IJLT.2005.007498 [18] R. Laurillard, Teaching as a Design Science: Building Pedagogical Patterns for Learning and Technology, London, UK:Routledge,2012.DOI:https://doi.org/10.4324/9780203125083 [19] A. Al-Fraihat, M. Joy, R. Masa’deh, and J. Sinclair, “Evaluating e-learning systems success: An empirical study,” Computers in Human Behavior, vol. 102, pp. 67–86, 2020. https://doi.org/10.1016/j.chb.2019.08.004. [20] M. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with LanguageModels,3rded.Available:https://web.stanford.edu/~jurafsky/slp3/ [21] T. M. Mitchell, Machine Learning, New York, NY, USA: McGrawHill,1997.Available:https://www.cs.cmu.edu/~tom/mlbook.html. [22] I. H. Witten, E. Frank, and M. A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann,2011.Available:https://shop.elsevier.com/books/data-mining/witten/978-0-12-374856-0 [23] E. Fernandes, M. Holanda, M. Victorino, V. Borges, R. Carvalho, and G. Van Erven, “Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil,” Journal of Business Research, vol.94,pp.335343,2019.https://slejournal.springeropen.com/articles/10.1186/s40561-022-00192-z [24] H. Kagermann, W. Wahlster, and J. Helbig, “Recommendations for implementing the strategic initiative INDUSTRIE 4.0,” in Industrie 4.0 in a Global Context, Springer, 2017. https://link.springer.com/chapter/10.1007/978-3-319-52551-8_1 [25] UNESCO, “Digital learning and transformation of education,”UNESCO,2021.[Online].Available:https://www.unesco.org/en/digital-education [26] N. Daswani, C. Kern, and A. Kesavan, Foundations of Security: What Every Programmer Needs to Know. Berkeley, CA,USA:Apress,2007.https://link.springer.com/book/10.1007/978-1-4302-0377-3 [27] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), Minneapolis, MN, USA, 2019, pp. 4171–4186. https://aclanthology.org/N19-1423.pdf [28] B. Burns, J. Beda, and K. Hightower, Kubernetes: Up and Running: Dive into the Future of Infrastructure. Sebastopol, CA,USA:O’ReillyMedia,2017.https://www.oreilly.com/library/view/kubernetes-up-and/9781491935668/ [29] X. Su and T. M. Khoshgoftaar, “A survey of collaborative filtering techniques,” Advances in Artificial Intelligence, vol. 2009,pp.119,2009.DOI:10.1155/2009/421425.https://www.asc.ohio-state.edu/statistics/dmsl/Su_Khoshgoftaar_2009.pdf [30] D. Clow, “MOOCs and the funnel of participation,” in Proceedings of the Third International Conference on Learning Analytics and Knowledge (LAK ’13), Leuven, Belgium, 2013, pp.185189.DOI:10.1145/2460296.2460332.https://oro.open.ac.uk/36657/1/DougClow-LAK13-revised-submitted.pdf

Copyright

Copyright © 2026 Prof. Waqar Khan, Mr. Vinit Siraskar, Mr. Pranav Kale, Mr. Bhushan Hiwase, Mr. Palash Zodawane, Mr. Jayesh Tembekar. 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.