Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63364
Volume:
10 |
5 |
May 2026
Pages:
1-20
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
Department of Computer Science &Engg.
Government College Of Engineering,Chandrapur
AskNLearn is an AI-powered educational platform designed to improve the learning and revision process through intelligent content generation, adaptive practice, and performance analytics. Traditional study methods often require students to use multiple disconnected tools for notes, quizzes, and progress tracking, resulting in reduced efficiency and fragmented learning experiences. The proposed system provides a unified platform where users can upload or enter study material in multiple formats, including text, documents, images, audio, video, and URLs. The system processes the input using OCR, transcription, and AI-based content extraction techniques to generate structured learning resources such as summaries, flashcards, multiple-choice questions, and memory maps. The platform also includes subject-wise quiz practice, adaptive learning support, dashboard analytics, gamification features, and secure authentication mechanisms. AskNLearn is developed using React.js, Node.js, Express.js, FastAPI, MySQL, and AI model APIs such as Gemini/OpenAI. The architecture follows a dual-backend approach, separating application services from AI-processing tasks to improve scalability, maintainability, and system performance. The implementation demonstrates that integrating artificial intelligence with modern full-stack technologies can significantly improve revision efficiency, personalized learning, and student engagement. The proposed platform reduces the manual effort involved in study preparation while encouraging continuous learning through personalized practice, analytics-driven feedback, and interactive educational tools. Overall, the system demonstrates the practical application of artificial intelligence in enhancing digital education and building intelligent learning environments suitable for modern students and educational institutions. .
KEYWORDS
Crime Education and learning management have become increasingly dependent on digital technologies, intelligent automation, and personalized educational systems. Traditional learning methods often involve manual preparation of notes, fragmented study workflows, limited analytics, and inefficient revision processes. Therefore, the integration of Artificial Intelligence and modern web technologies into educational systems has become an important area of development. This research paper presented a comprehensive study of AskNLearn, an AI-powered educational platform developed using modern full-stack technologies, Artificial Intelligence, OCR systems, transcription tools, and adaptive learning techniques. The platform provides a centralized learning environment where students can upload study material, generate structured learning resources, practice adaptive quizzes, track progress, and access analytics-driven educational insights. The study also discussed important modules such as secure authentication, AI-based content generation, OCR and transcription processing, adaptive quizzes, dashboard analytics, gamification systems, and real-time community learning support. These features improve revision efficiency, personalized learning, student engagement, and accessibility of educational resources. The implementation results show that the developed system performs efficiently under normal operating conditions. Core modules such as AI generation, quiz systems, analytics dashboards, and secure authentication demonstrated reliable performance and positive user experience. The project proved that Artificial Intelligence combined with modern web technologies can significantly improve digital learning workflows and educational productivity. Although the platform achieved successful results, challenges such as AI dependency, OCR limitations, scalability requirements, media processing delays, and security considerations still remain. These limitations can be addressed through future enhancements such as advanced AI recommendation systems, cloud-native deployment, mobile applications, and stronger security mechanisms. In conclusion, AskNLearn provides a practical, scalable, and intelligent solution for AI-assisted education and adaptive digital learning. With continuous advancements in Artificial Intelligence and educational technologies, such platforms can play an important role in building smarter, more personalized, and more efficient learning environments for students and educational institutions.
[1] T. Brown, B. Mann, N. Ryder et al., “Language Models are Few-Shot Learners,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 1877–1901, 2020. [2] A. Vaswani, N. Shazeer, N. Parmar et al., “Attention Is All You Need,” IEEE Transactions on Neural Networks and Learning Systems, pp. 5998–6008, 2017. [3] J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of NAACL-HLT, pp. 4171–4186, 2019. [4] OpenAI, “GPT Models and AI-Based Educational Applications,” Available: https://openai.com, Accessed: 2026. [5] Google, “Gemini API Documentation,” Available: https://ai.google.dev, Accessed: 2026. [6] R. Smith, “An Overview of the Tesseract OCR Engine,” Proceedings of the International Conference on Document Analysis and Recognition, pp. 629–633, 2007. [7] A. Radford, J. Kim, T. Xu et al., “Robust Speech Recognition via Large-Scale Weak Supervision,” OpenAI Whisper Research Paper, 2022. [8] Facebook Inc., “React.js Documentation,” Available: https://react.dev, Accessed: 2026. [9] FastAPI, “FastAPI Framework Documentation,” Available: https://fastapi.tiangolo.com, Accessed: 2026. [10] Oracle Corporation, “MySQL Reference Manual,” Available: https://dev.mysql.com/doc, Accessed: 2026.
Publication Date
5/17/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...