Video-enhanced learning companion & co-pilot video to text approach (2nd Gen)
Abstract
This project presents CCDS24-1273: Video-Enhanced Learning Companion & Co-Pilot (2nd Gen), an AI-driven lecture chatbot that transforms video learning into an interactive and context-aware experience. Built on Azure’s AI ecosystem, it integrates Azure Video Indexer and Azure OpenAI within a Retrieval-Augmented Generation (RAG) framework. Two key modules were developed: a Temporal Identifier for timestamp-aware retrieval and a Document-Scope Identifier for multi-lecture reasoning. Evaluated using the RAGAS framework on test questions, the enhanced system achieved higher precision, faithfulness, and relevancy compared to the baseline. These results highlight the potential of RAG-based learning companions to improve engagement, contextual understanding, and scalability in modern education.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.