• 

  Frontend Design

Project: NoteWise: Smart Lecture Transcript Analysis

Inspiration

Our project was inspired by the challenges students face in comprehending and retaining lecture material. Often, students miss crucial topics during lectures, either due to distractions or the fast-paced nature of teaching. We wanted to build a solution that could analyze lecture transcripts and compare them with students' notes, highlighting missed concepts and areas requiring revision. This idea suited with the Glean Challenge, which aims to enhance students' learning experiences through technology.

What We Learned

Through this project, we gained valuable insights into:

• Comparative Analysis: Identifying gaps between lecture transcripts and student notes.
• Backend Development with FastAPI: Creating efficient API endpoints for data processing.
• Frontend Development: Implementing an interactive UI using HTML, CSS, JavaScript and Vite.
• Containerization with Docker: Ensuring smooth deployment and scalability.
• User Experience Considerations: Designing a solution that is intuitive for students.

How We Built It

1. Frontend Development: We used HTML, CSS, and JavaScript to design an intuitive user interface where students could upload their notes and view the analysis results.
2. Backend Development: We implemented the backend using FastAPI, handling:
   • Processing lecture transcripts.
   • Comparing them with student notes.
   • Generating an analysis report highlighting missed topics.
3. Analysis with Gemini:
   • Enhancing student notes to ensure complete coverage of lecture topics.
4. Containerization & Deployment:
   • We used Docker to containerize the application for easier deployment and scalability.
   • Ensured the system runs smoothly across different environments.

Accomplishments We Are Proud Of

• Successfully built a system that helps students track and revisit missed lecture topics.
• Created an intuitive and user-friendly interface for students to interact with their analysis results.
• Achieved seamless integration between the frontend and backend, ensuring smooth performance.

Challenges We Faced

1. Topic Extraction:
   • Extracting key concepts from large transcripts required refining our rule-based approach to ensure relevance.
2. Comparative Analysis Complexity:
   • Determining the exact topics a student missed was challenging, as wording in transcripts and notes could vary significantly. We used semantic similarity approaches to improve detection.
3. Frontend and Backend Integration:
   • Ensuring smooth communication between the FastAPI backend and JavaScript frontend took some debugging and API optimization.

Conclusion

Our project successfully demonstrated how AI-powered analysis can enhance students' learning experiences by identifying missed concepts in lectures. This solution not only improves comprehension but also personalizes revision strategies, making learning more effective. Moving forward, we plan to incorporate speech-to-text improvements, AI-powered summarization, and an interactive dashboard to further refine the user experience.

Built With

• css
• docker
• fastapi
• geminiapi
• html
• javascript
• python
• vite