Features and Requirements
Functional Requirements
Users will be able to receive multiple choice questions at critical points
- Questions will be related to the video to guide and enhance story comprehension
- Questions will be generated using a large language model and an object detection model
- Quiz questions will include varied interaction types (text-based, image-based, touch-based)
- Users will be able to customize their learning experience
- Special Object Detection Questions can be enabled in addition to regular MCQ questions
- Each video session must have a Subject Focus(s) for the questions: Mathematical, Nature, or Animal focus
- Penalty Options for wrong answers can either be having the video rewind, or auto skipping the question
- The video will pause when the user receives the question
- Question will automatically be read out loud
- Users shall have the option to skip the question
- After answering incorrectly, users cannot reselect options that they have previously selected
Users will receive a session recap at the end of the video
- Users will see a summary including total correct and incorrect answers, hints used, and total time spent answering questions
- Users can view aggregate user metrics across all sessions using a PIN
- Users can export aggregate metrics for research purposes
Nonfunctional Requirements
- Data analytics on aggregated user sessions data will be accessible to users
Questions and videos must be able to load efficiently to ensure a seamless user experience
- The system should be able to load within 5ms