System Requirements Document (SRD)

Project Name: onyx-learning

1. Introduction

The onyx-learning project aims to create an "AI Personalized Learning Assistant" that leverages machine learning to classify students into performance levels (Beginner, Intermediate, Advanced) and provides personalized study recommendations. This system is designed for a hackathon environment, with a focus on simplicity, functionality, and an impressive user experience.

This document outlines the system requirements, including functional and non-functional requirements, user personas, visual design elements, architecture, flow charts, and a comprehensive report generation capability.

2. System Overview

The onyx-learning system is a web-based application that integrates a modern React frontend, a Python Flask backend, and a scikit-learn machine learning model. The system processes student performance data (marks, study time, attendance) to classify students into performance levels and generate personalized study plans.

Key features include:

• A user-friendly interface for data input and result visualization.
• A robust backend for data processing and ML model integration.
• A machine learning model for classification and recommendation generation.
• Architecture and flow chart designs for better system understanding.
• A report generation feature for presenting results and insights.

3. Functional Requirements

• As a User, I should be able to input student marks, study time, and attendance via a form.
• As a User, I should be able to view the predicted performance level (Beginner, Intermediate, Advanced) on a dashboard.
• As a User, I should be able to receive personalized study recommendations based on weak subjects.
• As a User, I should be able to download a report summarizing the analysis and recommendations.
• As an Admin, I should be able to upload a CSV dataset for model training.
• As an Admin, I should be able to view system architecture and flow chart designs for documentation purposes.
• As a User, I should be able to navigate between pages (Landing, Dashboard, Form, Admin, Report) seamlessly.
• As a User, I should be able to trigger selective re-runs of the analysis and regenerate reports.

4. User Personas

1. Student:

   • Inputs personal academic data (marks, study time, attendance).
   • Views performance classification and recommendations.

2. Admin:

   • Manages the system, uploads datasets, and monitors performance.
   • Accesses architecture and flow chart designs for documentation.

5. Visuals Colors and Theme

Color Palette

The onyx-learning project adopts a modern, professional theme with a focus on accessibility and readability.

6. Signature Design Concept

Interactive Learning Dashboard with Dynamic Animations

The homepage will feature a dynamic, interactive dashboard that combines data visualization and animations to engage users.

• 3D Card Animations: Each student’s performance level will be displayed on a card that flips dynamically when hovered over, revealing personalized recommendations on the back.
• Progress Rings: Circular progress bars will visually represent attendance, study time, and marks.
• Animated Transitions: Smooth transitions between sections, with subtle scaling effects on buttons and cards.
• Dark Mode Aesthetic: A sleek, dark-themed interface with glowing accent colors for a futuristic feel.
• Selective Re-run Button: A prominent button on the dashboard allows users to re-run the analysis for updated results.

This design ensures the system is not only functional but also visually captivating, leaving a lasting impression on users and hackathon judges.

7. Architecture Design

System Architecture

Frontend (React) → Backend (Flask) → ML Model (scikit-learn) → Dataset (CSV) → Output (JSON)

Components:

1. Frontend:

   • Collects user inputs and displays results.
   • Communicates with the backend via API calls.

2. Backend:

   • Processes requests and integrates with the ML model.
   • Returns predictions and recommendations to the frontend.

3. ML Model:

   • Trains on the dataset and predicts performance levels.
   • Generates personalized recommendations.

4. Dataset:

   • CSV file containing student performance data.

8. Flow Chart Design

User Interaction Flow

[Start]  
   ↓  
[User Inputs Data] → [Validate Input] → [Send to Backend]  
   ↓  
[Backend Processes Data] → [Call ML Model] → [Generate Predictions]  
   ↓  
[Return Results to Frontend] → [Display on Dashboard]  
   ↓  
[Generate Report (Optional)]  
   ↓  
[Selective Re-run (Optional)]  
   ↓  
[End]  

9. Non-Functional Requirements

• Performance: The system must process inputs and return results within 2 seconds.
• Scalability: The architecture should support additional features like advanced NLP and larger datasets.
• Usability: The UI must be intuitive and accessible, adhering to WCAG standards.
• Reliability: The system must handle invalid inputs gracefully without crashing.
• Portability: The system should run seamlessly on Windows and Linux environments.

10. Tech Stack

Frontend

• React for modern UI development.

Backend

• Python Flask for lightweight API development.

Machine Learning

• scikit-learn for classification and recommendation generation.

Database

• CSV for initial dataset storage.

Tools

• Docker for containerization.

11. Assumptions and Constraints

Assumptions

• Users will input valid numerical data for marks, study time, and attendance.
• The dataset will be preprocessed and clean.

Constraints

• The system must be developed within a 6-hour hackathon timeframe.
• No external paid APIs can be used.

12. Glossary

• Frontend: The user interface of the system.
• Backend: The server-side logic that processes data.
• ML Model: A machine learning algorithm used for classification.
• Dataset: A structured file containing student performance data.
• API: Application Programming Interface for communication between frontend and backend.
• Selective Re-run: A feature allowing users to re-run the analysis for updated results.

This document provides a comprehensive overview of the onyx-learning project, ensuring clarity and alignment with the project goals. Let me know if you’d like further refinements, Thanush!