🎓 DaiNam University Plagiarism Detection System

🔬 Advanced Academic Integrity Through AI Innovation

A Next-Generation Plagiarism Detection System Powered by Deep Learning and Vector Search Technology

Architecture • Features • Tech Stack • Installation • Getting Started • Docs

🏗️ Architecture

The system employs a three-tier architecture:

1. 📄 Document Processing Layer: Extracts text from PDFs, segments into sentences, and generates embeddings
2. 💾 Storage Layer: Stores document metadata in PostgreSQL and vector embeddings in Milvus
3. 🔎 Search Layer: Performs high-performance similarity searches and generates detailed reports

✨ Key Features

🧠 Advanced AI Technology

• Semantic Analysis Engine: Powered by state-of-the-art transformer models
• Multi-lingual Support: Optimized for Vietnamese and English content
• Context-Aware Detection: Understanding beyond simple text matching

⚡ High-Performance Architecture

• Vector Search Technology: Using Milvus for lightning-fast similarity search
• Parallel Processing: Efficient handling of large document collections
• Scalable Infrastructure: Designed for institutional deployment

📊 Comprehensive Analysis

• Visual Results: Interactive visualization of matched content
• Detailed Reports: Page-by-page similarity analysis
• Evidence Mapping: Precise location of potential matches

🔧 Tech Stack

Core Technologies

Database Systems

📥 Installation

🛠️ Prerequisites

• 🐍 Python 3.8+ - Core programming language
• 🐘 PostgreSQL 12+ - Relational database for metadata
• 🔍 Milvus 2.x - Vector database for similarity search
• 🐳 Docker & Docker Compose - Container management
• 💾 RAM 8GB+ - Recommended for optimal performance
• 💻 CPU 4+ cores - For parallel processing
• 🖴 Storage 10GB+ - For document storage and embeddings

🗃️ Database Setup

1. 🐘 PostgreSQL Setup

   # Start PostgreSQL service
   docker run -d \
     --name postgres \
     -e POSTGRES_USER=username \
     -e POSTGRES_PASSWORD=password \
     -e POSTGRES_DB=database_name \
     -p 5434:5432 \
     postgres:12

2. 🔍 Milvus Setup

   # Download Milvus docker-compose file
   wget https://github.com/milvus-io/milvus/releases/download/v2.3.3/milvus-standalone-docker-compose.yml -O docker-compose.yml
   
   # Start Milvus
   docker-compose up -d

⚙️ Project Setup

1. 📦 Clone Repository

   git clone https://github.com/drkhanusa/DNU_PlagiarismChecker.git
   cd DNU_PlagiarismChecker

2. 🌟 Create Virtual Environment

   python -m venv venv
   source venv/bin/activate  # Windows: venv\Scripts\activate

3. 📚 Install Dependencies

   pip install -e .

4. ⚡ Environment Configuration

   # Copy example environment file
   cp .env.example .env
   
   # Edit .env with your settings
   # Example configuration:
   DATABASE_URL=postgresql://username:password@localhost:5434/database_name
   MILVUS_HOST=localhost
   MILVUS_PORT=19530

5. 🔄 Initialize Database

   # Create database tables
   python setup_database.py
   
   # Initialize Milvus collection
   python create_milvus_db.py

🚀 Getting Started

⚡ Quick Start

from plagiarism_checker import check_plagiarism_details

# Check a document
results = check_plagiarism_details(
    file_path="path/to/document.pdf",
    min_similarity=0.9
)

# View results
print(f"Overall Similarity: {results['data']['total_percent']}%")
for doc in results['data']['similarity_documents']:
    print(f"Match: {doc['name']} - {doc['similarity_value']}%")

📥 Adding Documents to Database

from create_corpus import CorpusCreator

creator = CorpusCreator()
creator.process_document("path/to/document.pdf")

📚 Documentation

For detailed documentation, please visit our Wiki or refer to the following sections:

• 📖 Installation Guide
• 👥 User Manual
• 🔧 API Reference
• 🤝 Contributing Guidelines

📝 License

© 2024 AIoTLab, Faculty of Information Technology, DaiNam University. All rights reserved.

---

Made with 💻 by AIoTLab at DaiNam University

Website • GitHub • Contact Us