This repository contains the final project for an AI/ML internship. The project titled "CyberGuardian AI" is a speech-based chatbot assistant built to provide guidance and awareness on digital threats and online safety. The chatbot uses a custom-built knowledge base and a machine learning model to classify user intent and deliver relevant spoken responses.
Here're some of the project's best features:
- Voice-Enabled Interaction: The chatbot listens for user queries through the microphone and responds with synthesized speech.
- AI-Powered Intent Classification: Utilizes a Logistic Regression model to understand the user's intent from their natural language query.
- Custom Knowledge Base: All responses are fetched from a comprehensive custom-made .json dataset focused on digital safety and cyber awareness.
- Dynamic and Interactive: The chatbot is designed to handle a wide range of queries related to phishing malware passwords online privacy and more.
1. Clone the Repository
git clone https://github.com/D-Majumder/CyberGuardian
cd CyberGuardian
3. Install Dependencies
pip install speechrecognition pyttsx3 scikit-learn numpy pandas
pip install pyaudio
5. Run the Jupyter Notebook
jupyter notebook
6. Execute the Cells
The first cell loads the data and prepares the training sentences.
The second cell trains the LogisticRegression model.
The third cell contains the main conversational loop which will initiate the speech-based dialogue.
Technologies used in the project:
- Python: The core programming language.
- Jupyter Notebook: Used for developing and demonstrating the chatbot's functionality.
- scikit-learn: For the TfidfVectorizer and LogisticRegression model implementation.
- speech_recognition: To transcribe the user's voice input into text.
- pyttsx3: To convert the chatbot's text responses back into speech.
- json: For managing the chatbot's knowledge base.