PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Mini Project
Intent-Based NLP Chatbot
Classifies what the user wants and answers from a response bank
1-2 weeks build
Overview
A classic retrieval chatbot built the way examiners expect to see it explained. User messages are tokenised and lemmatised, a small neural network predicts the intent, and a response is chosen from that intent's bank. A confidence threshold routes unclear messages to a fallback reply instead of a confident wrong answer.
What makes it stand up
- 01Editable intents file, so the bot's domain is easy to change
- 02Bag-of-words and embedding-based intent classifiers compared
- 03Confidence threshold with a graceful fallback response
- 04Simple slot capture for names, dates and numbers
- 05Browser chat widget served from a Flask back end
Module breakdown
- 01
Intents
JSON patterns and responses grouped by intent tag.
- 02
Preprocessing
Tokenising, lemmatising and vocabulary building.
- 03
Classifier
Dense network trained on the pattern set.
- 04
Dialogue
Response selection, fallback and short context memory.
- 05
Chat UI
Web chat window with typing indicator and history.
After this, you will be able to
- Explain intent classification versus generative chat
- Justify your confidence threshold with test examples
- Demo adding a new intent live and retraining
Technology stack
- Python
- TensorFlow
- NLTK
- Flask
- JavaScript
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support