To build a chatbot for college admission cells to guide students throughout their admission process.
A chatbot is a computer program that uses artificial intelligence (AI) and natural language processing (NLP) to understand users' questions and automate responses to them, simulating human conversation. Chatbots can make it easy for users to find the information they need by responding to their questions and requests—through text input, audio input, or both—without the need for human intervention. Chatbot technology is almost everywhere these days, from smart speakers at home to messaging applications in the workplace. The latest AI chatbots are often referred to as “virtual assistants” or “virtual agents.” They can use audio input, such as Apple's Siri, Google Assistant and Amazon Alexa, or interact with you via SMS text messaging. Either way, you’re able to ask questions about what you need in a conversational way, and the chatbot can help refine your search through responses and follow-up questions.
A well-designed college admission chatbot could automate responses to 80% of the pre-admission queries, retain user context across multiple conversation sessions for added relevance and nudge prospective students gently to the next step in their application journey.. now imagine all the above delivered 247365 in a channel (web, WhatsApp, FB messenger) of students preference. Understandably chatbots have become an integral part of pre-admission student engagement channels over the last few years.
Python, Rasa (Python Framework), Natural language understanding (NLU), Natural Language Generation (NLG).
Rasa NLU internally uses Bag-of-Word (BoW) algorithm to find intent and a Conditional Random Field (CRF) to find entities. Rasa NLU uses machine learning algorithms to analyze user input and make predictions about the intent and entities present in the text. A state tracker for tracking the dialogue state, A dialogue policy that selects the next action based on the current state.
- Faster support
(99.99% Uptime) - No waiting queues
(Instant Resolve) - Low barrier
(no need to call or email, just a click away) - Advanced analytics
(Admin can look into various KPIs) - Lead Collection
(Name, Phone Number, Email) - Personalization
(Messages including user name, eg. Hello <user_name>) - Content & Format
(Admin can manage various content according to user intent) - Multilingual support
(English, Bengali, Hindi) - Increased efficiency / reduced costs
- Doesn’t work well for older demographics
(e.g. if chat is done by student parents, who are not adequate with smartphones) - Human Fallback
(there may be an expectation, that humans have to come to resolve a user query) - Unemployment
(as AI Chatbot are very cost-effective, unemployment is an emerging problem)