Haptik offers two mobile applications:
- Haptik App: Launched in 2014 as a personal assistant app for everyday tasks.
- Rembo App: Helps the user remember tasks by providing reminders or tracking progress.
Haptik uses Conversational Machine Learning as its main technology. The steps executed by the conversational AI are:
The first step to resolving a user’s chat is to figure out the domain the user is chatting about.
Named Entity Recognition (NER)
NER is the ability to detect relevant entities from the user's message. This engine is designed ground up for chat bots and is an open source repository.
Deep Learning Layer Supervised
Using millions of data points built up through previous conversations and third party data, the machine learns to respond back to certain queries it may have never seen before.
Graph Based Chat Flows Supervised
The intent of the conversation is recognized, and the chat goes through a conversation tree to figure out the right response.
ML Orchestration Layer
The right response is picked from the input obtained from different algorithms. This layer makes the system more scalable and helps send data to the data lake which powers the analytics engine.
Documentaries, videos and podcasts