Project Owl is a proof of concept AI powered application that aims to demonstrate how the Expert AI Natural Language API can be used for auditing and gaining insight from customers by analysing audio recorded calls at call centres. Project Owl employs the Sentiment Analysis and Taxonomy features of the NLP API to analyse and prioritize customer service complaints and also provides insight on the customer emotional state respectively.
The inspiration for this project is to experiment how a call centre issue management system can be automated for customer serving financial institutions such as banks and fin-tech companies.
What it does
Project Owl is used for auditing and gaining insight from customers by analysing audio recorded calls at call centres.
How we built it
Project owl was built using React on the front end, Azure Function Serverless architecture on the backend.
Challenges we ran into
The main challenges were speaker diarization and finding real world customer call centre audio datasets.
Accomplishments that we're proud of
Building the application in time.
What we learned
Analysing text for emotional traits & sentiment analysis using NLP API. Serverless architecture using events and messaging. Real time web applications using Azure SignalR
What's next for Project Owl
Open source, tutorials