In cooperation with:
Christelijke Mutualiteit Vlaanderen. CM is the biggest health insurance fund of Belgium with the biggest IT department.
It plays a triple role:
By adding AI to the scanner it now becomes intelligent and self learning. It recognizes what is written down and makes suggestions of it on the screen of the employee before it automatically puts it in the system.
“Our people process 5 million handwritten documents per month. Thanks to the add on of AI to this process, our scanner recognizes a lot more!”
Peter Van Maele - Head of architecture ICT CM
Challenge
The current scanner solution processes 5 million handwritten documents per month. Yet the current scanner does not achieve the requirements as it not always recognizes the handwritings correctly. Consequently, employees still invest a huge amount of their time in deciphering and typing the text of the paper documents into their application.
Solution
The result is an automated process by adding AI to the scanner, which deciphers the handwriting on the documents and pre-fills it in the application. Thanks to this faster process refund of medical costs goes faster.
Leveraging the power of Google's AI Platform, we could quickly train and evaluate various tensorflow models. After each iteration, improved versions of the models and APIs were shared with interested stakeholders using Container Registry so they could try it for themselves
used technologies:
> Tensorflow <
> AI Platform <
> Google Storage and Container Registry <