The Evolution AI platform extracts data from a new document type in two minutes
In just two minutes, you can create a new document type, add custom fields and start accurately extracting data.
Our algorithms are so powerful they learn from a single example. Simply set up a new document type and upload an example to show the platform what data to extract. When you upload the second example, the algorithms start accurately extracting data.
Our platform’s interface is simple to use and requires no coding. In a day, a junior employee could build a solution from scratch and have performance metrics on hundreds of examples ready for evaluation.
Here’s the process:
Simply log in and go to Document Settings to add a new document type, e.g. ‘Complex Financial Document’.
Next, add all the fields you want to extract and whether each field is text, a number, a date or monetary value, e.g.: Sort code (Numerical), Address (Text), Total amount (Monetary value), Date of document (Date)
Upload the first example of the document and tell the platform where to find the fields on the example.
Upload a second example document and the platform will start extracting data. The whole process can be done in two minutes. The next step is to evaluate our platform’s performance.
Evolution AI conducts research with the Machine Learning Department at UCL and the Computer Science Department of the University of Southampton. We are funded by the creator of Amazon Alexa and one of the largest grants for an AI project ever awarded by the UK Government.
Our key partners and clients include RBS, RELX Group, Blue Prism, The Economist, Sky, Dun & Bradstreet, UiPath, the Office for National Statistics, Accenture, Natwest, Automation Anywhere, and Hitachi Consulting.