Let’s get simple things out of the way first.
IDC stands for Intelligent Data Capture, while OCR stands for well… Optical Character Recognition.
As the name suggests, OCR mostly deals with image pre-processing, identifying characters and putting together words, blocks, and sentences. The field of OCR revolves around digitizing what’s on paper or a scan or a photograph from a physical document. Online OCR plays a critical role in scenarios with a large number of scanned documents and images which need to be converted to text.
Intelligent Data Capture technology, on the other hand, is broader and more general field of information collection and analytics. It provides meaning to text extracted from many forms of digital assets such as documents, emails, text files and scanned images.
It’s a method above and beyond OCR software. In IDC, words and sentences get business meaning and become much more relevant. Let’s walk through an example;
An OCR system scanning dates may output ’12-May-2018’. A 100% accurate result but eventually it is just a sequence of characters and pixels appearing together on a picture. On the other hand, with the help of Intelligent Data Capture solutions, this sequence of characters will take one of the following meaning:
‘PAYMENT DUE DATE’ for credit card statements, ‘CHECK-IN DATE’ or a ‘CHECK-OUT date’ for hotel invoices ‘RENEWAL DATE’ on a contract
Or some other such business interpretation is driven from the context of the document.
WHERE IS THE INTELLIGENT DATA CAPTURE SYSTEM APPLICABLE?
Any place where meaningful snippets of information are hidden deep inside digital documents and images. This can be most common in industries such as Finance, Legal, Insurance, Auditing etc.
These industries generate millions of documents every month as a byproduct of their business processes. The challenge originates when these documents flow through the business workflow and reach the consumers of the document. In most cases, they are far removed from the document producers. They will have no access to digital data embedded in these documents.
In short, the far removed downstream stakeholders and consumers of these documents will have to force themselves to rely on manual labor for information extraction. Examples of such information are dates from contracts, ticker symbols from stock market reports or name and address of the fund manager from a fund prospectus.
HOW DO ENTERPRISE AI AND MACHINE LEARNING ALGORITHMS HELP?
Technology has reached the state where it is possible today for computer programs to read and understand digital documents as humans do. We can train Intelligent algorithms to look for specific entities such as dates, contract numbers, purchase order numbers in different documents. These trained systems regularly produce accuracy levels of more than 90%. Hence, one can efficiently analyze 100s and 1000s of documents per minute.
Although one of the most obvious advantages of these systems is the reduction of humans in the loop. But, the REAL WIN is the capability of automation and efficient integration of otherwise manual workflow with other business workflows. This characteristic of the IDC system makes it one of the most essential building blocks for your robotic process automation (RPA) program and architecture. More on this later.
INFRRD AND IDC?
We are investing heavily in building a scalable universal trained model capable of extracting common entities from common business documents such as trade notes, shipping labels, contracts, invoices, receipts etc.
Want to understand how we can customize for your needs?
Originally published at infrrd.ai on July 20, 2018.