Automated Data Extraction

Automated data extraction via OCR technology takes the burden off of staff

Gathering the important information from business documents is a crucial business process – but also completely manual at many organisations. Staff are devoted to reviewing each document and manually keying data into various business systems, creating tedious and error-prone tasks. Moreover, as organisations and processing demands grow, so do their workforce requirements.

Once documents are captured and classified, OnBase data capture automatically and accurately pulls the critical information right off the page - including machine printed, hand-printed or barcoded documents. OnBase data capture leverages the following technologies:

  • OCR - Optical Character Recognition, used to extract machine-printed characters
  • ICR - Intelligent Character Recognition, used to extract hand-printed characters
  • OMR - Optical Mark Recognition, used to determine a selection from a list of choices (i.e. checks in check boxes)
  • BCR - Barcode Recognition, used to extract data from barcodes located on the document

These capture solutions are entirely flexible to fit your needs, allowing you to create templates for each document you process – giving you full control over where data is pulled, what is pulled and how each piece of data is translated into the formats you use – or leverage completely intelligent capture and allow the software to do all the thinking in finding the information.

Once the data is captured, OnBase automatically validates the data before sharing the data with your other systems. Extracted data can both be used for automated document indexing in OnBase, or another content management system, and it can be used to update your other business information management systems.  

 

aiim whitepaper