Posted: 30 Jun 2020 5:55 EDT Last activity: 23 Sep 2020 12:12 EDT
Using Pega OCR with Designer Studio in Pega 8.4
Can we use Pega OCR capabilities while designing a case in Pega 8.4.
I have a requirement to upload a invoice in a case and then extract the details from uploaded document to map case properties.(Uploaded document can either be in pdf or image based file like png, jpeg etc)
Also is it possible to categorize uploaded docs. E.g. i will upload all the documents together and based on content can it identify those documents accordingly like which document is uploaded for Driving license, ID proof and Invoice etc and map accordingly.
Please provide some steps regarding how to configure and use Pega OCR.
In the installation step for Pega OCR it is mentioned that we need to install abbyy_installation_pegaXX_vYYYmmDD.zip and this is available on Pega Marketplace but i couldn't find this.
As it comes to categorization - you would need to implement that on your own, based on the results from OCR. You can employ Pega NLP to help you identify certain fields and values to help you decide what category you should assign.
Regarding documentation - on the link above you can see how to use it Email Channel, as it comes to low-level approach you can take a look at Rule-File-Binary#pyExtractText which then calls Pega OCR for OCR-able documents (Work-Channel-Triage-Email#pyOCRTextExtractor).