PDF Document Processing

Help Studio
, , , ,
1

Hi, we are automating invoice processing, However the problem is the Invoices we receive could have multiple invoices combined into single PDF Or Invoice could have unnecessary pages other than Invoice.

So currently we are handing the situation with bit of complex round about Logic which involves multiple iterations of digitalization / extractions.

  1. First we are splitting every PDF into individual pages
  2. Every page is Digitized / extracted to read Invoice Number
  3. We merge Pages having common Invoice Number into one file
  4. Finally the merged files are processed with another digitalization & extraction

So this makes AI unit consumption multifold.

Are there any better way to handle this scenario in UiPath? Looking for expert opinion and inputs

2

@leela.chakka

You can try using intelligent keyword classifier to clasify the documents which can work with classifying the document swithout splitting as well and it can handle multiple different invoices in same pdf as well

Cheers