Document understanding extract data in pdf where pages is dynamic

Help Studio
1

Hi Good day,

I have a problem using DU where the number of pages is dynamic or sometimes it is 4pages, 2pages and More.

The initial DU I created is designed for 4pages PDF file, now there are some scenarios that is more than or Less than 4pages.

Original Design in 4pages PDF file:

  • GET data from the 3rd page of the File.

New Scenario 2Pages PDF File:

  • The data from the 3rd page of PDF file is moved in the 1st Page of PDF File(New Scenario)

For your Reference: This is where i followed the DU
(48) UiPath Document Understanding: Extract Tables Out of PDFs - YouTube

Thank you in advance.
-Vincent

2

Hi @Vincent_Nuestro

For dynamic pages, use can use regex or ML extractor instead of form extractor.

Regards,

3

For this u try this
step 1) Digitization under use UiPath Documents OCR
step 2) For extraction
-implement ChatGPT extract information or implement Regex Or Advanced DU
step 3) extraction O/P store in excel or othe

4

Hi @Vincent_Nuestro ,

Maybe performing a Classification to properly classify the Page as required would help for this scenario.

Is there a Classification method already in place ?