I have some medical tests from different laboratories.
The documents for each laboratory have almost the same format (semi-structured), but there are documents with 10 pages and others with 300 pages for the same laboratory.
An idea that came to me to improve the processing time, increase the efficiency and reduce the consumption of the AI units is to do the digitalization and classification part on a process and then add some business rules to extract the only pages i need using ( Extract PDF Page Range) than use in another process digitalization and extraction using the new pdfs .
Is it a better idea , does it give better result ?
Welcome to UiPath community.
We have implemented the same idea and we have reduced the consumption of AI units since we are using only the required pages. The efficiency is also good.
Happy Automation 
Cheers
This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.