QuestionQ100

VerifiedUiPath Document Understanding - Model building

In a Document Understanding project, a user must extract information from PDF documents that meet these requirements:

  1. The documents may contain scanned or digitally typed text.
  2. The documents may contain checkboxes, which must be extracted.
  3. The automation must use logical processors as efficiently as possible to achieve the greatest degree of parallelism.

Which properties should be provided to the Digitize Document activity during the Digitize phase?

Explanation

ApplyOcrOnPdf set to Auto supports PDFs with both native typed text and scanned content by applying OCR when needed. DetectCheckboxes must be True to detect checkboxes. A DegreeOfParalelism value of -1 automatically processes pages using the machine’s core count minus one, which is the supported automatic maximum-parallelism setting.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!