Answered

Document type recognition using text recognition

(0) Share

Report

Posted on by Augustin_LSD

Hello everyone, I am very happy to work with you 🙂

I need to work with a PDF file that can contain several different files in it. And here is my problem, because I need each of those documents to trigger different flows later

My idea was to use AI Builder and use the "Extract all text in photos and PDF documents (OCR)" action and then another action where I will be able to determine that if there are a few strings that I already know are going to be inside then I know that this page is my invoice for example,

I already know how to extract text from a PDF file but, once it is into a string I loose the ability of knowing the Page Number

I'll hope you'll be alble to help me with this

I'm just getting started into PowerAutomate and RPA and I find it super interesting

Categories:

AI Builder

I have the same question (0)

All responses (2)

Answers (1)

Verified answer

JoeF-MSFT on at

Like (0)

Report
Copy link

Link copied!

Hi @Augustin_LSD - welcome to Power Automate, we're also happy to work with you! 🙂

Have a look at the following flow example you can import in your environment: Know where to split a PDF with multiple documents ... - Power Platform Community (microsoft.com) The flow searches for a specific word and returns the page numbers where that word is present.

Here is another example flow that searches for a word within what is returned by the Recognize text in an image or PDF document. Search a specific Text from an image - Power Platform Community (microsoft.com)

Let us know if this helpful for you!

Was this reply helpful? Yes No
Augustin_LSD 6 on at

Like (1)

Report
Copy link

Link copied!

Hi @JoeF-MSFT Thank you so much for your help, both of the process are working great, You just unblocked me, thank you! keep up the great work you do 👌

Was this reply helpful? Yes No