Extract multiple GSTIN number from invoices

Help Document Understanding
, ,
1

While using Receipt and Invoice AI, I even wanted to extract GSTIN or GST number of both the buyer and the seller. How would be I able to do that. Any of regular expression or machine learning extractor work. I wanted to extract multiple values of GSTIN numbers.

1 Like
2

can i see the sample Data??
@shauryachauhan

3

\d{2}[A-Za-z]{5}\d{4}[A-Za-z]{1}\d{1}[A-Za-z]{1} this is for GSTIN
use this expression in Matches activity
@shauryachauhan
Cheers

1 Like
4

Can this extract multiple Gstin numbers from one particular invoice? Had tried using this.

1 Like
5

yes!
you can do this to see

  • get Matches output like outRegex then pass it to For Each Loop and keep argument type as Object
  • use writeline like this Item.ToString
    cheers
    @shauryachauhan
6

you can try this

  • Use Load Image activity and pass the image path and the result will be of type Image get output like this outImage

  • Now you can use Microsoft OCR and pass the outImage as input to the Micriosoft OCR this will give you the result of type System.String and get output like outString

  • Now get Matches activity and pass the outString as input to the Matches activity and pass this pattern \d{2}[A-Za-z]{5}\d{4}[A-Za-z]{1}\d{1}[A-Za-z]{1} and output as outGSTIN

  • now if you want to print the output pass outGSTIN to For Each Loop and keep argument type as Object and use WriteLine like this item.ToString

7

how to use it in regex based extractor?

1 Like
8

Use matches activity!
@gpal

9

Can we extract GST or PAN through ML model?