we are trying to extract only specific information from Unstructured scanned pdf document,But the pdf doc will be dynamic format.
One document will come in one format but other will come in different format.But only few changes in body of the pdf paragraph.
for example,out of 3 pages Doc,we will extract only first page necessary information.
Using Electroneek is it possible ?Please help us.
Yes, you can extract specific information from dynamic format documents.
As an option you recognize the whole paragraph and then look up for the keywords using JS.
Then you anchor needed data to those keywords.
Or you can use “Unstructured data” activities to recognize invoices, passports, driver licenses, etc.