I am facing an issue while classifying the documents, Currently my document has keyword in format PO-CH000000 and I have used key word “po-ch” in keyword classifier but when I use it, it is getting failed to classify based on keywords. Please help to solve the issue.
After digitize the document,have you checked the document text and make sure that the text has been extracted from the document correctly(check if the text has po-ch)…
I have checked inside doc text there is the PO-CH000000 (6 digit num instead of 0) code and using po-ch keyword it is not classifying.
To increase the confidence of being classified add some more unique keywords so that it can classify the document correctly
@vijay.pattar please give po as seperate keyword and ch as seperate keyword and give a try.
And also make sure it is O and not 0.
Prasath , I just gave 0 as example there will be 6 digit number. like PO-CH123456. asnd there is no regex based classifier like we have a regex based classifier.
Actually that is the unique formatted keyword ,For example if PO number is PO-CH123456, keyword based classifier can classify when we give keyword as PO-CH123456 as it searches for exact keyword not a part of it. if we give po-ch (which will be common format) it will not work. which can work using regex pattern
@vijay.pattar think I didn’t convey clearly, I was referring to the letter o next to p as sometimes Ocr will pick up a letter o with a zero and is there not any solid information on the pdf besides the Po Number to classify it.