Document understanding extraction

Hi,
I have a document and in that document same type of form is there in multiple page but i only want to extract data from a specific page as per the keywoard. I am using ML extractor and AI center to extract the data, but it is extracting data from first page how can i tell it to extract only from that page where that keywoard is present. document type can be of pdf or word.

Try using form extractor and indicate the files you need to extract , ML , since mapping is there it will start extracting from beginning.

Hi @ashish_negi try with regex extractor or generative extractor

Hi @ashish_negi ,

Could you try using the Classifiers - Keyword Based or Intelligent Keyword Based Classifier and check if you are able to get the particular page as only the required for extraction. This would mean that the keyword(s) are Unique to be found in only that specific page.

There are other normal ways of understanding the Keyword placements in the document using PDF activities, but we would need to understand some more details - Document Type (Digital or Scanned), Max Number of pages that could be present, Does the data span multiple pages ?

Let us know if you are able to test the classifiers and provide us with the feedback on it.

Didnt work, i split the pdf and sended single page to DU

Form extractor is not working for my case