Uipath DU file

[Ritaman_Baral]

I am using UiPath DU to extract some fields from a PDF.
However for a particular non native pdf the value from a particular field is not getting extracted
What to do ??

[pavan_kumar5 (pavan kumar)]

Hi refer below mentioned playlist,

Still if you have any questions or not resolved provide the proper requirements with adding screenshots will provide the solution on it.

Link:- https://youtube.com/playlist?list=PLvDPN0D6ZiJPNc7prqzNtmH3WKP1Rxe3v&si=4FVIv6X5TqkdDZPO

[Anil_G (Anil Gorthi)]

@Ritaman_Baral

There might be multiple reasons for this

1. Retraining on more documents might fix this
2. The resolution of the document might be less
3. If it is habdwritten or if the values are cut it might not be detected properly

Cheers

[KevinE (Kevin)]

Try adding the Present Validation Station activity and do a few samples. It will highlight for you what field it has found and what the confidence level is. You can lower the confidence level if needed.

If it is a semi-structured PDF, use an anchor or several anchors to help identify the field.

[muthuerd]

Hi @Ritaman_Baral ,

You can try enabling apply OCR in digitization sometimes if it’s non native pdf the digitization will not extract the text.

If it’s not helpful please elaborate more information.

Thanks
Muthu

[Archana_Gulli]

Hey @Ritaman_Baral ,

->Verify that the non-native PDF follows a standard format and structure by checking the PDF format.

->Also ensure that the PDF is not corrupted and can be opened and read properly using a PDF viewer.

->Examine the extraction configuration settings in UiPath DU for the specific field that is not getting extracted.

HAPPY AUTOMATION!!