How do I get extractor confidence level from the extracted document?

I’m using RegEx extractor, however I realize that the extractor found 2 possible matches (which makes the confidence level of the extractor to be 50%) - Refer pic below.


Note: The ‘2’ in the orange circle indicates that there are 2 possibilities, while the yellow & green highlighted dropdown fields are the first & second occurrence respectively.

The RegEx pattern for both occurrences seem to be identical (only the first occurrence is the required data and if the first one is not found, for sure the second one would be extracted instead). So, I would like to see the pattern for the second one to be excluded in the RegEx (from 1000 documents), I assume 100% confidence level of extracted data means the second one is extracted instead.

I’ve tried ExtractionResults.ResultsDocument.DocumentTypeField.Confidence, however it only gives the Confidence Level of the Document Type which is 72%.

The question is how can I find the confidence level for an Extraction Result Data only? Been searching for the whole time.

Dear Azeem,

It depends on the stability ,structure and format of the document and the extracted data accuracy to decide on.
You can place a condition to check if the accuracy is greater than 80%(assume) or more after the extraction .

Please refer below link:

Thanks,
Geetishree Rao

1 Like

Thanks @geetishree.rao. This is very helpful, I just got what I really wanted

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.