Data is not extracted properly via Taxonomy

Help Studio
1

We were using Document understanding process to extract the data from the pdf. We use the pdf which is having minimum length characters as Template. But When we pass the pdf which is having maximum values in the field, the data is not extracted properly.

image
image1007×394 90.7 KB

This is Template I used , you can see the To field has single line data but the pdf which i used having multi line data and that time the data is not extracted properly and we can’t able to use regex.

2

Hi @agathiyanv

Can you please train both the Documents or the document with maximum length.

Also can you please let me know the extractor being used.

Thanks

3

We used Intelligent form extractor and we also trained with maximum length Document but it’s not working when I passed other pdfs

4

Can you please try with ML Extractor .

Thanks

1 Like
5

When I use ML extractor , the skills are not loading for PurchaseOrder

6

please try with different end points can check if that works.

Thanks