Multiple Invoices per page

Hi,

I am working on a Document Understanding project and I have data in pdf files. Each Page in the pdf has 2 or more invoices. Did any one suggest me on how to process these multiple invoices in one page?

Aprox. Structure of the pdf page:

Page 1
Invoice 1
Invoice 2
Invoice 3
Page 2
Invoice 1
Invoice 2
Invoice 3
Invoice 4

Thanks
Satya

Hello @satya.allamraju ,

If you are not going for any ML modeling, i would suggest to go with Regex expressions.

You can read the pdf and use the regex to fetch the similar pattern of invoice numbers.

Eventhough the number of invoices change, then also you can get it using regex.

Thank you Rahul. But the case I am working on is not well fitted for RegEx. I am working on extracting the data from a pdf - Each page contains one or more Insurance EOP’s.

Each EOP is in the below format:

Do you know any suitable / related end point for ML Extractor for above type of EOP?

Hi @satya.allamraju

have you tried using Classify Document to Classify the Documents .

Thanks.

If one page resorts to one invoice, you can split the document into single pages before it enters the document understanding model.