What is the best way to handle Document Processing and Document Understanding?

Hello all,

I am new to UiPath and am having a hard time researching document processing/understanding.
The use case is to process order confirmation emails.
One of the last things my team needs to solve in order to complete the use case is to successfully extract the data within the documents.
We want to grab the order number (we can use regex to do this reliably), the date of arrival, the amount of items purchased, and the price of each item.
Because these documents have many dates and numbers, it is difficult to extract the date, price, and amount.
What is the best way to extract this data? I thought NLP might be helpful, but am unsure where to start with that. Is there an activity that I am missing that would be helpful?

Hi @grant.walker

If the documents are digital and are having relaivle anchors then we can read the values using read pdf and regex.

If you want to use ML then you have to use something related to document reading like invoice reading might help

Hope this helps

You need nlp if you are having scanned documents and hand written documents but again accuracy is the key it might be a lottle low but yes that is the only way for scanned or handwritten