1
$\begingroup$

I am trying to extract product information from email receipts HTML. Most services I have found focus on OCR from paper receipts or PDFs. I would imagine that extraction of product information would be easier from structured HTML. What type of AI approach would be used to support this?

$\endgroup$
  • $\begingroup$ This depends entirely on the kind of information you would like to extract, and on whether this desired information is available in a form that is easy to process automatically. If you do not show actual examples of input and desired output, your question cannot be answered. A deep learning approach might not be needed at all, or it might be very useful. $\endgroup$ – Mathias Müller Jan 28 at 19:49
1
$\begingroup$

It depends on the data. If it is structured like form data, then you might not need AI at all — simple regular expression patterns might be fine. This would apply for example to address data. If you have the word street followed by a colon, followed by some text, it seems fairly obvious that this is the name of a street, and possibly also a house number.

If, however, you have free text, eg the answer to "describe any medical conditions you have", or "which companies have you worked at before?", then you might need to look at named entity extraction (NER) to identify names of medical conditions or companies.

So, some Natural Language Processing (NLP) and information extraction might be required apart from simple pattern matching.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.