IBM Watson™ Discovery Service Ideas

We've moved...

You'll be redirected shortly, we've moved to our new idea portal:

Smart Document Understanding returns document structure

Right now, the output of SDU is aggregated into a JSON array.

It would be great if SDU could return the parsed structure of the document. This way we can know for sure if this word in the document is a 'Table of Content' type, or 'Subtitle' type.


  • Guest
  • Apr 11 2019
  • Already exists
Why is it useful?
Who would benefit from this IDEA? If I had this, I would be able to identify sections of a document and treat it accordingly. For example, if I combined this with TTS service, I would read different sections of the document in different styles.
How should it work?
Idea Priority
Priority Justification
Customer Name
Submitting Organization
Submitter Tags
  • Attach files
  • Admin
    Phil Anderson commented
    July 24, 2019 18:43

    It should already do this today? If you define a label for ToC, the highlights will come out of ToC when terms matched there.