Skip to Main Content
IBM Data and AI Ideas Portal for Customers

This portal is to open public enhancement requests against products and services offered by the IBM Data & AI organization. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (

Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:

Search existing ideas

Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,

Post your ideas

Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,

  1. Post an idea

  2. Upvote ideas that matter most to you

  3. Get feedback from the IBM team to refine your idea

Specific links you will want to bookmark for future use

Welcome to the IBM Ideas Portal ( - Use this site to find out additional information and details about the IBM Ideas process and statuses.

IBM Unified Ideas Portal ( - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM. - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.

IBM Employees should enter Ideas at

Status Not under consideration
Workspace Watson Discovery
Created by Guest
Created on Nov 9, 2022

Improve Smart Document Uderstanding processing time

Real-life scenario: the user uploads a document and the extracted info are needed as input for another tool or ML model (real time scoring is needed). The customer experience suffers from the waiting time. The processing time of one document is too long for real life scenarios (up to 6 minutes for a one page document) and not predictable (it does ot seem to be document dependent). A similar problem is faced with other WD enrichment, but not as extreme as in Watson SDU, and can be mitigated via preprocessing.

Needed By Yesterday (Let's go already!)
  • Guest
    Nov 23, 2022

    One type of document was KYC (Know Your Customer Documents), another one was Energeausweis (a German document with info about a building energetic status).

    In one case we build a UI in which the user (bank analyst who is usually extracting info manually) could upload the document and receive a table with the extracted entites. The user could then give feedback if the extraction was correct, before the data was sent to a database.

    In another case, the end user wants to renovate his house to make it more energie efficient. With an app, the user needs to take pictures of the energy document, the info extracted from the document are passed to another service which calculates possibilities of renovation based on the extracted data. The possibilities are then shown to the user.

    We have done so far 4 MVPs in which info needs to be extracted real time from documents, and my understanding is that Watson Discovery (so far) is not a good choice for real time applications.

  • Admin
    Calin Furau
    Nov 17, 2022

    What type of document and SDU training model was used when seeing these slow response times?

    Could you also give us an example of real-time scenario using SDU? What extracted info from SDU would you use to feed another ML model?

    Thanks for your feedback.