About our Knowledge Discovery Technology

Background Information

The lack of accessibility, usability, and readability of digital content presents many barriers for individuals with print disabilities.  For example:

• There are billions of PDF, DOC(X), RTF, TXT, and ePub files downloadable from the Internet. Only a small percentage of them are fully-accessible.

• It is estimated that the indexed Web contains more than 1.79 billion pages.[i]

• Google estimates the number of books printed in the modern era to be 129,864,880[ii]

• There are 7.5 million unique publishers of instructional materials[iii] (including individuals) have been issued International Standard Name Identifier (ISNI) ID numbers.

• Bowker, the world’s leading provider of solutions for self-publishers, counted more than 391,000 self-published titles… a 59 percent increase compared to last year.[iv]

• Open educational resources (OER) are freely available, open-licensed instructional materials that are used for teaching, learning, educational assessment, and to conduct research.[v]  There are open resources for almost every age, grade, and subject[vi]. For example: SchoolForge[vii] and SourceForge[viii] provide resources designed to find, create, and publish open instructional materials and software. There are many “open source” educational resource databases and search engines including:

  • OEDb with over 10,000 free courses from universities[ix];

  • Open Tapestry with more than 100,000 open-licensed online learning resources for academic and general audiences[x]; and,

  • OER Commons with 40,000+ open educational resources from elementary school through higher education.[xi]

Filter Failure

Educators often describe there being too much information available as, “information overload.”  In September of 2008, at Web Expo 2.0, an observation by Clay Shirky forever changed many people’s perception of this problem. Shirky stated, “It’s not information overload. It’s Filter Failure.”[xii]

Breaking down the accessibility, usability, and readability barriers across all digital content on the web is often viewed as an insurmountable task. Actually, it isn’t. It is the objective of IDEAL Group’s Knowledge Discovery Data Mining Technology.

Objective

The objective of IDEAL Group's Knowledge Discovery Data Mining (KDD) technology is to enable individuals with print disabilities, and everyone else, to more easily acquire knowledge from single or collections of digital content in the following formats:

• HTML files, including web pages, websites, blogs, and wikis

• PDF files

• Doc/Docx files

• ePub2/3 eBooks

• RTF files; and,

• TXT files

Note: The source content does not need to have been designed with accessibility, usability or readability in mind in order to automatically knowledge mine it into accessible formats.

Strategies

Provide users the ability to submit single or collections of digital content to cloud-based KDD services that automatically:

• Extract and present keywords/phrases in alphabetical order and ranked by importance;

• Generate both short and long content summaries based upon a keywords/phrase;

• Compile the collateral generated in steps 1-2 above into fully accessible EPUB3 eBooks readable by any ePub3 reader on any platform;

• Generate interactive mind maps from each keywords/phrase;

• Provide exportable files of all of the collateral, listed above, in both HTML and RTF formats;

• Provide files suitable for importing into (and exporting from) third-party applications such as Microsoft Project, Microsoft Word, Excel, PowerPoint, MindManager, XMind, iThoughts, MindGenius, MindMeister, FreePlane Connected Mind, Apache OpenOffice word processing, spreadsheets, presentations, databases, Google Docs, etc., etc.

• Provide users the ability to do steps 1-2 above using a fully-accessible mobile application; and,

• Simplify the results to make it more readable.

Knowledge Discovery Technology by Knowledge Discovery Solutions, Inc.

For more information please contact Steve Jacobs: steve.jacobs@ideal-group.org