Datacap and Content Classification Setup Part 1
This video will show you how to create a IBM Content Classification training application using Datacap. The final result will be an application that saves the text off documents to be used in creating a knowledge base for page identification. The first part of this demonstration shows how to get the text off the documents and save them in folders which are named to be easily imported into IBM Content Classification when building a knowledge base.
This same technique could be used in-line in a production Datacap application to build an application that learns based on user choices processing documents that are not identified properly. The results of those choices could be saved and used to build a new knowledge base later which has more accurate information.