IBM Business Automation Content Analyzer

 New in 19.0.1  Content Analyzer is an AI-based REST API web service to extract and classify data from your documents in the IBM Cloud Pak for Automation platform.

Content Analyzer uses and constructs custom Document Ontology from multiple file types. Document classification is done on words, title phrases, keys, and headers. Content Analyzer also uses the Watson™ Natural Language Understanding (NLU) API to extract entities, keywords, and relations from documents. It calls the NLU API by using the ModelID of the model. If the ModelID is not provided in the associated NLU integration, NLU uses the default model to extract document insights.

To use the Watson Discovery Service (WDS), Documents must be segmented into headers and text before you insert them to a WDS instance.

Content Analyzer stores the analysis in PDF, JSON, or UTF-8 text files, and can back up the ontology and other data, and replicate or restore the backed-up data. The output files can be used downstream for further analysis and insight extraction.

For more information, see Business Automation Content Analyzer documentation.