Sensitive information can automatically be identified in any text-based content. Artificial Intelligence Solutions identify such data on the basis of features in text, such as the appearance of specific words or phrases. Once such information is identified documents are analyzed and categorized against a corporate knowledge structure (i.e., corporate taxonomy or ontology.). Business can use pre-existing taxonomies/ontologies as the knowledge management structures, or it can build a brand new one using a Taxonomy/Ontology Editor. There are two ways to build a knowledge structure:
- manually, using solutions such as the Taxonomy Editor
- by mirroring a file structure, using the Taxonomy Trainer (enabling Artificial Intelligence based on machine learning)
Once the information is correctly tagged and categorized, then automatic workflows can be applied to enforce record management regulations.