IBM will announce an update to its system to manage and interpret unstructured data in the enterprise next week.
Monday will see IBM unveil the latest version of IBM Classification Module, its "self-learning" content classification software that streamlines enterprise content management.
The system can automatically sift through mounds of information, automatically interpret the meaning of unstructured text in real-time, and categorise that information for users.
More details about the upgrade will be unveiled on Monday, but IBM said extra functionality will allow users to review data more efficiently using the right level of automation.
An improved review capability uses IBM Classification Module's real-time learning technology to provide the system with feedback in order to improve accuracy, and automatically adapt to changes inevitable in the business environment, said IBM.
The ability to understand linguistics, semantics and the context of information allows IBM Classification Module to analyse unstructured and semi-structured content and metadata.