Cognitive Classification for Input Management

Today, companies receive information in a wide variety of formats and forms, including text, images, tables and forms. Often, these formats are mixed and this is also purposeful, because a piece of information can be expressed differently and better in a certain format than in others.

For automation tools, on the other hand, this heterogeneous flow of information often poses a major challenge. Classic classifiers in input management are often optimized for specific formats and therefore quickly reach their limits. Not so the new cognitive classifier from Insiders, which relies on Deep Learning – and thus takes the automation of business processes to a new level.

“The more precise and comprehensive the input management, the more efficiently the data can be used in the subsequent process flow.”

The hybrid cognitive classifier developed by Insiders Technologies analyzes a document as a whole in one step, combining cognitive capabilities such as recognizing images, reading, seeing structures and layouts. The hybrid cognitive classifier integrates different AI methods and merges their respective strengths into a common deep learning algorithm. This combination in particular results in significant process accelerations and increased automation rates.

In its current issue (76th volume | November 2021), Versicherungswirtschaft also reports on the cognitive classifier from Insiders Technologies. Using practical examples from the insurance industry, authors Karl-Josef Krechel-Mohr and Dr. Darko Obradovic demonstrate the enormous potential savings that these new classification options unleash in companies’ input management.