taking input manage­ment to a new level with the cognitive clas­si­fier

Aug 1, 2022

Insiders has enabled the reliable reco­gni­tion of image and text documents with the Cognitive Clas­si­fier for Debeka. The insurance group thus benefits from an enormous auto­ma­tion effect.

With its diverse range of insurance and financial services, the Debeka Group is one of the top five in the German insurance and home savings industry. Every year, Debeka receives around 16 million document pages via a wide variety of input channels: clas­si­cally by mail or fax, by e‑mail, as an upload via the customer portal, or via sales. In addition to the sheer volume of documents, the com­ple­xity of incoming document types is a challenge due to the many different insurance lines.

Debeka has been using our smart FIX solution very suc­cessfully for several years. Essen­ti­ally, two use cases were imple­mented here: iden­ti­fying the respon­sible division and analyzing the document structure and content. Based on the iden­ti­fied document class, routing to the appro­priate service depart­ment takes place and the cor­re­spon­ding workflows are started.

The incoming mail of the car insurance and building society divisions is cha­rac­te­rized by many incoming documents with images such as accident pictures, real estate plans, or ID documents. These documents offer little potential for purely text-based clas­si­fi­ca­tion and thus had to be indexed almost entirely manually. Thus, the idea arose to extend the text clas­si­fier used so far with an image clas­si­fi­ca­tion. The new Cognitive Clas­si­fier now combines the best of both worlds: the proven excellent text reco­gni­tion and now, newly, the clas­si­fi­ca­tion of images with Deep Learning. The previous workflows remained unchanged and the front end for users also remained the same. The AI continues to work reliably in the back­ground and decides whether text reco­gni­tion, image reco­gni­tion, or both are to be used.

The auto­ma­tion effect of the combined clas­si­fier is enormous. While the majority of documents con­tai­ning images had to be indexed manually before the intro­duc­tion of the new process, this is now less than 10 percent.

„Together with our partner Insiders Tech­no­lo­gies, we have deployed an AI solution that is abso­lutely at the cutting edge for an important use case.This makes working with Insiders fun!“

says Patrick Schneider, Head of Frontend Depart­ment at Debeka Kran­ken­ver­si­che­rungs­verein a. G.

With the Cognitive Clas­si­fier, a universal solution for the clas­si­fi­ca­tion of documents and photos is now available that puts all existing approa­ches in the shade. This allows proven processes to be used even more effec­tively and the level of auto­ma­tion to be further increased. The insurer’s and Insiders‘ project for the Cognitive Clas­si­fier is already attrac­ting a great deal of interest in the industry.