An AI that translates letters into information

Now you’ll be able to read between the lines

How things used to be

Paper is indispensable in correspondence between insurance policy holders and insurance companies – for example, a form might be sent by fax, while the claim report and supporting documents are sent by post. The problem is that the information that is relevant to the employees who are processing the claim is hidden somewhere in these written documents. This may include address data, contract numbers and transaction numbers, as well as relevant specialist explanations and references. This data can be found in different letters from different solicitors, for example, and transferring it to an IT system is an arduous and monotonous process. This takes up employees’ valuable time, which they need to complete more complex tasks, and is prone to error.

Then AI came along

The automatic extraction of structured information from unstructured texts is a typical application for AI solutions. We have developed the Heuristic Claims Management (HCM) solution specially for insurance companies. This application automatically searches through incoming correspondence for relevant information, processes it and supplies it to the responsible systems for further structured processing in the applicable formats, such as XML and JSON.

The data is automatically loaded to the processing system. Having to enter it manually becomes a thing of the past, and further processing is fully digitalised.

The situation today

HCM helps to prevent media discontinuities, increase the processing speed and reduce the error quota.

HCM also allows unstructured information to be processed automatically. This helps companies to achieve their digitalisation goals. Administrators are relieved from having to carry out routine activities and are able to concentrate on more challenging tasks.

"Search correspondence, evaluate content, automate editing: In the environment of paper-based communication, an AI application can play to its strengths."

Dr. Thomas Franz, Head of Technology Advisory Board
adesso AG

For which companies is the approach suitable?
Insurance companies, banks and any company that carries out paper-based processes involving the manual extraction of information.
For which decision makers is the approach interesting?
All managers involved in claims management or legal protection. Anyone who is involved in process automation and the digitalisation of paper-based processes.
Backgrounds for the technically interested
Combination of machine-based learning processes such as support-vector machines, random forests and different Bayesian analyses.

Contact

Do you have any questions about AI?

Are you wondering what possibilities AI can open up in your company? Would you like to learn more about its applications and the technology? We cannot give you a pack full of stock responses, but we can share with you our specialist knowledge, our curiosity about your company and our passion for technology.

We would be delighted to talk to you.

Contact

AI Process Model

The AI Process Model: Building AI-based Systems

Developing data-driven AI applications requires a different project structure and expertise than traditional IT solutions. Our "Building AI-based System" fulfill these differences. Coming soon ...

Read more