News & Presse
How the insurance industry can benefit from enterprise search modelled on the German mining industry
ambeRoad: Artificial intelligence quickly finds the right data and optimises search results in the process
Search engines such as Google and others show the way: Enter keywords or a short question and the result you are looking for is there. The "KISS42" project promises the answer to all operational questions for RAG. In cooperation with an interdisciplinary RAG team, the start-up ambeRoad from Aachen developed the intelligent search engine amberSearch - designed for the company's special data and requirements. The software from Aachen solves a problem that is not only known in mining, but also in insurance - making knowledge from different archives accessible.
Every third person needs between 5 and 25 minutes per search (!) for a document, other studies by McKinsey assume up to 1.8 hours per day per employee. If one scales this, one arrives at six-digit values for smaller insurance companies alone, which are used for personnel costs for searching for information. Moreover, the search is not only about the search process itself, but also about the processes attached to it. If the employee does not find the required information, a colleague is first asked and thus prevented from working. Alternatively, documents or knowledge are created again, which also costs an enormous amount of time. For this reason, good knowledge availability for employees is crucial for the success of all companies whose success is based on the accessibility of information.
ambeRoad's Enterprise Search helps RAG not only to make the search in RAG's documents efficient for the employees, but above all to make the archived knowledge from 150 years of coal mining usable for current operational tasks. There are many parallels between the IT infrastructure of insurance companies and mining companies: Documents are often stored on universally usable systems such as SharePoint, network drives or the intranet, but are subsequently difficult to find again due to large amounts of data and poor search functions. Such parallels can easily be used by insurance companies to find specific knowledge from older contracts, case studies, relevant insurance conditions or reasons for rejection quickly and efficiently with the help of such innovative technology.
"For us, the project was a successful start to the use of AI methods in the field of geoinformation and search technology. The know-how and innovative spirit of ambeRoad opened up completely new possibilities for the intelligent use of our databases," emphasises Peter Vosen, head of the geodata department at RAG and head of the KISS42 project.
"It's always exciting when start-ups work together with corporations; sometimes two cultures collide," says Julian Reinauer from ambeRoad. "The cooperation with RAG has shown that both sides can learn from each other. On the one hand, the corporations benefit from the speed and agility of the startups, on the other hand, startups gain insights into the processes and structures of large corporations."
It may come as a surprise, but even an artificial intelligence must learn before it can fully display its competence. During a trial phase, the search engine amberSearch first learned what types of data it should be able to read: Geodata, Office documents from Excel to PowerPoint, (scanned) PDFs, but also maps, graphics, images and much more should be available to users to match their query. The advantage of ambeRoad's solution: through customised language models trained without customer data, amberSearch is quickly able to learn the specialised terms of insurance companies. "Training the special terms to our algorithms was a huge challenge at first, but ultimately leads to users learning to love our search," says ambeRoad's Phillipp Reißel.
Teething problems of the software had to be cured, the user-friendliness of the search had to be ensured: As simple as possible, as complex as necessary, was the motto. And finally, the artificial intelligence must also understand and implement the different authorisations of the RAG users so that data protection is maintained with all transparency.
The new search is based on an existing database software, the "Digital Service File". It is available to all RAG employees as a research tool, but so far it only maps a section of the company's data and is more of a Google for specialists. Therefore, other data sources will also be connected in the future. Furterhmore, KISS42 also expands the in-house data with information from the internet, searches and adds to it and creates intelligent links from internal and public documents. The search results are available within a few fractions of a second and this with millions of documents and around 40 terrabytes of data volume.
After the company-wide implementation, the artificial intelligence continues to learn - with every user feedback, every query, based on selected search results and recurring search terms. KISS42 is constantly optimising itself, so to speak, and in the end provides the right answers to all questions.