German startup amberSearch, Aachen, unveiled two technical innovations in its online demo: amberGPT and 3D Model Search. These new features offer companies a better way to efficiently use in-house knowledge with Artificial Intelligence (AI) and make 3D models easily searchable by content and visual features (Figure 1).
Fig. 1. 3D model search with amberSearch: a) screws, b) gears. // Bild 1. 3D-Modellsuche mit amberSearch: a) Schrauben, b) Zahnräder. Source/Quelle: ambeRoad
amberGPT revolutionises the use of AI and ChatGPT technology in enterprises. Instead of being based on general knowledge, amberGPT draws on specific and in-house know-how and takes access rights into account. This enables employees to quickly and effortlessly ask questions and get answers to various use cases, such as email suggestions, project reports, contact searches or finding internal policies and guidelines.
The 3D Model Search allows employees from technical professions to effortlessly search 3D models in their organisation for content and visual features. The function makes it possible to quickly find the right part and open it in the target application without users having to tediously click through different systems.
With this innovation, amberSearch addresses:
Employees of medium-sized companies in Germany with 100 to 2,000 employees;
people with an interest in technical innovations (ChatGPT for companies, 3D model search, AI, etc.);
decision-makers who want or need to keep an eye on trends and developments;
cross-sector, especially mechanical engineering, construction and consulting.
ambeRoad Tech GmbH, Aachen/Germany, closes a financing round with various business angels to expand its proprietary software amberSearch and distribution. The founding team (Figure 1), consisting of Julian Johannes Reinauer, Philipp Reißel, Igli Manaj and Bastian Maiworm, pursues the vision of making enterprise search a no-brainer. They enable employees to find knowledge that is stuck in different data silos or file formats. Their intelligent and multimedia search engine amberSearch enables an intuitive search experience, as the user knows it from the web. In contrast to existing solutions, amberSearch searches not only text documents, but also other file formats such as images, videos and audio files. This takes into account the trend that ensures that knowledge is stored in more and more diverse file formats. “We have noticed that the search for information at the workplace is currently tedious and annoying. -ambeRoad puts an end to exactly this annoying search; no one else offers such an easy and fast way to get information. With the investment, we will further democratise access to knowledge within an organisation and thus advance our customers,” says Julian Reinauer, CEO of ambeRoad.
The five investors include former founders as well as managers such as Daniel Rüben, Mirko Kersch-baum and Ralf Kersting. Daniel Rüben comments the investment as follows: “ambeRoad solves several important everyday problems at once: For one thing, I know many friends and acquaintances who always have to spend a lot of time finding the right information in their companies. On the other hand, the topic of “knowledge transfer” is a very important one in SMEs. Those SMEs that manage to pass on their knowledge to new employees and a new generation will definitely be more successful compared to those that do not. Both are important reasons for me to invest in the innovative start-up ambeRoad.”
Fig. 1. The search engine amberSearch of the Aachen-based start-up ambeRoad Tech GmbH helps to make the archived know-ledge from 150 years of coal mining usable for current operational tasks. Photo: RAG, Volker Wiciok
Search engines like 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 Aktiengesellschaft, Essen/Germany. In cooperation with an interdisciplinary RAG team, the start-up ambeRoad Tech GmbH from Aachen developed the intelligent search engine amberSearch – designed for the specific data and requirements of the company (Figure 1). It not only helps to make research in RAG’s documents efficient for employees, but above all to make the archived knowledge from 150 years of coal mining usable for current operational tasks.
“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 has to 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, PDFs, but also maps, graphics, images and much more should be available to users to match the query. Another challenge: the sources. Because the company data are often in different places: in SharePoint team rooms or in databases – they come from SAP, Elo or the company-wide intranet.
Also on the syllabus: the mining language with all its technical terms and the special features of the coal industry – for the coal industry, robbery is not a criminal offence, Walsum is not just a district of Duisburg and West and East refer to much more than just the direction of the sky. “Training our algorithms to use these special terms was a huge challenge at first, but in the end, users learn to love our search,” says Philipp Reißel from ambeRoad.
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 last but not least, 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. Furthermore, in future more data sources will be integrated. 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 TB 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. (ambeRoad/Si.)
