Fraunhofer Institute for Intelligent Analysis and Information Systems IAISCutting-edge research on conversational AI and knowledge graphs: At the institute's location in Dresden, we are working on new systems of human-machine interaction and developing dialogue systems for various application areas.
Intelligent systems that support people are already part of our everyday lives: smartphones and voice assistants, for example, accompany us every day, providing support and information – quickly, intuitively and in real time. But Artificial Intelligence systems are also becoming increasingly important in our daily work life and offer great potential to support people in their tasks. Intelligent assistants and learning systems are becoming increasingly important, especially in industry, for example in the area of production technology, logistics or customer service.
Development of Conversational AI and knowledge graphs for companies
Institute branch lab Dresden
Technology offerings
Knowledge graphs
Retrieve information efficiently and conveniently
The amount of data available in companies is growing and growing. Quick access to relevant information can offer decisive advantages.
Knowledge graphs structure data and information, enable semantic linking and, in many cases, are the basis for making Artificial Intelligence applications explainable and delivering results that are comprehensible to humans.
Conversational AI
From chatbot to cognitive assistant
We develop intelligent dialogue systems that enable fast and efficient access to information via voice commands or text input. We work with knowledge-driven language models.
The result: complete solutions for very different areas of application that meet data protection requirements and are tailored to the respective needs of the users – such as specific, German-language technical vocabulary or special requirements of the areas of application. Our solutions are quickly operational and easily scalable.
Large AI language models
Data-based business solutions for European needs
A language model maps how words relate to each other. "Car", for example, is related to "traffic". The AI software learns such relationships from knowledge inputs through texts from websites and books and with the help of neural networks. The more artificial synapses a language model has and the more text it has "read" during training, the better the programme can figure out how to complete a sentence.
The economic potential of new large AI language models and foundation models is enormous. The most successful AI language models still come from the USA and China. These are often not available to the free market, or only to a limited extent, and are only used for English and Chinese languages. Due to the rapidly growing importance of large AI language models, there is an urgent need to ensure technology and data independence as well as innovation and competitiveness in Europe. In the OpenGPT-X project, Fraunhofer IAIS is working on a European answer to the American and Chinese large language models.