The analysis of patent data and the exploitation of technical knowledge and trends from patent documents confronts research with major challenges and at the same time offers unimagined opportunities for the exploitation and use within the scientific value creation process, in particular linking essential information from patents with scientific literature and further (domain-specific) sources. Furthermore, the new possibilities that arise from enriched and linked patent knowledge not only allow the derivation of new and efficient indicators for future innovations and developments, but also provide scientists with access to new approaches and solutions, experiments, technical specifications or detailed information such as chemical structures, ready to be used in the context of their everyday research work.

In the area of Patents & Scientific Information, we therefore research and develop new approaches and methods for indexing, analyzing and linking of patent content based on machine learning (ML) and semantic technologies such as Natural Language Processing (NLP), Deep Learning (DL), Knowledge Graphs (KG), etc. addressing different target user groups in the sciences.