Information exploitation and fusion of heterogeneous data and information

The world of the future will be increasingly digitized and networked. Modern communication technologies enable the dissemination of data and information in (almost) real time. Moreover, technological development in terms of sensors and platforms, databases, etc., as well as network technology and storage capabilities have developed rapidly in recent years, and even mass data can now often be shared and disseminated in a technically straightforward manner. The fusion of heterogeneous data and information is necessary to create a bundled, high-quality information basis for subsequent decisions. It often also makes it possible to recognize valuable connections in the extensive data and information stocks in the first place.

At Fraunhofer IOSB, we develop machine-implementable models and processes that enable IT systems and applications to provide humans with a “cognitive” way of accessing, formalizing, and combining different information contributions and making them usable in the best possible way for solving a specific task.  

Fields of application

We develop tools for the IT-supported fusion of syntactically incompatible data and information, also under consideration of the semantic interoperability and applicability in system networks. The use of Natural Language Processing (NLP) methods also enables the exploitation of unstructured textual information contributions.

In the EU projects MAGNETO and PREVISION, we develop text and data mining methods for the extraction of relevant information from large unstructured text and data collections in order to support police investigators in solving extensive and complex crime cases.