11/2024 - Project explanation and research updates of the ODIX project
Even today, a lot of knowledge is still contained in various documents, such as PDFs. In technical areas such as DLR's, this ranges from protocols of various (large-scale) machines to data sheets and other texts. However, these documents are primarily aimed at people and therefore often cannot be processed automatically. This makes it difficult to use this knowledge for analyses and to gain further insights. In some cases, it is even unknown what information is already available.
The aim of ODIX is to develop methods that process the knowledge contained in documents and other sources (e.g. measurement series, process data) in such a way that it can be used directly in AI applications as well as being examined and analysed by humans. To this end, factual information is first extracted from the documents and annotated using semantic concepts. The resulting knowledge graph is stored together with other collected data in a data management system and linked to this data. On this basis, interfaces are then developed for both human and automated utilisation of this now structured knowledge. The project focusses on the requirements and documents of the domain institutes involved in the project.
The project started at the beginning of 2024 and so far we have mainly defined requirements, looked at the state of the art and detailed plans for implementing the project. A first paper on concepts in the project has been submitted.
If you have any questions about the project or are interested in exchanging ideas, please contact us!