The goal of the PLASS project is the development of a prototypical B2B platform for AI-based decision support for supply chain management. The focus is on the automatic recognition of decision-relevant information and the extraction of structured knowledge from global and multilingual text sources. These sources provide a large database for SCM information, especially for the early recognition of critical events and risks, but also of opportunities, e.g. through new technologies, suppliers and supply chains. PLASS enables SMEs and large enterprises to continuously monitor their suppliers and supply chains, and supports supply chain managers in risk assessment and decision-making. The DFKI plays a central role in the processing of unstructured, textual data. DFKI's work will focus on the development of neural and non-neural text analytics technologies to extract structured knowledge about SC events from global, multilingual sources, while at the same time gaining linguistic knowledge for extraction tasks. A further core task of the DFKI is the investigation of adaptive models for supply chain event extraction with sparse and noisy training data, as well as the provision of high-performance models and services for the generation of SC event and risk information for the platforms of the industrial partners. Further research topics for the DFKI are the development of methods for the integration of external knowledge into neuronal models as well as for cross- and multilingual information extraction. Another focus for DFKI is the further development of the text analytics pipeline SPREE for the application scenarios of the PLASS project.
Lead: Siemens AG Corporate Technology
Partner: Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI), Beuth Hochschule für Technik, Ubermetrics Technologies GmbH, Institut für Angewandte Informatik (InfAI, Universität Leipzig)