Objectif
In this proposal we will offer a unified view of graph mining systems and recommender systems. We propose a system that monitors the time evolution of graph entities (such as customer-product graphs) and allows for a broad set of knowledge extraction operators. The proposed system will feature advanced collaborative tagging techniques, which we call 'auto-tagging' that aim at automating information extraction about the monitored graph entities from various web sources, such as RSS feeds, blog posts and news events. The system will offer several exhiting innovations such as:
- Incorporation of Ontologies and hierarchies on top of the graph structure
- Automatic expansion of entity information from diverse web sources
- Interactive Exploration of the graph space
- Knowledge extraction algorithms, including clustering and bi-clustering, recommendations, anomaly detection and prediction.
Appel à propositions
FP7-PEOPLE-2009-RG
Voir d’autres projets de cet appel
Régime de financement
MC-IRG - International Re-integration Grants (IRG)Coordinateur
8803 Rueschlikon
Suisse