Using Concept Lattices for Visual Navigation Assistance in Large Databases: Application to a Pantent Database

The increasing size of indexed document sets that are digitally available emphasizes the crucial need for more suitable representation tools than traditional textual lists of results. Many efforts have been made to develop graphical tools capable of providing both overall and local views of a collection when focusing on a particular subset of documents. However an overcrowded visual representation may not be useful to users if they are not guided in the navigation process. Our goal is to combine the classification features of FCA and existing visualisation techniques to suggest navigation paths in a visual representation through meaningful and progressive foci. While results are promising, in particular concerning interactions between local and overall views, some difficulties arise concerning non-binary attributes. Therefore we propose embedded Multidimensional scaling (MDS) projection that offers various abstraction layers. The test collection used for our study is an indexed patent database provided by our industrial partner.