Ontology matching for patent classification

Interdisciplinary research and development projects in medical engineering benefit from well selected collaboration partners. The process of finding such partners from often unfamiliar fields is difficult, but can be supported by an expert profile that is based on patent analysis and classifying the patents to competence fields in medical engineering. Patent analysis and categorization are difficult and require the analysis of the semantic content. Hence, we propose a twofold approach using a large controlled vocabulary, a smaller competence field ontology, and an alignment between them to assign patents to a certain competence field. The approach has two parts: a Topic Map approach and a Publication approach. We evaluate these approaches and its components in several ways. Furthermore, we compare four different ways to assign a patent to a competence field and show that the semantic wealth of a large biomedical ontology is beneficial to the classification task.