Abstract
International patent classifications (IPCs) are assigned to patent documents; however, since the procedure for assigning classifications is manually done by the patent examiner, it takes a lot of time and effort to select some IPCs from about 70,000 IPCs. Hence, some research has been conducted on patent classification with machine learning. However, patent documents are very voluminous, and learning with all the claims (the part describing the content of the patent) as input would run out of the necessary memory. Therefore, most of the existing methods learn by excluding some information, such as using only the first claim as input. In this study, we propose a model that considers the contents of all claims by extracting important information for input. We also propose a new decoder that considers the hierarchical structure of the IPC. Finally, we evaluate the model using an evaluation index that assumes the actual use of IPC selection for patent documents.
A new learning algorithm for the hierarchical structure learning automata operating in the nonstationary S-model random environment
