Patent Document Retrieval and Classification at KAIST

In this paper, we propose a method to retrieve similar patent documents for a given patent and classify a given patent. We focus on the one of patents’ characteristics: “patents are structuralized by claims, purposes, effects, embodiments of the invention and so on.” In order to retrieve similar documents from target document set, some specific components to denote the so-called ‘semantic elements’ such as “claim”, “purpose” and “application field” are compared instead of the whole texts. Keyword: Patent Retrieval, Patent Classification, Structural Information, kNN, MEM, Hierarchical Classification