Graph Convolutional Network Based Patent Issue Discovery Model

With the increasing attention on the protection of intellectual property rights, a large number of patents need to be processed. However, since patent is a kind of complicated technical text, it is difficult to understand patents. How to quickly understand a patent by computer is the problem. To solve the above problem, our method is to tag the issue sentences, these sentences describe problems to be solved in patents. Tagging the issue sentences is a very important research topic in patent understanding, because a patent revolves around issue sentences, issue sentences are the key to understand a patent. There are two challenges in our task: (1) How to extract issue sentences to get corpus? (2) What kinds of features and models are better for our task? In order to solve the above challenges: (1) We find that the issue sentences mainly exist in the “technical background” section of patent, so that we can extract issue sentences from this section to get corpus. (2) We split the “background technology” section into sentences, and obtain two sets of features from a sentence include: 1) Part-of-speech features of a sentence. 2) Association information feature between the sentence and the claim of patent. Then we construct graph according to above two sets of features, and use Graph Convolutional Neural Network to train and test.