An automatic classification method for patents
Chi Xue, Qingying Qiu, Peien Feng, Zhen-Nong Yao · 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery · 2010
As an important preprocessing technology in patent knowledge utilization, patent classification should be accurate and efficient. Commonly used feature selection methods and classification algorithms, like information gain (IG) and k nearest neighbors (k-NN) algorithm, are superior in text classification but have some drawbacks in patent classification. In the paper, we focus on patent classification which is rarely cared about by researchers. We present a new systematic classification method called improved IG & k-NN based patent classification (IIKPC) consisted of a new feature selection method based on IG and a new classification algorithm based on k-NN algorithm for automatic patent classification. We ran the experiment on experimental patent dataset and compared the proposed method with other methods usually among the best performing methods for text classification. As the results indicate, we find the proposed method is better than others.