Author(s)

Shuangyuan Zou, Wenxi Zheng and Min Wu

Corresponding Author

Shuangyuan Zou

ABSTRACT

As the core-competitiveness of enterprises, patent infringement litigation is becoming more frequent at present. Once companies are involved in patent infringement disputes, they usually spend a lot of time and energy to deal with it. In this paper, the Word2Vec word vector model is trained by some Chinese patent data samples and other Chinese corpus such as Wikipedia, and use this model to calculate the similarity between Chinese words. Then use traditional vector space model (VSM) and Word2Vec model to calculate the similarity of Chinese patent claims. Using similarity to determine whether a patent is infringed. This paper provides an effective method for the retrieval of patent infringement related personnel patent examiners and patent owners, etc.

KEYWORDS

Chinese patent, patent infringement, VSM, Word2Vec