Patents contain a lot of technical, economic and legal information, and they are the main references of enterprises' technological innovation. As a tool of patent analysis and mining, technology/effect matrix provides important support for technological innovation and avoidance. In the process of building technology/effect matrix, most of current technical efficiency annotation is by manually work, which requires heavy labor. Considering the distribution and morphological characteristics of patent abstract texts, this paper proposes a multi-features fused scoring algorithm named PaEffExtr, which automatically extracts effect statements from patent abstract texts. The experimental results show that the algorithm has good recall and accuracy.
展开▼
