科研管理

科研管理 ›› 2009, Vol. 30 ›› Issue (2): 70-76 .

• 论文 • 上一篇    下一篇

基于k-means聚类算法的专利地图制作方法研究

邱洪华，余翔   



  1. (华中科技大学管理学院，湖北 武汉430076)
  • 收稿日期:2008-06-03 修回日期:2009-01-06 出版日期:2009-01-01 发布日期:2009-01-01

Research on a method for building up a patent map based on k-means clustering algorithm

Qiu Honghua, Yu Xiang   

  1. School of Management,Huazhong University of Science & Technology,Wuhan 430076,China
  • Received:2008-06-03 Revised:2009-01-06 Online:2009-01-01 Published:2009-01-01

PDF

2596

摘要： 利用专利文献，制作专利地图是有效监测和了解技术发展现状和趋势的重要手段之一，因此最近几年以来，关于专利地图的研究在知识产权领域引起了广泛的关注。本文分析了专利地图在国内外的研究现状，归纳了专利地图的功能，剖析了当前专利地图制作方法的不足，利用了专利文献中的结构化项目和非结构化项目，通过k-means聚类算法，形成语义网络，并最终制作完成可视化专利地图。而根据该专利地图，可以清晰而直观的看出所研究目标技术领域的技术发展路径。

关键词: 专利地图, k-means聚类算法, 专利

Abstract: Abstract: To build up a patent map with patent documents has been one of important means to supervise and realize the developing status quo and trend of technology. The status quo of the research on the patent map at home and abroad is analyzed, the function of patent map is summed up, and a new visualization method for a patent map which represents patent analysis results with considering both structured and unstructured items of each patent document is studied by the adoption of the k-means clustering algorithm and semantic networks; the concrete steps making a patent map which gives a clear and instinctive insight into the targeted technology are suggested.

Key words: patent map, k-means clustering algorithm, patent

中图分类号: