计算机与现代化 ›› 2013, Vol. 1 ›› Issue (3): 38-40.doi:

• 算法分析与设计 • 上一篇    下一篇

基于姓氏用字驱动与统计的中文姓名识别方法的研究

方玉萍1,罗陈红1,陈 恳2   

  1. 1.云南师范大学职业技术教育学院,云南昆明650032; 2.云南师范大学后勤保障处,云南昆明650032
  • 收稿日期:2012-11-06 修回日期:1900-01-01 出版日期:2013-04-03 发布日期:2013-04-03

Research on a Chinese Name Indentification Method Based  on Family Name Drived and Statistcs

FANG Yu-ping1, LUO Chen-hong1, CHEN Ken2   

  1. 1. College of Vacational and Technical Education, Yunnan Normal University, Kunming 650032, China; 2. Department of Logistical Protection, Yunnan Normal University, Kunming 650032, China
  • Received:2012-11-06 Revised:1900-01-01 Online:2013-04-03 Published:2013-04-03

摘要: 中文姓名识别是中文信息处理中未登录词处理的范畴,同时也是中文文本特征词处理的重要部份。针对中文姓名构成的一般规律和特征,本文进行姓氏用字驱动与统计相结合的中文姓名识别方法的研究,该方法以中文姓氏为驱动,并以此为线索,再结合统计方法评价姓名的真实性。

关键词: 中文姓名识别, 姓氏用字驱动, 统计方法, 识别方法

Abstract: Indentification of Chinese names is field of unknown word in processing of Chinese information, but also it is important to process the feature of Chinese text. Aimed at general laws and characteristics of Chinese name composition, this paper proposes a method of hybrid Chinese name identification based on family name drived approach, which combines methods of statistcs. The method deals surname for driving, and uses it as a clue, combined with the statistical method to evaluation of the authenticity of the name.

Key words: Chinese name indentification, family name drived, statistical method, indentification method