基于搜索引擎的模糊字频统计  

Fuzzy frequency statistics of Chinese characters based on search engine

作　　者：李世明[1] 李铮 苑志伟[1] 尤枫[3] 赵恒永[3] 

机构地区：[1]中国石油化工股份有限公司催化剂分公司,北京100011 [2]一零二四互动营销顾问(北京)有限公司,北京100029 [3]北京化工大学信息科学与技术学院,北京100029

出　　处：《计算机工程与设计》2010年第2期443-446,共4页Computer Engineering and Design

摘　　要：针对传统字频统计方法周期长、代价高的弱点,提出了一种利用互联网内容并借助搜索引擎检索进行汉字模糊字频统计的全新方法,有效利用了网络时代的相关技术和发展成果,在一定程度上缓解了字频统计需求频繁的和传统统计方法的低效且代价高昂之间的矛盾,同时对该方法进行了实例化的分析、验证和改进。Considering the traditional frequency statistics methods have drawbacks that may take longer time and higher spending, a brand new way of fuzzy frequency statistics of Chinese characters is presented by utilizing content of Internet and relying on search engines. To a certain degree the new method relieves the inconsistency between excessive demand of frequency statistics and ineffectiveness, expensiveness of traditional statistical method. Meanwhile, the analysis, verification and improvement of this new method are discussed by using a prototype.

关 键 词：中文信息处理 模糊字频统计 搜索引擎 互联网 汉字字频 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]