首页> 外国专利> Text mining system for analysis target data, a text mining method for analysis target data and a recording medium for recording analysis target data

Text mining system for analysis target data, a text mining method for analysis target data and a recording medium for recording analysis target data

机译:用于分析目标数据的文本挖掘系统,用于分析目标数据的文本挖掘方法和用于记录分析目标数据的记录介质

摘要

A text mining system including an analysis target search unit which judges whether a commonality in expressions among text data exists, an analysis viewpoint generation unit which generates an analysis viewpoint to extract an expression from the target data, a positive example set identification unit which identifies a positive example set including an expression matching the generated analysis viewpoint in the target data, a characteristic quantity calculation unit which calculates a characteristic quantity showing a degree of characterizing the positive example set of expressions in the target data, and a characteristic expression ranking unit which extracts expressions having the calculated characteristic quantity equal to or greater than a predetermined threshold as characteristic expressions and ranks the extracted characteristic expressions, and the target search unit extracts the analysis viewpoint among which a difference in ranks provided for the characteristic expressions is equal to or greater than a predetermined threshold.
机译:一种文本挖掘系统,包括:分析目标搜索单元,用于判断文本数据之间的表达是否存在共性;分析视点生成单元,用于生成分析视点以从目标数据中提取表达式;正例集识别单元,其用于识别文本数据。包括与目标数据中的生成的分析视点匹配的表达式的正例集,特征量计算单元和特征量排名单元,特征量计算单元计算出表示目标数据中正例集的特征化程度的特征量具有计算出的特征量等于或大于预定阈值的表达式作为特征表达式并对所提取的特征表达式进行排名,并且目标搜索单元提取分析观点,其中为该特征表达式提供的等级差为等于或大于预定阈值。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号