首页> 外国专利> Method, apparatus and method for matching semantic text data, and computer readable storage medium for storing instructions

Method, apparatus and method for matching semantic text data, and computer readable storage medium for storing instructions

机译:用于匹配语义文本数据的方法,装置和方法,以及用于存储指令的计算机可读存储介质

摘要

The present invention relates toHow to match semantic text data with tagsPreprocessing multiple semantic text dataGet the original corpus data containing multiple semantic independent members andBased on the reproduction relationship in the natural text of multiple semantic independent membersDetermine the degree of association between any two of the multiple semantic independent membersBased on the degree of association between any twoDetermine the theme corresponding to the relevantIn addition, the mapping probability relationship between multiple semantic text data and themes is determinedSelect one of the multiple semantic independent members corresponding to the association as a tag for the themeBased on the mapping probability relationship between the determined semantic text data and the themeMapping multiple semantic text data to tagsThe mapping relationship between the determined semantic text data and the tag is used as training data.Matching unmapping semantic text data to a tag based on training dataA method of including containing.Diagram
机译:本发明涉及用TAGSPREPROOCESSING多个语义文本DATAGET匹配语义文本数据的匹配语义文本数据,其包含多个语义独立成员的原始语料库数据,并且在多个语义独立成员的自然文本中的再现关系上,多个语义中的任何两个之间的关联程度。独立的成员在任何双重细节之间关联的关联程度,对应于相关型添加的主题,多个语义文本数据和主题之间的映射概率关系被确定为与关联对应的多个语义独立成员中的一个作为主题上的标签选择将确定的语义文本数据和针对标签之间的概率关系映射到确定的语义文本数据和标签之间的标签映射关系,用作训练数据。拔样语义文本数据到a基于培训DataA方法的标签,包括包含.diagram

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