首页> 外国专利> Document information extraction device and document information extraction method

Document information extraction device and document information extraction method

机译:文档信息提取设备和文档信息提取方法

摘要

PROBLEM TO BE SOLVED: To provide a document information extraction device and a document information extraction method for efficiently extracting useful information used for MA (Materials Information) or the like from a huge amount of data such as a patent document. A document information extraction device 100 uses a storage unit 110 to classify words extracted from an extraction source document into categories and a value indicating the degree of conformity with the category to which the words are classified. Category probability table (before adjustment) 112 that contains information indicating a certain category probability, and category probability table (before adjustment) by changing the category probability of the category probability table (before adjustment) based on the structure of sentences containing words in the document. The category probability table (after adjustment) 117 generated by adjusting the previous) is stored. [Selection diagram] FIG. 11
机译:要解决的问题:提供一种文档信息提取装置和文档信息提取方法,用于从诸如专利文献的大量数据中有效地提取用于MA(材料信息)等的有用信息。文档信息提取设备100使用存储单元110将从提取源文档中提取的单词分类为类别,并指示单词被分类的类别的符合性的值。类别概率表(在调整之前)112包含通过改变包含文档中包含单词的词语的句子的结构的类别概率表(在调整之前)的类别概率来指示某个类别概率和类别概率表(在调整之前)的信息。存储通过调整先前生成的类别概率表(调整后)117。 [选择图]图。 11.

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