首页> 外国专利> DUPLICATION NEWS DETECTION SYSTEM AND METHOD FOR DETECTING DUPLICATION NEWS

DUPLICATION NEWS DETECTION SYSTEM AND METHOD FOR DETECTING DUPLICATION NEWS

机译:重复新闻检测系统和检测重复新闻的方法

摘要

The present invention relates to a system and a method for combining overlapping news articles. The system for combining overlapping news articles includes: a sentence similarity computation unit which calculates the similarities of the respective sentences of a particular seed news article and the sentences of an overlapping news article, and calculates the maximum similarity which is the maximum value of the calculated similarities; and a combined news article generation unit which combines the sentences of the overlapping news article to the seed news and generates a combined news article. [Reference numerals] (101) Seed news DB; (102) Search engine; (103) Target news DB; (104) News providing server system A; (105) News providing server system B; (106) News providing server system C; (110) Duplicate candidate news detection unit; (120) Duplicate news detection unit; (130) Duplicate news DB; (140) Duplicate news combining unit; (141) Similarity calculation unit; (142) Combined news generation unit; (150) News recommendation unit; (AA,CC,EE) Seed news; (BB) Target news; (DD) Duplicate candidate news; (FF) Duplicate news; (GG) Network
机译:本发明涉及一种用于组合重叠新闻文章的系统和方法。用于组合重叠新闻的系统包括:句子相似度计算单元,其计算特定种子新闻文章的各个句子与重叠新闻的句子的相似度,并计算最大相似度,该最大相似度是所计算出的最大值。相似点组合新闻文章生成单元,其将重叠的新闻文章的句子组合为种子新闻,并生成组合新闻文章。 [参考数字](101)种子新闻数据库; (102)搜索引擎; (103)目标新闻数据库; (104)新闻提供服务器系统A; (105)新闻提供服务器系统B; (106)新闻提供服务器系统C; (110)候选新闻检测单元重复; (120)新闻检测单元重复; (130)新闻数据库重复; (140)新闻合并部重复; (141)相似度计算单元; (142)合并新闻产生单位; (150)新闻推荐单位; (AA,CC,EE)种子新闻; (BB)目标新闻; (DD)候选新闻重复; (FF)新闻重复; (GG)网络

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