首页> 外国专利> SYSTEM FOR IDENTIFYING ARTICLES AND METHOD TO DETERMINE THE AUTHENTICITY OF PROPOSITIONS REFLECTING THE RELIABILITY OF MEDIA

SYSTEM FOR IDENTIFYING ARTICLES AND METHOD TO DETERMINE THE AUTHENTICITY OF PROPOSITIONS REFLECTING THE RELIABILITY OF MEDIA

机译:确定文章的系统和方法,确定反映媒体可靠性的提案的真实性

摘要

A method of learning a machine learning model for discriminating articles performed by an article discrimination system reflecting the reliability of the media, according to an embodiment of the present invention, comprising: receiving a subject proposition for authenticity discrimination; Searching a related article by performing a web crawl based on the received target proposition, and calculating a similarity between the target proposition and the sentence included in the searched related article; Determining a sentence as true, false, or neutral according to the similarity of the calculated sentence and setting a discrimination value; And inputting information of the media that provided the relevant article including the sentence, the discrimination value set in each sentence, and the sentence in which the similarity was calculated as learning data into the machine learning model and performing learning. I would like to provide a model learning method.
机译:根据本发明的实施例的学习机器学习模型的方法,该机器学习模型由反映媒体的可靠性的物品判别系统执行以判别物品,该方法包括:接收用于真实性判别的主题命题;通过基于接收到的目标命题进行网络爬取,并计算目标命题与搜索到的相关文章中包含的句子之间的相似度,来搜索相关文章;根据计算出的句子的相似度确定句子为真,假或中性,并设置判别值;并且,将提供包括句子,在每个句子中设置的判别值,以及其中计算了相似度的句子作为学习数据的提供了相关文章的媒体的信息输入到机器学习模型中并进行学习。我想提供一种模型学习方法。

著录项

  • 公开/公告号KR1020200064884A

    专利类型

  • 公开/公告日2020-06-08

    原文格式PDF

  • 申请/专利权人 고려대학교 산학협력단;

    申请/专利号KR1020190098775

  • 发明设计人 정창성;서영경;

    申请日2019-08-13

  • 分类号

  • 国家 KR

  • 入库时间 2022-08-21 10:59:08

相似文献

  • 专利
  • 外文文献
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