首页> 外国专利> NEWS POSITIVITY LEVEL ANALYSIS SOLUTION AND DEVICE USING DEEP LEARNING NLP MODEL

NEWS POSITIVITY LEVEL ANALYSIS SOLUTION AND DEVICE USING DEEP LEARNING NLP MODEL

机译:新闻阳性级别分析解决方案和设备使用深学习NLP模型

摘要

The present disclosure relates to a method for analyzing a news article, and an electronic device for performing the same method. According to an embodiment, a method for analyzing a news article may comprise the steps of: identifying a sentence including a pre-stored financial word or person word in the news article; inputting a partial sentence of the identified sentence to a neural network model trained to output a score of the news article, and obtaining a first news score from the neural network model; inputting a partial sentence of the identified sentence to a pre-trained model, and obtaining a second news score from the pre-trained model; and on the basis of the first news score and the second news score, determining a global assessment score regarding a financial tendency of the news article.
机译:本公开涉及用于分析新闻制品的方法和用于执行相同方法的电子设备。 根据一个实施例,用于分析新闻文献的方法可以包括以下步骤:识别包括新闻文章中预先存储的财务单词或人字的句子; 将所识别的句子的部分句子输入到培训的神经网络模型,以输出新闻文章的分数,并从神经网络模型获取第一新闻评分; 将所识别的句子的部分句子输入预训练的模型,并从预先训练的模型获取第二个新闻评分; 在第一次新闻评分和第二个新闻评分的基础上,确定了关于新闻文章的财务趋势的全球评估评分。

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