首页> 外国专利> TEXT SENTIMENT ANALYSIS METHOD, READABLE STORAGE MEDIUM, TERMINAL DEVICE, AND APPARATUS

TEXT SENTIMENT ANALYSIS METHOD, READABLE STORAGE MEDIUM, TERMINAL DEVICE, AND APPARATUS

机译:文本情感分析方法,可读存储介质,终端设备和设备

摘要

The present application relates to the technical field of computers, and in particular to a text sentiment analysis method, a computer readable storage medium, a terminal device, and an apparatus. The method comprises: performing word segmentation on a statement text to be analyzed to obtain segmented words constituting the statement text; respectively searching a preset word vector database for column vectors of the segmented words, and forming an input matrix using the column vectors of the segmented words, wherein each column of the input matrix corresponds to a column vector, and the word vector database is a database for recording the correspondence between words and column vectors; selecting, from the statement text, a segmented word corresponding to a preset analysis object as a sentiment subject for text sentiment analysis; inputting the input matrix and an input vector into a preset text sentiment analysis neural network model to obtain a sentiment type of the sentiment subject in the statement text, the input vector being the column vector of the sentiment subject.
机译:本发明涉及计算机技术领域,尤其涉及一种文本情感分析方法,计算机可读存储介质,终端设备和装置。该方法包括:对要分析的语句文本进行单词分割,以获得构成语句文本的分段单词;分别在预设的词向量数据库中查找所述分段词的列向量,并利用所述分段词的列向量形成输入矩阵,所述输入矩阵的每一列对应一列向量,所述词向量数据库为数据库用于记录单词和列向量之间的对应关系;从陈述文本中选择与预设分析对象相对应的分段词作为文本情感分析的情感主体;将输入矩阵和输入向量输入到预设的文本情感分析神经网络模型中,以获取陈述文本中情感主体的情感类型,输入矢量为情感主体的列矢量。

著录项

  • 公开/公告号WO2019196208A1

    专利类型

  • 公开/公告日2019-10-17

    原文格式PDF

  • 申请/专利权人 PING AN TECHNOLOGY(SHENZHEN) CO. LTD.;

    申请/专利号WO2018CN93344

  • 发明设计人 ZHANG YI;WANG WEI;XIAO JING;

    申请日2018-06-28

  • 分类号G06F17/27;G06F17/30;

  • 国家 WO

  • 入库时间 2022-08-21 11:52:54

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