首页> 外国专利> Identifying representative conversations using a state model

Identifying representative conversations using a state model

机译:使用状态模型识别代表性对话

摘要

A plurality of conversations may be processed to obtain one or more representative conversations to allow a better understanding of the plurality of conversations. A representative conversation may be determined by representing each conversation as a sequence of states where a state may represent messages with similar meanings. Distances may be computed between pairs of conversations, and the conversations may be clustered using the distances. To obtain a representative conversation for a cluster of conversations, a representative sequence of states may be obtained for the cluster and a representative message may be obtained for each state of the sequence of states. The representative conversation may then be presented to a user.
机译:可以处理多个对话以获得一个或多个代表性对话以允许更好地理解多个对话。可以通过将每个对话作为状态的序列来确定代表性会话,其中状态可以表示具有类似含义的消息。可以在对话对之间计算距离,并且可以使用距离聚集对话。为了获得用于对话群集的代表性会话,可以针对群集获得代表性的状态序列,并且可以针对状态序列的每个状态获得代表性消息。然后可以向用户呈现代表性会话。

著录项

  • 公开/公告号US10984781B2

    专利类型

  • 公开/公告日2021-04-20

    原文格式PDF

  • 申请/专利权人 ASAPP INC.;

    申请/专利号US201916252063

  • 发明设计人 MICHAEL GRIFFITHS;LEI XU;SHAWN HENRY;

    申请日2019-01-18

  • 分类号G10L15/10;G10L15/06;G10L15/14;G06F40/35;G06F40/30;

  • 国家 US

  • 入库时间 2024-06-14 21:26:31

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