利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

3 条记录 (耗时 0.012 秒)

    VIRTUAL ASSISTANT ESCALATION
    2.
    发明申请
    VIRTUAL ASSISTANT ESCALATION 审中-公开

    公开(公告)号：US20170277993A1

    公开(公告)日：2017-09-28

    申请号：US15465412

    申请日：2017-03-21

    申请人： Next IT Corporation

    发明人： Ian Beaver ,  Fred A. Brown ,  Cynthia Freeman

    IPC分类号： G06N3/00 ,  G06N99/00

    CPC分类号： G06F17/2785 ,  G06F17/279 ,  G06Q30/00 ,  G06Q30/0201

    摘要： Techniques and architectures for analyzing conversations between users and virtual assistants to identify instances where the virtual assistants have not satisfied user requests are described. The techniques and architectures may use such analysis to tag conversations regarding unsatisfied user requests, provide information to users regarding conversations with unsatisfied user requests, learn conversation or contextual data for unsatisfied user requests, and/or perform a variety to other processes to improve the virtual assistants.

    Evaluating Conversation Data based on Risk Factors
    3.
    发明申请
    Evaluating Conversation Data based on Risk Factors 审中-公开
    基于风险因素评估对话数据

    公开(公告)号：US20160071517A1

    公开(公告)日：2016-03-10

    申请号：US14849541

    申请日：2015-09-09

    申请人： Next IT Corporation

    发明人： Ian Beaver ,  Fred Brown ,  Casey Gossard

    IPC分类号： G10L15/18 ,  G06F3/0484 ,  G10L17/22 ,  G10L25/51 ,  G06F17/27 ,  G10L15/06

    CPC分类号： G06F3/04842 ,  G06F17/2785 ,  G06F17/279 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L25/51 ,  G10L25/63 ,  G10L25/66

    摘要： This disclosure describes techniques and architectures for evaluating conversations. In some instances, conversations with users, virtual assistants, and others may be analyzed to identify potential risks within a language model that is employed by the virtual assistants and other entities. The potential risks may be evaluated by administrators, users, systems, and others to identify potential issues with the language model that need to be addressed. This may allow the language model to be improved and enhance user experience with the virtual assistants and others that employ the language model.

    摘要翻译： 本公开描述了用于评估对话的技术和架构。 在某些情况下，可以分析与用户，虚拟助理和其他人的对话，以识别由虚拟助理和其他实体使用的语言模型中的潜在风险。 管理员，用户，系统和其他人可能会评估潜在风险，以确定需要解决的语言模型的潜在问题。 这可能会使语言模型得到改进，并增强了虚拟助手和其他使用语言模型的用户体验。