知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

6 条记录 (耗时 0.016 秒)

    MULTI-COMMAND SINGLE UTTERNACE INPUT METHOD
    2.
    发明申请
    MULTI-COMMAND SINGLE UTTERNACE INPUT METHOD 审中-公开

    公开(公告)号：US20200043482A1

    公开(公告)日：2020-02-06

    申请号：US16600950

    申请日：2019-10-14

    申请人： Apple Inc.

    发明人： Thomas R. GRUBER ,  Harry J. SADDLER ,  Jerome Rene BELLEGARDA ,  Bryce H. NYEGGEN ,  Alessandro SABATELLI

    IPC分类号： G10L15/18 ,  G10L15/28 ,  G10L15/26 ,  G06F17/27

    摘要： Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each sub string can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.

    MULTI-COMMAND SINGLE UTTERANCE INPUT METHOD
    4.
    发明申请
    MULTI-COMMAND SINGLE UTTERANCE INPUT METHOD 有权
    多命令单输入法

    公开(公告)号：US20150348551A1

    公开(公告)日：2015-12-03

    申请号：US14724623

    申请日：2015-05-28

    申请人： Apple Inc.

    发明人： Thomas R. GRUBER ,  Harry J. SADDLER ,  Jerome Rene BELLEGARDA ,  Bryce H. NYEGGEN ,  Alessandro SABATELLI

    IPC分类号： G10L15/26 ,  G06F17/27

    CPC分类号： G10L15/1822 ,  G06F17/2705 ,  G10L15/1815 ,  G10L15/26 ,  G10L15/28 ,  G10L2015/088 ,  G10L2015/221 ,  G10L2015/223 ,  G10L2015/225 ,  G10L2015/228

    摘要： Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.

    摘要翻译： 公开了用于处理虚拟助理的多部分语音命令的系统和过程。 语音输入可以从包含单个话语中的多个可操作命令的用户接收。 可以使用语音转录过程从语音输入生成文本串。 文本字符串可以基于域关键字，命令动词，预定子字符长度等被解析成多个候选子字符串。 对于每个候选子串，可以确定指示候选子串是否对应于可动作命令的概率。 这样的概率可以基于语义一致性，与用户请求模板的相似性，查询服务以确定可管理性等来确定。 如果概率超过阈值，则可以确定每个子串的用户意图，可以执行与用户意图相关联的过程，并且可以向用户提供确认。

    MULTI-COMMAND SINGLE UTTERANCE INPUT METHOD
    5.
    发明申请
    MULTI-COMMAND SINGLE UTTERANCE INPUT METHOD 有权

    公开(公告)号：US20210151041A1

    公开(公告)日：2021-05-20

    申请号：US17127394

    申请日：2020-12-18

    申请人： Apple Inc.

    发明人： Thomas R. GRUBER ,  Harry J. SADDLER ,  Jerome Rene BELLEGARDA ,  Bryce H. NYEGGEN ,  Alessandro SABATELLI

    IPC分类号： G10L15/18 ,  G10L15/26 ,  G10L15/28 ,  G06F40/205

    摘要： Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.