公开(公告)号：US09117447B2

公开(公告)日：2015-08-25

申请号：US13725761

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Thomas Robert Gruber ,  Adam John Cheyer ,  Didier Rene Guzzoni

IPC: G10L21/00 ,  G10L15/18 ,  G06F17/30 ,  G10L15/22 ,  G06F17/28 ,  G06F3/16 ,  G06F9/54 ,  G10L15/26 ,  G10L21/06

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. An event alert is detected, where the event alert includes context data. A representation of an intent is derived based at least in part on the context data. At least one domain, at least one task, and at least one parameter for the task are identified based at least in part on the representation of the intent. The identified task is performed using the at least one parameter. An output is provided to the user, where the output is related to the performance of the first task.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 检测到事件警报，其中事件警报包括上下文数据。 至少部分地基于上下文数据导出意图的表示。 至少部分地基于意图的表示来识别至少一个域，至少一个任务以及用于该任务的至少一个参数。 使用至少一个参数来执行所识别的任务。 向用户提供输出，其中输出与第一任务的性能相关。

公开(公告)号：US08903716B2

公开(公告)日：2014-12-02

申请号：US13725481

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Lik Harry Chen ,  Adam John Cheyer ,  Didier Rene Guzzoni ,  Thomas Robert Gruber

IPC: G06F17/28 ,  G06F17/27 ,  G06F17/21 ,  G10L15/26 ,  G10L17/00 ,  G10L21/00 ,  G06F3/16 ,  G10L15/18 ,  G10L15/22 ,  G06F17/30 ,  G10L21/06 ,  G06F9/54

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A text string is obtained from a speech input received from a user. The received text string is interpreted to derive a representation of user intent based at least in part on a plurality of words associated with a user and stored in memory associated with the user, the plurality of words including words from a plurality of user interactions with an automated assistant. At least one domain, a task, and at least one parameter for the task, are identified based at least in part on the representation of user intent. The identified task is performed. An output is provided to the user, where the output is related to the performance of the task.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 从从用户接收的语音输入获得文本串。 所接收的文本串被解释为至少部分地基于与用户相关联并存储在与用户相关联的存储器中的多个单词来导出用户意图的表示，所述多个单词包括来自多个用户与 自动助理 至少部分地基于用户意图的表示来识别至少一个域，任务和用于该任务的至少一个参数。 执行所识别的任务。 向用户提供输出，其中输出与任务的性能相关。

公开(公告)号：US08799000B2

公开(公告)日：2014-08-05

申请号：US13725713

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Didier Rene Guzzoni ,  Adam John Cheyer ,  Thomas Robert Gruber ,  Christopher Dean Brigham ,  Harry Joseph Saddler

IPC: G10L21/00

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from a user. Two or more alternative interpretations of user intent are obtained based on the received user request. One or more commonalities and one or more differences among the two or more alternative interpretations of user intent are identified. A response is provided to the user, the response presenting at least one of the identified differences and eliciting additional user input to choose among the two or more alternative interpretations of user intent based on the at least one difference.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 接收到用户请求，用户请求至少包括从用户接收的语音输入。 基于接收到的用户请求获得对用户意图的两个或多个替代解释。 识别用户意图的两个或多个替代解释中的一个或多个共同点和一个或多个差异。 向用户提供响应，所述响应呈现所识别的差异中的至少一个，并且引起额外的用户输入，以基于所述至少一个差异在所述两个或更多个用户意图的替代解释中进行选择。

公开(公告)号：US20130117022A1

公开(公告)日：2013-05-09

申请号：US13725481

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Lik Harry Chen ,  Adam John Cheyer ,  Didier Rene Guzzoni ,  Thomas Robert Gruber

IPC: G10L15/26

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A text string is obtained from a speech input received from a user. The received text string is interpreted to derive a representation of user intent based at least in part on a plurality of words associated with a user and stored in memory associated with the user, the plurality of words including words from a plurality of user interactions with an automated assistant. At least one domain, a task, and at least one parameter for the task, are identified based at least in part on the representation of user intent. The identified task is performed. An output is provided to the user, where the output is related to the performance of the task.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 从从用户接收的语音输入获得文本串。 所接收的文本串被解释为至少部分地基于与用户相关联并存储在与用户相关联的存储器中的多个单词来导出用户意图的表示，所述多个单词包括来自多个用户与 自动助理 至少部分地基于用户意图的表示来识别至少一个域，任务和用于该任务的至少一个参数。 执行所识别的任务。 向用户提供输出，其中输出与任务的性能相关。

公开(公告)号：US10318871B2

公开(公告)日：2019-06-11

申请号：US15299264

申请日：2016-10-20

Applicant: Apple Inc.

Inventor： Adam Cheyer ,  Didier Rene Guzzoni

IPC: G06F3/00 ,  G06N5/02 ,  G06F9/54 ,  G09B21/00 ,  G09B23/28 ,  G06N7/00

Abstract: A method and apparatus are provided for building an intelligent automated assistant. Embodiments of the present invention rely on the concept of “active ontologies” (e.g., execution environments constructed in an ontology-like manner) to build and run applications for use by intelligent automated assistants. In one specific embodiment, a method for building an automated assistant includes interfacing a service-oriented architecture that includes a plurality of remote services to an active ontology, where the active ontology includes at least one active processing element that models a domain. At least one of the remote services is then registered for use in the domain.

公开(公告)号：US08942986B2

公开(公告)日：2015-01-27

申请号：US13725550

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Adam John Cheyer ,  Christopher Dean Brigham ,  Didier Rene Guzzoni

IPC: G10L21/00 ,  G10L15/18 ,  G06F17/30 ,  G10L15/22 ,  G06F17/28 ,  G06F3/16 ,  G06F9/54 ,  G10L15/26 ,  G10L21/06

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A plurality of predefined domains each representing a respective area of service offered by an intelligent automated assistant are stored. A text string derived from a user request is obtained, the text string including at least one or more words derived from a speech input received from a user. From the plurality of predefined domains, a relevant domain for the user request is identified based at least on respective degrees of match between the text string derived from the user request and a respective plurality of words associated with each predefined domain. A task is executed in accordance with steps specified in a task flow associated with the relevant domain, and in accordance with one or more task parameters derived from the user request.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 存储各自表示由智能自动助理提供的相应服务区域的多个预定义域。 从用户请求获得的文本串获得，文本串包括从用户接收的语音输入中导出的至少一个或多个单词。 从多个预定义域中，至少基于从用户请求导出的文本串与与每个预定义域相关联的相应多个单词之间的相应匹配度来识别针对用户请求的相关域。 根据与相关域相关联的任务流中指定的步骤并根据从用户请求导出的一个或多个任务参数来执行任务。

公开(公告)号：US08892446B2

公开(公告)日：2014-11-18

申请号：US13725616

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Adam John Cheyer ,  Didier Rene Guzzoni ,  Thomas Robert Gruber ,  Christopher Dean Brigham

IPC: G10L21/00 ,  G10L15/22 ,  G10L15/18 ,  G06F17/28 ,  G10L21/06 ,  G06F17/30 ,  G06F3/16 ,  G06F9/54 ,  G10L15/26

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from the user. The user request is processed to obtain a representation of user intent, where the representation of user intent associates the user request with a task flow operationalizing a requested task, and the task flow is operable to invoke a plurality of services each supporting functions according to a respective plurality of service parameters. Based on the representation of user intent, one or more relevant task parameters are identified from a plurality of task parameters of the task flow. A subset of the plurality of services are selectively invoked during execution of the task flow, where the selectively invoked subset of the plurality of services support functions according to the identified one or more relevant task parameters.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 接收到用户请求，用户请求至少包括从用户接收的语音输入。 处理用户请求以获得用户意图的表示，其中用户意图的表示将用户请求与执行所请求的任务的任务流相关联，并且该任务流可操作以调用多个服务，每个服务根据 相应的多个服务参数。 基于用户意图的表示，从任务流的多个任务参数识别一个或多个相关任务参数。 在所述任务流的执行期间，选择性地调用所述多个服务的子集，其中所述多个服务的选择性调用的子集根据所识别的一个或多个相关任务参数来支持功能。

公开(公告)号：US08660849B2

公开(公告)日：2014-02-25

申请号：US13725656

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Thomas Robert Gruber ,  Adam John Cheyer ,  Didier Rene Guzzoni ,  Christopher Dean Brigham ,  Harry Joseph Saddler

IPC: G10L15/22

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from a user. The user request including the speech input is processed to obtain a representation of user intent for identifying items of a selection domain based on at least one selection criterion. A prompt is provided to the user, the prompt presenting two or more properties relevant to items of the selection domain and requesting the user to specify relative importance between the two or more properties. A listing of search results is provided to the user, where the listing of search results has been obtained based on the at least one selection criterion and the relative importance provided by the user.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 接收到用户请求，用户请求至少包括从用户接收的语音输入。 处理包括语音输入的用户请求，以基于至少一个选择标准来获得用于识别选择域的项目的用户意图的表示。 向用户提供提示，提示呈现与选择域的项目相关的两个或多个属性，并请求用户指定两个或多个属性之间的相对重要性。 搜索结果的列表被提供给用户，其中已经基于至少一个选择标准和用户提供的相对重要性来获得搜索结果的列表。

公开(公告)号：US20130111348A1

公开(公告)日：2013-05-02

申请号：US13725656

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Thomas Robert Gruber ,  Adam John Cheyer ,  Didier Rene Guzzoni ,  Christopher Dean Brigham ,  Harry Joseph Saddler

IPC: G06F3/16

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A user request is received, the user request including at least a speech input received from a user. The user request including the speech input is processed to obtain a representation of user intent for identifying items of a selection domain based on at least one selection criterion. A prompt is provided to the user, the prompt presenting two or more properties relevant to items of the selection domain and requesting the user to specify relative importance between the two or more properties. A listing of search results is provided to the user, where the listing of search results has been obtained based on the at least one selection criterion and the relative importance provided by the user.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 接收到用户请求，用户请求至少包括从用户接收的语音输入。 处理包括语音输入的用户请求，以基于至少一个选择标准来获得用于识别选择域的项目的用户意图的表示。 向用户提供提示，提示呈现与选择域的项目相关的两个或多个属性，并请求用户指定两个或多个属性之间的相对重要性。 搜索结果的列表被提供给用户，其中已经基于至少一个选择标准和用户提供的相对重要性来获得搜索结果的列表。

公开(公告)号：US20130110520A1

公开(公告)日：2013-05-02

申请号：US13725742

申请日：2012-12-21

Applicant: Apple Inc.

Inventor： Adam John Cheyer ,  Didier Rene Guzzoni ,  Thomas Robert Gruber ,  Christopher Dean Brigham

IPC: G10L15/22

CPC classification number: G10L15/1815 ,  B60K35/00 ,  G06F3/167 ,  G06F9/54 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/3087 ,  G10L13/00 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L21/06 ,  H04M1/6091 ,  H04M1/72547 ,  H04M1/72563 ,  H04M1/72597

Abstract: Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A text string is obtained from a speech input received from a user. Information is derived from a communication event that occurred at the electronic device prior to receipt of the speech input. The text string is interpreted to derive a plurality of candidate interpretations of user intent. One of the candidate user intents is selected based on the information relating to the communication event.

Abstract translation: 公开了与操作智能数字助理相关的方法，系统和计算机可读存储介质。 从从用户接收的语音输入获得文本串。 信息来源于在接收语音输入之前在电子设备处发生的通信事件。 文本串被解释为导出用户意图的多个候选解释。 基于与通信事件有关的信息来选择候选用户意图之一。