公开(公告)号：WO2015184186A1

公开(公告)日：2015-12-03

申请号：PCT/US2015/033051

申请日：2015-05-28

Applicant: APPLE INC.

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

IPC: G10L15/18 ,  G10L15/26 ,  G10L15/28 ,  G10L15/08 ,  G10L15/22

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

Abstract: 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.

Abstract translation: 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。

公开(公告)号：WO2014200728A1

公开(公告)日：2014-12-18

申请号：PCT/US2014/040394

申请日：2014-05-30

Applicant: APPLE INC.

Inventor： CARSON, David, A. ,  KEEN, Daniel ,  DIBIASE, Evan, S. ,  SADDLER, Harry, J. ,  IACONO, Marco, P. ,  LEMAY, Stephen, O. ,  PITSCHEL, Donald, W. ,  GRUBER, Thomas, R.

IPC: G06F17/30

CPC classification number: G06F3/167 ,  G06F3/04842 ,  G06F17/30684

Abstract: An electronic device with one or more processors and memory includes a procedure for enabling conversation persistence across two or more instances of a digital assistant. In some embodiments, the device displays a first dialogue in a first instance of a digital assistant user interface. In response to a request to display a user interface different from the digital assistant user interface, the device displays the user interface different from the digital assistant user interface. In response to a request to invoke the digital assistant, the device displays a second instance of the digital assistant user interface, including displaying a second dialogue in the second instance of the digital assistant user interface, where the first dialogue remains available for display in the second instance of the digital assistant user interface.

Abstract translation: 具有一个或多个处理器和存储器的电子设备包括用于在数字助理的两个或多个实例上实现对话持久性的过程。 在一些实施例中，设备在数字助理用户界面的第一实例中显示第一对话。 响应于显示与数字助理用户界面不同的用户界面的请求，设备显示与数字助理用户界面不同的用户界面。 响应于调用数字助理的请求，设备显示数字助理用户界面的第二实例，包括在数字助理用户界面的第二实例中显示第二对话，其中第一对话保持可用于在数字助理用户界面中显示 二次数字助理用户界面。

公开(公告)号：WO2014197737A1

公开(公告)日：2014-12-11

申请号：PCT/US2014/041173

申请日：2014-06-05

Applicant: APPLE INC.

Inventor： GRUBER, Thomas, R. ,  SADDLER, Harry, J. ,  NAPOLITANO, Lia, T. ,  SCHUBERT, Emily, Clark ,  SUMNER, Brian, Conrad

IPC: G06F3/16 ,  G10L15/00 ,  H04M1/60

CPC classification number: G06F3/167 ,  H04M1/6083 ,  H04M1/6091

Abstract: The method includes automatically, without user input and without regard to whether a digital assistant application has been separately invoked by a user, determining that the electronic device is in a vehicle. In some implementations, determining that the electronic device is in a vehicle comprises detecting that the electronic device is in communication with the vehicle (e.g., via a wired or wireless communication techniques and/or protocols). The method also includes, responsive to the determining, invoking a listening mode of a virtual assistant implemented by the electronic device. In some implementations, the method also includes limiting the ability of a user to view visual output presented by the electronic device, provide typed input to the electronic device, and the like.

Abstract translation: 该方法包括自动地，没有用户输入，并且不考虑用户是否单独调用数字助理应用，确定电子设备在车辆中。 在一些实现中，确定电子设备在车辆中包括检测电子设备与车辆通信（例如，经由有线或无线通信技术和/或协议）。 该方法还包括响应于确定，调用由电子设备实现的虚拟助理的聆听模式。 在一些实现中，该方法还包括限制用户查看由电子设备呈现的视觉输出的能力，向电子设备提供类型输入等。

公开(公告)号：WO2016003509A1

公开(公告)日：2016-01-07

申请号：PCT/US2015/023089

申请日：2015-03-27

Applicant: APPLE INC.

Inventor： VAN OS, Marcel ,  SADDLER, Harry, J. ,  NAPOLITANO, Lia, T. ,  RUSSELL, Jonathan, H. ,  LISTER, Patrick, M. ,  DASARI, Rohit

IPC: H04N21/41 ,  G10L15/26 ,  H04N21/422 ,  H04N21/431 ,  H04N21/472

CPC classification number: H04N21/482 ,  G06F17/30823 ,  G09C1/00 ,  G10L15/22 ,  G10L15/26 ,  G10L17/005 ,  G10L17/22 ,  G10L2015/223 ,  H04N21/2541 ,  H04N21/25891 ,  H04N21/4122 ,  H04N21/4126 ,  H04N21/42203 ,  H04N21/4312 ,  H04N21/4316 ,  H04N21/4438 ,  H04N21/4532 ,  H04N21/4627 ,  H04N21/47214 ,  H04N21/4828 ,  H04N21/4882 ,  H04N21/84 ,  H04N21/858

Abstract: Systems and processes are disclosed for controlling television user interactions using a virtual assistant. A virtual assistant can interact with a television set-top box to control content shown on a television. Speech input for the virtual assistant can be received from a device with a microphone. User intent can be determined from the speech input, and the virtual assistant can execute tasks according to the user's intent, including causing playback of media on the television. Virtual assistant interactions can be shown on the television in interfaces that expand or contract to occupy a minimal amount of space while conveying desired information. Multiple devices associated with multiple displays can be used to determine user intent from speech input as well as to convey information to users. In some examples, virtual assistant query suggestions can be provided to the user based on media content shown on a display.

Abstract translation: 公开了用于使用虚拟助理控制电视用户交互的系统和过程。 虚拟助手可以与电视机顶盒进行交互，以控制电视上显示的内容。 可以从具有麦克风的设备接收虚拟助理的语音输入。 可以从语音输入确定用户意图，并且虚拟助理可以根据用户的意图执行任务，包括在电视机上播放媒体。 虚拟助手的互动可以在电视上显示在扩展或收缩的界面中，以占用最小的空间，同时传达所需的信息。 可以使用与多个显示器相关联的多个设备来确定来自语音输入的用户意图以及向用户传达信息。 在一些示例中，可以基于显示器上显示的媒体内容向用户提供虚拟助理查询建议。

公开(公告)号：WO2014197730A1

公开(公告)日：2014-12-11

申请号：PCT/US2014/041159

申请日：2014-06-05

Applicant: APPLE INC.

Inventor： SCHUBERT, Emily, Clark ,  SADDLER, Harry, J. ,  NAPOLITANO, Lia, T. ,  GRUBER, Thomas, R.

IPC: H04M1/60 ,  H04M1/725

CPC classification number: H04M1/72569 ,  H04M1/6075 ,  H04M1/72552 ,  H04M2250/74

Abstract: An electronic device receives a first input that corresponds to a request to open a respective application, and in response to receiving the first input, in accordance with a determination that the device is being operated in a limited-distraction context, provides a limited-distraction user interface that includes providing for display fewer selectable user interface objects than are displayed in a non-limited user interface for the respective application, and in accordance with a determination that the device is not being operated in a limited-distraction context, provides a non-limited user interface for the respective application.

Abstract translation: 电子设备接收对应于打开相应应用的请求的第一输入，并且响应于接收到第一输入，根据在有限分散的上下文中操作该设备的确定，提供有限的分心 用户界面，其包括提供显示比在相应应用的非限制用户界面中显示更少的可选用户界面对象，并且根据确定该设备未在有限分散的上下文中操作， 用于各个应用程序的无限用户界面。

公开(公告)号：WO2018057269A1

公开(公告)日：2018-03-29

申请号：PCT/US2017/049775

申请日：2017-08-31

Applicant: APPLE INC.

Inventor： SADDLER, Harry, J. ,  PIERCY, Aimee, T. ,  WEINBERG, Garrett, L. ,  BOOKER, Susan, L.

IPC: G10L15/00

Abstract: Systems and processes for operating an automated assistant are disclosed. In one example process, an electronic device provides an audio output via a speaker of the electronic device. While providing the audio output, the electronic device receives, via a microphone of the electronic device, a natural language speech input. The electronic device derives a representation of user intent based on the natural language speech input and the audio output, identifies a task based on the derived user intent; and performs the identified task.

Abstract translation: 公开了用于操作自动化助理的系统和过程。 在一个示例过程中，电子设备经由电子设备的扬声器提供音频输出。 在提供音频输出的同时，电子设备经由电子设备的麦克风接收自然语言语音输入。 电子设备基于自然语言语音输入和音频输出导出用户意图的表示，基于导出的用户意图识别任务; 并执行已识别的任务。

公开(公告)号：WO2017213684A1

公开(公告)日：2017-12-14

申请号：PCT/US2016/059953

申请日：2016-11-01

Applicant: APPLE INC.

Inventor： KUDURSHIAN, Aram, D. ,  JONES, Bronwyn ,  CRANFILL, Elizabeth, Caroline ,  SADDLER, Harry, J.

IPC: G06F3/16

Abstract: Systems and processes for operating a digital assistant are provided. In one example, a method includes receiving a first speech input from a user. The method further includes identifying context information and determining a user intent based on the first speech input and the context information. The method further includes determining whether the user intent is to perform a task using a searching process or an object managing process. The searching process is configured to search data, and the object managing process is configured to manage objects. The method further includes, in accordance with a determination the user intent is to perform the task using the searching process, performing the task using the searching process; and in accordance with the determination that the user intent is to perform the task using the object managing process, performing the task using the object managing process.

Abstract translation: 提供了用于操作数字助理的系统和过程。 在一个示例中，一种方法包括接收来自用户的第一语音输入。 该方法进一步包括识别上下文信息并基于第一语音输入和上下文信息确定用户意图。 该方法还包括使用搜索处理或对象管理处理来确定用户意图是否要执行任务。 搜索过程被配置为搜索数据，并且对象管理过程被配置为管理对象。 该方法进一步包括根据用户意图使用搜索过程来执行任务的确定，使用搜索过程来执行任务; 并根据用户意图使用对象管理过程执行任务的确定，使用对象管理过程执行任务。

公开(公告)号：WO2014200731A1

公开(公告)日：2014-12-18

申请号：PCT/US2014/040403

申请日：2014-05-30

Applicant: APPLE INC.

Inventor： ROBERTS, Andrew, J. ,  MARTIN, David, L. ,  SADDLER, Harry, J.

IPC: H04W76/00 ,  H04W4/22

CPC classification number: H04M1/72536 ,  G06F17/2765 ,  H04M1/72572 ,  H04W4/025 ,  H04W4/90 ,  H04W76/50

Abstract: A method of operating a digital assistant to provide emergency call functionality is provided. In some embodiments, the method is performed at a device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a speech input from a user, determining whether the speech input expresses a user request for making an emergency call, and determining a local emergency dispatcher telephone number based on a geographic location of the device. The method also includes, in response to determining or obtaining a determination that the speech input expresses a user request for making an emergency call, calling the local emergency dispatcher telephone number using the emergency call functionality.

Abstract translation: 提供了一种操作数字助理以提供紧急呼叫功能的方法。 在一些实施例中，该方法在包括一个或多个处理器的设备和由一个或多个处理器执行的存储器存储指令的设备上执行。 所述方法包括从用户接收语音输入，确定所述语音输入是否表达用户进行紧急呼叫的请求，以及基于所述设备的地理位置来确定本地紧急调度员电话号码。 该方法还包括响应于确定或获得语音输入表达用户进行紧急呼叫请求的确定，使用紧急呼叫功能来呼叫本地紧急调度员电话号码。

公开(公告)号：WO2013048880A1

公开(公告)日：2013-04-04

申请号：PCT/US2012/056382

申请日：2012-09-20

Applicant: APPLE INC.

Inventor： GRUBER, Thomas, Robert ,  SADDLER, Harry, J.

IPC: H04M1/725

CPC classification number: H04M1/72552 ,  H04M1/72569 ,  H04M2250/74

Abstract: A user interface for a system such as a virtual assistant is automatically adapted for hands-free use. A hands-free context is detected via automatic or manual means, and the system adapts various stages of a complex interactive system to modify the user experience to reflect the particular limitations of such a context. The system of the present invention thus allows for a single implementation of a complex system such as a virtual assistant to dynamically offer user interface elements and alter user interface behavior to allow hands-free use without compromising the user experience of the same system for hands-on use.

Abstract translation: 用于诸如虚拟助理的系统的用户界面被自动地适用于免提使用。 通过自动或手动方式检测免提上下文，并且系统适应复杂交互系统的各个阶段以修改用户体验以反映这种上下文的特定限制。 因此，本发明的系统允许诸如虚拟助理的复杂系统的单个实现来动态地提供用户界面元素并且改变用户界面行为以允许免提使用而不会损害同一系统的用户体验， 使用。