公开(公告)号：WO2017058292A1

公开(公告)日：2017-04-06

申请号：PCT/US2016/031059

申请日：2016-05-05

Applicant: APPLE INC.

Inventor： GRUBER, Thomas, R. ,  SKINDER, Jason, A. ,  VESCOVI, Marcos ,  GUZZONI, Didier, Rene

IPC: H04M3/00

CPC classification number: G06N3/006 ,  G06F3/04842 ,  G06F3/0488 ,  G06F17/241 ,  G06F17/28 ,  G06F17/30976 ,  G06N5/04 ,  G06Q10/109 ,  G10L15/1815 ,  G10L15/22 ,  G10L15/26 ,  G10L25/63

Abstract: A method of using a virtual assistant, comprises, at an electronic device configured to transmit and receive data, generating, in response to a trigger, at least one experiential data structure accessible to a virtual assistant, wherein the experiential data structure comprises an organized set of data associated with at least one of the user and the electronic device at a particular point in time. The method further comprises storing at least one experiential data structure; modifying at least one experiential data structure with one or more annotations associated with the experiential data structure, utilizing the virtual assistant; receiving a natural-language user request for service from the virtual assistant; and outputting information responsive to the user request using at least one experiential data structure.

Abstract translation: 一种使用虚拟助理的方法包括：在被配置为发送和接收数据的电子设备中，响应于触发而生成虚拟助理可访问的至少一个经验数据结构，其中经验数据结构包括有组织的集合 在特定时间点与用户和电子设备中的至少一个相关联的数据。 该方法还包括存储至少一个经验数据结构; 利用所述虚拟助理修改具有与经验数据结构相关联的一个或多个注释的至少一个经验数据结构; 从虚拟助手接收服务的自然语言用户请求; 以及使用至少一个经验数据结构来响应于所述用户请求输出信息。

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：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：WO2014197334A2

公开(公告)日：2014-12-11

申请号：PCT/US2014/040393

申请日：2014-05-30

Applicant: APPLE INC. ,  NAIK, Devang, K. ,  WEINER, Liam ,  BINDER, Justin, G. ,  SRISUWANANUKORN, Charles ,  EVERMANN, Gunnar ,  WILLIAMS, Shaun ,  CHEN, Hong ,  NAPOLITANO, Lia, T.

Inventor： NAIK, Devang, K. ,  WEINER, Liam ,  BINDER, Justin, G. ,  SRISUWANANUKORN, Charles ,  EVERMANN, Gunnar ,  WILLIAMS, Shaun ,  CHEN, Hong ,  NAPOLITANO, Lia, T. ,  GRUBER, Thomas, R.

IPC: G10L13/00

CPC classification number: G10L13/027 ,  G10L13/04 ,  G10L13/08 ,  G10L15/063 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0631 ,  G10L2015/0638

Abstract: The method is performed at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors. A first speech input including at least one word is received. A first phonetic representation of the at least one word is determined, the first phonetic representation comprising a first set of phonemes selected from a speech recognition phonetic alphabet. The first set of phonemes is mapped to a second set of phonemes to generate a second phonetic representation, where the second set of phonemes is selected from a speech synthesis phonetic alphabet. The second phonetic representation is stored in association with a text string corresponding to the at least one word.

Abstract translation: 该方法在具有一个或多个处理器的电子设备中执行，存储器存储一个或多个程序以供一个或多个处理器执行。 接收包括至少一个字的第一语音输入。 确定所述至少一个单词的第一语音表示，所述第一语音表示包括从语音识别语音字母表中选择的第一组音素。 将第一组音素映射到第二组音素以产生第二语音表示，其中从语音合成语音字母表中选择第二组音素。 第二语音表示与对应于至少一个单词的文本串相关联地存储。

公开(公告)号：WO2017213682A1

公开(公告)日：2017-12-14

申请号：PCT/US2016/056510

申请日：2016-10-12

Applicant: APPLE INC.

Inventor： WALKER, Robert, A. II ,  NEWENDORP, Brandon, J. ,  DASARI, Rohit ,  GIULI, Richard, D. ,  GRUBER, Thomas, R. ,  RADEBAUGH, Carey, E. ,  GARG, Ashish ,  KHOSLA, Vineet ,  RUSSELL, Jonathan, H. ,  PETERSON, Corey

IPC: G06F17/27

Abstract: Systems and processes for application integration with a digital assistant are provided. In accordance with one example, a method includes, at an electronic device having one or more processors and memory, receiving a natural-language user input; identifying, with the one or more processors, an intent object of a set of intent objects and a parameter associated with the intent, where the intent object and the parameter are derived from the natural-language user input. The method further includes identifying a software application associated with the intent object of the set of intent objects; and providing the intent object and the parameter to the software application.

Abstract translation: 提供应用程序与数字助理集成的系统和过程。 根据一个示例，一种方法包括：在具有一个或多个处理器和存储器的电子设备处接收自然语言用户输入; 利用一个或多个处理器识别一组意图对象的意图对象和与意图相关联的参数，其中意图对象和参数是从自然语言用户输入中导出的。 该方法还包括识别与该意图对象集合的意图对象相关联的软件应用程序; 并向软件应用程序提供意图对象和参数。

公开(公告)号：WO2014197635A2

公开(公告)日：2014-12-11

申请号：PCT/US2014/040961

申请日：2014-06-04

Applicant: APPLE INC.

Inventor： GRUBER, Thomas, R. ,  CHEYER, Adam, J. ,  KEEN, Daniel

CPC classification number: G06Q10/02 ,  G06Q10/109 ,  G06Q30/0203 ,  G06Q30/0259 ,  G06Q30/0269

Abstract: The intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Abstract translation: 智能自动辅助系统使用自然语言对话以集成的对话方式与用户互动，并且在适当时调用外部服务以获得信息或执行各种动作。 可以使用诸如网络，电子邮件，智能手机等的许多不同平台中的任何一个或其任何组合来实现该系统。 在一个实施例中，该系统基于相互关联的域和任务的集合，并且采用额外的功能由外部服务供电，系统可以通过该外部服务进行交互。

公开(公告)号：WO2014124332A2

公开(公告)日：2014-08-14

申请号：PCT/US2014/015418

申请日：2014-02-07

Applicant: APPLE INC.

Inventor： BINDER, Justin, G. ,  TACKIN, Onur ,  POST, Samuel, D. ,  GRUBER, Thomas, R.

IPC: G10L17/24

CPC classification number: G10L21/16 ,  G06F3/167 ,  G10L15/22 ,  G10L15/265 ,  G10L15/30 ,  G10L17/24

Abstract: A method for operating a voice trigger is provided. In some implementations, the method is performed at an electronic device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a sound input. The sound input may correspond to a spoken word or phrase, or a portion thereof. The method includes determining whether at least a portion of the sound input corresponds to a predetermined type of sound, such as a human voice. The method includes, upon a determination that at least a portion of the sound input corresponds to the predetermined type, determining whether the sound input includes predetermined content, such as a predetermined trigger word or phrase. The method also includes, upon a determination that the sound input includes the predetermined content, initiating a speech-based service, such as a voice-based digital assistant.

Abstract translation: 提供了一种用于操作语音触发器的方法。 在一些实现中，该方法在包括一个或多个处理器和用于存储由一个或多个处理器执行的指令的存储器的电子设备处执行。 该方法包括接收声音输入。 声音输入可以对应于说出的单词或短语或其一部分。 该方法包括确定声音输入的至少一部分是否对应于预定类型的声音，诸如人声。 该方法包括，在确定声音输入的至少一部分对应于预定类型时，确定声音输入是否包括预定内容，诸如预定的触发词或短语。 该方法还包括在确定声音输入包括预定内容时，发起基于语音的服务，诸如基于语音的数字助理。

公开(公告)号：WO2014144949A2

公开(公告)日：2014-09-18

申请号：PCT/US2014/029562

申请日：2014-03-14

Applicant: APPLE INC.

Inventor： PITSCHEL, Donald, W. ,  CHEYER, Adam, John ,  BRIGHAM, Christopher, Dean ,  GRUBER, Thomas, R.

IPC: G10L15/22

CPC classification number: G10L15/063 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/227

Abstract: An electronic device with one or more processors and memory includes a procedure for training a digital assistant. In some embodiments, the device detects an impasse in a dialogue between the digital assistant and a user including a speech input. During a learning session, the device utilizes a subsequent clarification input from the user to adjust intent inference or task execution associated with the speech input to produce a satisfactory response. In some embodiments, the device identifies a pattern of success or failure associated with an aspect previously used to complete a task and generates a hypothesis regarding a parameter used in speech recognition, intent inference or task execution as a cause for the pattern. Then, the device tests the hypothesis by altering the parameter for a subsequent completion of the task and adopts or rejects the hypothesis based on feedback information collected from the subsequent completion.

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训练数字助理的过程。 在一些实施例中，设备检测数字助理和包括语音输入的用户之间的对话中的僵局。 在学习会话期间，该设备利用来自用户的后续澄清输入来调整与语音输入相关联的意图推断或任务执行，以产生令人满意的响应。 在一些实施例中，设备识别与先前用于完成任务的方面相关联的成功或失败模式，并且生成关于在语音识别，意图推断或任务执行中使用的参数的假设作为模式的原因。 然后，设备通过改变参数以便随后完成任务来测试假设，并基于从随后完成中收集的反馈信息采用或拒绝该假设。

公开(公告)号：WO2014144395A3

公开(公告)日：2014-09-18

申请号：PCT/US2014/028785

申请日：2014-03-14

Applicant: APPLE INC.

Inventor： PITSCHEL, Donald, W. ,  GRUBER, Thomas, R.

IPC: G06F17/28 ,  G09B19/06 ,  G10L15/22 ,  G09B5/04 ,  G10L15/18

Abstract: The method includes receiving, from a user, a first speech input spoken in a first language; inferring a user intent based on at least the first speech input in the first language; based on the inferred user intent, generating one or more alternative expressions of the first speech input in the first language; and providing feedback to the user introducing the alternative expressions as a more preferred input to express the inferred user intent than the first speech input provided by the user.

公开(公告)号：WO2013173504A8

公开(公告)日：2013-11-21

申请号：PCT/US2013/041225

申请日：2013-05-15

Applicant: APPLE INC.

Inventor： GRUBER, Thomas, R. ,  BRIGHAM, Christopher, D. ,  CHEYER, Adam, J. ,  KEEN, Daniel ,  KOCIENDA, Kenneth

IPC: G06Q10/10

Abstract: The electronic device with one or more processors and memory receives an input of a user. The electronic device, in accordance with the input, identifies a respective task type from a plurality of predefined task types associated with a plurality of third party service providers. The respective task type is associated with at least one third party service provider for which the user is authorized and at least one third party service provider for which the user is not authorized. In response to identifying the respective task type, the electronic device sends a request to perform at least a portion of a task to a third party service provider of the plurality of third party service providers that is associated with the respective task type.