-
公开(公告)号：US20210224032A1
公开(公告)日：2021-07-22
申请号：US17226988
申请日：2021-04-09
Applicant: Apple Inc.
Inventor： Ryan M. ORR , Daniel J. MANDEL , Andrew J. SINESIO , Connor J. BARNETT
IPC: G06F3/16 , G10L15/26 , G06F16/48 , G06F40/30 , G06F40/169 , G06F40/279
Abstract: An exemplary method for identifying media may include receiving user input associated with a request for media, where that user input includes unstructured natural language speech including one or more words; identifying at least one context associated with the user input; causing a search for the media based on the at least one context and the user input; determining, based on the at least one context and the user input, at least one media item that satisfies the request; and in accordance with a determination that the at least one media item satisfies the request, obtaining the at least one media item.
-
公开(公告)号：US20190220246A1
公开(公告)日：2019-07-18
申请号：US16360695
申请日：2019-03-21
Applicant: Apple Inc.
Inventor： Ryan M. ORR , Daniel J. MANDEL , Andrew J. SINESIO , Connor J. BARNETT
CPC classification number: G06F3/167 , G06F16/48 , G06F17/241 , G06F17/2765 , G06F17/2785 , G10L15/26
Abstract: An exemplary method for identifying media may include receiving user input associated with a request for media, where that user input includes unstructured natural language speech including one or more words; identifying at least one context associated with the user input; causing a search for the media based on the at least one context and the user input; determining, based on the at least one context and the user input, at least one media item that satisfies the request; and in accordance with a determination that the at least one media item satisfies the request, obtaining the at least one media item.
-
公开(公告)号：US20240379110A1
公开(公告)日：2024-11-14
申请号：US18379094
申请日：2023-10-11
Applicant: Apple Inc.
Inventor： Andrew J. SINESIO , Alexandr N. ABRAMETS , Ivana M. HONG , Ryan R. KLEMS , Catherine M. LOO , Daniel J. MANDEL , Ryan M. ORR , Zeyad H. SALEH
Abstract: Systems and processes for operating an intelligent automated assistant are provided. An exemplary process includes, at a first user device with one or more processors and memory: receiving an audio input including a task and an application for performing the task; in response to a determination that the application is available to the first user device, performing the task with the application at the first user device; in response to a determination that the application is not available to the first user device: causing performance of the task with the application at a second user device; receiving the result of the task from the second user device; and providing the result of the task as an audio output.
-
公开(公告)号：US20200221155A1
公开(公告)日：2020-07-09
申请号：US16367829
申请日：2019-03-28
Applicant: Apple Inc.
Inventor： Bryan HANSEN , Vince LANE , Benjamin S. PHIPPS , Karl Ferdinand SCHRAMM , Andrew J. SINESIO , Jaireh TECARRO
IPC: H04N21/41 , G10L15/22 , H04N21/422 , H04N21/475
Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process, information associated with media playback is received from one or more user devices. A speech request for a media item is received from a user. At least the speech request and the information associated with media playback is transmitted to a second electronic device. Based on at least the speech request and the information associated with media playback, an instruction for media playback on a secondary user device is received. At least one task is performed based on the instruction for media playback.
-
公开(公告)号：US20160378747A1
公开(公告)日：2016-12-29
申请号：US14819343
申请日：2015-08-05
Applicant: Apple Inc.
Inventor： Ryan M. ORR , Daniel J. MANDEL , Andrew J. SINESIO , Connor J. BARNETT
CPC classification number: G06F3/167 , G06F16/48 , G06F17/241 , G06F17/2765 , G06F17/2785 , G10L15/26
Abstract: An exemplary method for identifying media may include receiving user input associated with a request for media, where that user input includes unstructured natural language speech including one or more words; identifying at least one context associated with the user input; causing a search for the media based on the at least one context and the user input; determining, based on the at least one context and the user input, at least one media item that satisfies the request; and in accordance with a determination that the at least one media item satisfies the request, obtaining the at least one media item.
Abstract translation: 用于识别媒体的示例性方法可以包括接收与媒体请求相关联的用户输入，其中该用户输入包括包括一个或多个单词的非结构化自然语言语言; 识别与所述用户输入相关联的至少一个上下文; 基于所述至少一个上下文和所述用户输入来搜索所述媒体; 基于所述至少一个上下文和用户输入确定满足所述请求的至少一个媒体项; 并且根据确定所述至少一个媒体项目满足所述请求，获得所述至少一个媒体项目。
