公开(公告)号：US20180276197A1

公开(公告)日：2018-09-27

申请号：US15994795

申请日：2018-05-31

Applicant: Apple Inc.

Inventor： Garett NELL ,  Roshni MALANI ,  Sean P. BROWN ,  Benjamin L. BRUMBAUGH

IPC: G06F17/27 ,  G10L15/22

CPC classification number: G06F17/279 ,  G10L15/22 ,  G10L2015/223 ,  H04L12/2823

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process, discourse input representing a user request is received. The process determines whether the discourse input relates to a device of an established location. In response to determining that the discourse input relates to a device of an established location, a data structure representing a set of devices of the established location is retrieved. The process determines, using the data structure, a user intent corresponding to the discourse input, the user intent associated with an action to be performed by a device of the set of devices, and a criterion to be satisfied prior to performing the action. The action and the device are stored in association with the criterion, where, in accordance with a determination that the criterion is satisfied, the action is performed by the device.

公开(公告)号：US20170357637A1

公开(公告)日：2017-12-14

申请号：US15274859

申请日：2016-09-23

Applicant: Apple Inc.

Inventor： Garett R. NELL ,  Roshni MALANI ,  Sean P. BROWN ,  Benjamin L. BRUMBAUGH

IPC: G06F17/27 ,  G10L15/22

CPC classification number: G06F17/279 ,  G10L15/22 ,  G10L2015/223

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process, discourse input representing a user request can be received. The process can determine one or more possible device characteristics corresponding to the discourse input. Data structure representing a set of devices of an established location can be retrieved. The process can determine, based on the data structure, one or more candidate devices from the set of devices. The one or more candidate devices can correspond to the discourse input. The process can determine, based on the one or more possible device characteristics and one or more actual device characteristics of the one or more candidate devices, a user intent corresponding to the discourse input. Instructions that cause a device of the one or more candidate devices to perform an action corresponding to the user intent can be provided.