公开(公告)号：US11423908B2

公开(公告)日：2022-08-23

申请号：US16554475

申请日：2019-08-28

Applicant: Apple Inc.

Inventor： Qiwei Sun ,  Gagan Aneja ,  Xinjie Di ,  William Pui Lum Li ,  Deepak Muralidharan

IPC: G10L15/26 ,  G10L15/197 ,  G10L15/22 ,  G10L25/30 ,  G10L15/18

Abstract: In an exemplary process for interpreting spoken requests, audio input containing a user utterance is received. In accordance with a determination that a text representation of the user utterance does not exactly match any of a plurality of user-defined invocation phrases, the process determines whether a comparison between the text representation and a user-defined invocation phrase of the plurality of user-defined invocation phrases satisfies one or more rule-based conditions. In accordance with a determination that the comparison between the text representation and the user-defined invocation phrase satisfies the one or more rule-based conditions, the text representation and the user-defined invocation phrase is processed using a machine-learned model to determine a score representing a degree of semantic equivalence between the text representation and the user-defined invocation phrase. In accordance with a determination that the score satisfies a threshold condition, a predefined task corresponding to the user-defined invocation phrase is performed.

公开(公告)号：US10445429B2

公开(公告)日：2019-10-15

申请号：US15867480

申请日：2018-01-10

Applicant: Apple Inc.

Inventor： Mubarak Ali Seyed Ibrahim ,  Juan C. Garcia ,  Rushin N. Shah ,  Nicholas K. Treadgold ,  Justin J. Brinegar ,  Gagan Aneja ,  Alan Qian

IPC: G06F17/27 ,  G10L15/22 ,  G10L15/26 ,  G10L15/18

Abstract: Systems and processes for natural language processing using vocabularies with compressed serialized tries are described in the present disclosure. In one example process, natural language input is received. The natural language input is parsed, using a vocabulary, to determine a corresponding user intent. The parsing includes using a data structure of the vocabulary to map a first word of the natural language input to first semantic information and a second word of the natural language input to second semantic information. The data structure includes pointers that map to a same semantic data object of the vocabulary. The first semantic information and the second semantic information are determined using the same semantic data object. The user intent is determined based on the first semantic information and the second semantic information. Performance of a task corresponding to the determined user intent is initiated.

公开(公告)号：US20190087412A1

公开(公告)日：2019-03-21

申请号：US15867480

申请日：2018-01-10

Applicant: Apple Inc.

Inventor： Mubarak Ali SEYED IBRAHIM ,  Juan C. GARCIA ,  Rushin N. SHAH ,  Nicholas K. TREADGOLD ,  Justin J. BRINEGAR ,  Gagan Aneja ,  Alan Qian

IPC: G06F17/27

CPC classification number: G06F17/2785 ,  G06F17/27 ,  G06F17/2705 ,  G10L15/1815 ,  G10L15/22 ,  G10L15/26

Abstract: Systems and processes for natural language processing using vocabularies with compressed serialized tries are described in the present disclosure. In one example process, natural language input is received. The natural language input is parsed, using a vocabulary, to determine a corresponding user intent. The parsing includes using a data structure of the vocabulary to map a first word of the natural language input to first semantic information and a second word of the natural language input to second semantic information. The data structure includes pointers that map to a same semantic data object of the vocabulary. The first semantic information and the second semantic information are determined using the same semantic data object. The user intent is determined based on the first semantic information and the second semantic information. Performance of a task corresponding to the determined user intent is initiated.