公开(公告)号：US11227585B2

公开(公告)日：2022-01-18

申请号：US16815188

申请日：2020-03-11

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Alexandra R. Shapiro ,  Melanie Chie Bomke Gens ,  Spyridon Matsoukas ,  Kellen Gillespie ,  Rahul Goel

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

Abstract: Methods and systems for determining an intent of an utterance using contextual information associated with a requesting device are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Entity data representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. Natural language understanding processing may attempt to resolve one or more declared slots for a particular intent and may generate an initial list of intent hypotheses ranked to indicate which are most likely to correspond to the utterance. The entity data may be compared with the declared slots for the intent hypotheses, and the list of intent hypothesis may be re-ranked to account for matching slots from the contextual metadata. The top ranked intent hypothesis after re-ranking may then be selected as the utterance's intent.

公开(公告)号：US11081107B2

公开(公告)日：2021-08-03

申请号：US16298533

申请日：2019-03-11

Applicant: Amazon Technologies, Inc.

Inventor： Kellen Gillespie ,  Melanie Chie Bomke Gens

IPC: G10L15/22 ,  G10L15/18 ,  G06Q30/02 ,  G06F40/30 ,  G06F40/295 ,  G06F3/16 ,  G06F3/0484 ,  G10L15/26

Abstract: Methods and systems for resolving entities using multi-modal functionality are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Contextual metadata representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. When natural language understanding processing attempts to resolve one or more declared slots for a particular intent, matching slots from the contextual metadata may be determined, and the matching entities may be placed in an intent selected context file to be included with the natural language understanding's output data. The output data may be provided to a corresponding application for causing one or more actions to be performed.

公开(公告)号：US10229680B1

公开(公告)日：2019-03-12

申请号：US15394753

申请日：2016-12-29

Applicant: Amazon Technologies, Inc.

Inventor： Kellen Gillespie ,  Melanie Chie Bomke Gens

IPC: G06F3/16 ,  G06F17/27 ,  G06Q30/02 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26

Abstract: Methods and systems for resolving entities using multi-modal functionality are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Contextual metadata representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. When natural language understanding processing attempts to resolve one or more declared slots for a particular intent, matching slots from the contextual metadata may be determined, and the matching entities may be placed in an intent selected context file to be included with the natural language understanding's output data. The output data may be provided to a corresponding application for causing one or more actions to be performed.

公开(公告)号：US20200279555A1

公开(公告)日：2020-09-03

申请号：US16815188

申请日：2020-03-11

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Alexandra R. Shapiro ,  Melanie Chie Bomke Gens ,  Spyridon Matsoukas ,  Kellen Gillespie ,  Rahul Goel

IPC: G10L15/18 ,  G10L15/22

Abstract: Methods and systems for determining an intent of an utterance using contextual information associated with a requesting device are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Entity data representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. Natural language understanding processing may attempt to resolve one or more declared slots for a particular intent and may generate an initial list of intent hypotheses ranked to indicate which are most likely to correspond to the utterance. The entity data may be compared with the declared slots for the intent hypotheses, and the list of intent hypothesis may be re-ranked to account for matching slots from the contextual metadata. The top ranked intent hypothesis after re-ranking may then be selected as the utterance's intent.

公开(公告)号：US10600406B1

公开(公告)日：2020-03-24

申请号：US15463339

申请日：2017-03-20

Applicant: Amazon Technologies, Inc.

Inventor： Alexandra R. Shapiro ,  Melanie Chie Bomke Gens ,  Spyridon Matsoukas ,  Kellen Gillespie ,  Rahul Goel

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

Abstract: Methods and systems for determining an intent of an utterance using contextual information associated with a requesting device are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Entity data representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. Natural language understanding processing may attempt to resolve one or more declared slots for a particular intent and may generate an initial list of intent hypotheses ranked to indicate which are most likely to correspond to the utterance. The entity data may be compared with the declared slots for the intent hypotheses, and the list of intent hypothesis may be re-ranked to account for matching slots from the contextual metadata. The top ranked intent hypothesis after re-ranking may then be selected as the utterance's intent.

公开(公告)号：US20190206405A1

公开(公告)日：2019-07-04

申请号：US16298533

申请日：2019-03-11

Applicant: Amazon Technologies, Inc.

Inventor： Kellen Gillespie ,  Melanie Chie Bomke Gens

IPC: G10L15/22 ,  G06F17/27 ,  G10L15/18 ,  G06Q30/02

CPC classification number: G10L15/22 ,  G06F3/167 ,  G06F17/278 ,  G06F17/2785 ,  G06Q30/0201 ,  G10L15/1815 ,  G10L15/26 ,  G10L2015/223 ,  G10L2015/225 ,  G10L2015/228

Abstract: Methods and systems for resolving entities using multi-modal functionality are described herein. Voice activated electronic devices may, in some embodiments, be capable of displaying content using a display screen. Contextual metadata representing the content rendered by the display screen may describe entities having similar attributes as an identified intent from natural language understanding processing. When natural language understanding processing attempts to resolve one or more declared slots for a particular intent, matching slots from the contextual metadata may be determined, and the matching entities may be placed in an intent selected context file to be included with the natural language understanding's output data. The output data may be provided to a corresponding application for causing one or more actions to be performed.