US 11,081,107 B2Granted

Contextual entity resolution

AssigneeAmazon Technologies, Inc.

InventorsKellen Gillespie, Melanie Chie Bomke Gens

Life of this patent

Estimating the term…

Loading patent…

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.

Claims22

Dependent claims

A system, comprising:

at least one processor;
and
at least one computer-readable medium encoded with instructions which, when executed by the at least one processor, cause the system to:
receive, over a first network connection between a computing system and a device controllable using voice commands, audio data representing an utterance received by the device,
determine that a first content source provided content that was presented on a display screen associated with the device while at least a portion of the utterance was spoken,
receive, from a first system component associated with the first content source and after receiving the audio data, contextual data representing at least a portion of the content, the first system component being remote from both of the device and the display screen,
determine, by the computing system and based at least in part on the audio data and the contextual data, an intent of the utterance,
determine output data corresponding to the intent, and
send the output data to an application.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/298,533Filed 11 Mar 2019 · continuation
Priority: 29 Dec 2016
Published: US 2019/0206405 A14 Jul 2019
Granted: 3 Aug 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G06F 40/295
Phrasal analysis, e.g. finite state techniques or chunking: named entity recognition
G06F 40/30
Handling natural language data: semantic analysis
G06Q 30/0201
Marketing; Price estimation or determination; Fundraising: market modelling; Market analysis; Collecting market data