Voice enabling applications
AssigneeAmazon Technologies, Inc.
InventorsManikandan Thangarathnam, Suraj Gopalakrishnan
Life of this patent
Estimating the term…
Abstract
Systems and methods for voice control of computing devices are disclosed. Applications may be downloaded and/or accessed by a device having a display, and content associated with the applications may be displayed. Many applications do not allow for voice commands to be utilized to interact with the displayed content. Improvements described herein allow for non-voice-enabled applications to utilize voice commands to interact with displayed content by determining screen data displayed by the device and utilizing the screen data to determine an intent associated with the application. Directive data to perform an action corresponding to the intent may be sent to the device and may be utilized to perform the action on an object associated with the displayed content.
Claims20
A system comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, from a device, audio data representing a user utterance to control display of content on a display;
- determining a content-streaming application associated with the content being displayed on the display;
- generating, based at least in part on the audio data and the content-streaming application, a command to control display of the content;
- and
- sending the command to the device, the command causing the content-streaming application to control the display of the content on the device.
A method, comprising:
- receiving, from a device, audio data representing a user utterance to control display of content on a screen;
- determining that a content-streaming application is associated with the content being displayed on the screen;
- generating, based at least in part on the audio data, a command to control display of the content, the command associated with the content-streaming application;
- and
- sending the command to the device, the command causing the content-streaming application to control the display of the content on the device.
A system, comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, from a device, audio data representing a user utterance to control content presented on a display;
- determining an application associated with the content being displayed on the display;
- generating, based at least in part on the audio data and the application, a command to control display of the content;
- and
- sending the command to the device, the command causing the application to control display of the content on the display.
Dependencies are inferred from the claim text.