US 10,896,679 B1Granted

Ambient device state content display

AssigneeAmazon Technologies, Inc.

InventorsGuoning Hu, Michael Hart, Seth Brickman, Ashok Gupta, David Jason Jones, Sandy Huang Cook

Life of this patent

Estimating the term…

Loading patent…

Abstract

Devices and techniques are generally described for sending a first instruction for a device to output first content while the speech-processing device is in an ambient state during a first time period. First feedback data is received indicating that a first action associated with the first content was requested at a first time. A determination is made that the first time is during the first time period. Timing data related to a current time of the device is determined. Second content is determined based at least in part on the first action being requested during the first time period and the timing data. A second instruction is sent effective to cause the device to output second content while in the ambient state during a second time period.

Claims20

Dependent claims

A method of determining content, the method comprising:

receiving, from a first computing device, ambient state data comprising an indication of a way in which the first computing device entered into an ambient state, the ambient state comprising a default state of the first computing device;
receiving, from the first computing device, timing data indicating a time of day and a day of week;
generating a first feature vector representation of the ambient state data;
generating a second feature vector representation of the timing data;
sending the first feature vector representation and the second feature vector representation to an input layer of a first machine learning model;
determining first activations of neurons in an output layer of the first machine learning model;
determining first content represented by the first activations;
and
sending a command to the first computing device, the command effective to cause the first computing device to display the first content during the ambient state of the first computing device.

6 more elements

A method comprising:

sending a first command for a device to output first content during a first time period, wherein the first command causes the device to output the first content while in an ambient state of the device;
receiving first feedback data indicating that a first action associated with the first content was requested;
determining that the first action was requested during the first time period;
determining first timing data related to a current time of the device;
determining second content based at least in part on the first action being requested during the first time period and the first timing data;
and
sending a second command for the device to output second content during a second time period, wherein the second command causes the device to output the second content while in the ambient state.

4 more elements

A computing device comprising:

at least one processor;
and
at least one non-transitory computer readable memory storing instructions that, when executed by the at least one processor, program the at least one processor to perform a method comprising:
sending a first command for a device to output first content during a first time period, wherein the first command causes the device to output the first content while in an ambient state of the device;
receiving first feedback data indicating that a first action associated with the first content was requested;
determining that the first action was requested during the first time period;
determining first timing data related to a current time of the device;
determining second content based at least in part on the first action being requested during the first time period and the first timing data;
and
sending a second command for the device to output second content during a second time period, wherein the second command causes the device to output the second content while in the ambient state.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/365,509Filed 26 Mar 2019
Granted: 19 Jan 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification13 codes

G06F 3/167
Sound input; Sound output: audio in a user interface, e.g. using voice commands for navigating, audio feedback
G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G06N 3/0442
Recurrent networks, e.g. Hopfield networks: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]