US 10,885,091 B1Granted

System and method for content playback

AssigneeAmazon Technologies, Inc.

InventorsJane Meng, Toby Ray Latin-Stoermer, Jason Christopher Hall, Kintan Dilipkumar Brahmbhatt, Daniel Paul Ryan, Benjamin Lee Shepherd, Daren Gill, Brandon Scott Durham

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Approaches provide for a voice communications device to control, refine, or otherwise manage the playback of media content in response to instructions, such as spoken instructions. For example, the voice communications device receives input data associated with a command, such as a request to begin media playback. Accounts corresponding to users associated with the command are identified and one or more refinements extracted from the input data are used to filter content, such as from respective content catalogs or via trained models associated with the users. Determined content is generated that includes content from each of the content catalogs or trained models associated with the users. Thereafter, the voice communications device can initiate media playback.

Claims19

Dependent claims

A computing system, comprising:

a device processor;
a memory device including instructions that, when executed by the device processor, cause the computing system to:
receive input data from a voice communications device, the input data corresponding to a command received by the voice communications device;
determine at least a first user and a second user from the input data;
determine a first account associated with the input data, the first account corresponding to the first user having permission to access content associated with the voice communications device;
determine a second account associated with the input data, the second account corresponding to the second user having permission to access content associated with the voice communications device;
extract a refinement from the command based at least on the first user and the second user, the refinement utilized to determine content accessible via the voice communications device;
analyze a first catalog, associated with the first account, the first catalog being updated based at least in part on content accessed by the first account;
analyze a second catalog, associated with the second account, the second catalog being updated based at least in part on content accessed by the first second account;
use the refinement to identify selected content, the selected content including one or more features corresponding to the refinement and being selected from the first catalog of content and the second catalog of content;
generate a combined set of recommendations from the selected content;
play selected media from the combined set of recommendations using the voice communications device;
and
disregard the selected media for the purposes of updating either the first catalog or the second catalog.

11 more elements

A computing system, comprising:

a computing device processor;
a memory device including instructions that, when executed by the computing device processor, enable the computing system to:
receive input data including a command to access content available to the computing device;
identify a first user associated with the command;
determine an authorized first account corresponding to the first user that includes permission to access the content and is associated with a first trained content model;
retrieve a first user profile from the first trained content model, the first trained content model receiving user interactions with the computing device and predicting user preferences based at least in part on the user interactions;
receive second input data corresponding to a second command to access content available to the computing device;
analyze the second input data, to identify a second user associated with the second command, wherein presence of the second user is identified based on the first command and the second command;
determine the second user does not have an authorized second account;
retrieve a second trained content model, the second trained content model including commands and content corresponding to users without authorized accounts;
determine content corresponding to the command based at least in part on the first user profile and the second content model;
update the second trained content model, based at least in part on the content;
and
disregard the content for the purposes of updating the second trained content model.

11 more elements

A method, comprising:

receiving input data including a command to access content available to the computing device;
identifying a first user associated with the command;
determining an authorized first account corresponding to the first user that includes permission to access the content and is associated with a first trained content model;
retrieving a first user profile from the first trained content model, the first trained content model receiving user interactions with the computing device and predicting user preferences based at least in part on the user interactions;
receiving second input data corresponding to a second command to access content available to the computing device;
analyzing the second input data, to identify a second user associated with the second command, wherein presence of the second user is identified based on the first command and the second command;
determining the second user does not have an authorized second account;
retrieving a second trained content model, the second trained content model including commands and content corresponding to users without authorized accounts;
determining content corresponding to the command based at least in part on the first user profile and the second content model;
updating the second trained content model, based at least in part on the content;
and
disregarding the content for the purposes of updating the second trained content model.

9 more elements

Dependencies are inferred from the claim text.