Personalized device routines
AssigneeAmazon Technologies, Inc.
InventorsSven Eberhardt, Soyoung Kim, Maisie Wang, Kunal Pramod Ghogale
Life of this patent
Estimating the term…
Abstract
Systems and methods for personalized device routines include determining devices associated with user account data and generating device usage data indicating aspects of smart device usage over a period of time. The usage data may then be utilized to identify candidate smart devices, time indicators, and trigger event types to associate with candidate routines. One or more of the candidate routines may be recommended to a user based at least in part on the usage data and the trigger event types at issue to personalize the device routine recommendations.
Claims20
A method comprising:
- generating first data indicating device usage of multiple devices associated with a user account;
- generating, utilizing the first data, a query as input to a trained model configured to infer a routine to recommend, the routine indicating an association between a trigger event and an action to be performed by one or more of the devices associated with the user account responsive to the trigger event when the trigger event occurs;
- inputting the query to the trained model;
- receiving, from the trained model, result data indicating the trained model has inferred a recommended routine utilizing at least the first data, the result data including content generated by the trained model for presenting the recommended routine;
- and
- sending the content to a user device associated with the user account, the content configured to be presented by the user device.
A system, comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
- generating first data indicating device usage of multiple devices associated with a user account;
- generating, utilizing the first data, a query as input to a trained model configured to infer a routine to recommend, the routine indicating an association between a trigger event and an action to be performed by one or more of the devices associated with the user account responsive to the trigger event when the trigger event occurs;
- inputting the query to the trained model;
- receiving, from the trained model, result data indicating the trained model has inferred a recommended routine utilizing at least the first data, the result data including content generated by the trained model for presenting the recommended routine;
- and
- sending the content to a user device associated with the user account, the content configured to be presented by the user device.
Dependencies are inferred from the claim text.