US 2020/0090068 A1Published application

State prediction of devices

AssigneeAmazon Technologies, Inc.

InventorsCharles Edwin Ashton Brett, Sara Parker Hillenmeyer, Sven Eberhardt, William Evan Welbourne, Aniruddha Basak, Lizhen Peng

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Systems and methods for state prediction of devices are disclosed. A group of reference devices may be identified and a subset of the reference devices may be identified and/or determined based at least in part on a degree of similarity between reference usage-patterns associated with the reference devices and a usage pattern of a target device. The current state of the subset of the reference devices may be determined and may be utilized to determine a probability that the target device should be in a given state. The state prediction information may be utilized for one or more actions, such as sending recommendations, target inference operations, and/or device configuration, for example.

Claims20

Dependent claims

A system comprising:

one or more processors;
and
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:
determining usage-pattern data associated with a device situated in a first building, the usage-pattern data indicating transitions of the device between an on state and an off state over a period of time, the device associated with a device type indicating functionality of the device;
identifying reference devices associated with the device type;
determining reference usage-pattern data indicating a reference usage pattern of a reference device of the reference devices over the period of time, the reference device situated in a second building, the reference usage pattern indicating transitions of the reference device between the on state and the off state;
determining a degree of similarity between the reference usage pattern and the usage pattern;
identifying, using the degree of similarity, the reference device for inclusion in a subset of the reference devices;
determining, using current-state data indicating a state of the subset of the reference devices, a first number of the subset of the reference devices in the on state;
determining, using the current-state data, a second number of the subset of the reference devices in the off state;
and
determining, from the first number and the second number, a probability value that the device should be in the on state.

9 more elements

A method, comprising:

identifying, based at least in part on a degree of similarity between a reference usage pattern of a reference device of reference devices and a usage pattern associated with a device, the reference device for inclusion in a subset of the reference devices;
determining a first number of the subset of the reference devices in a first state at a time;
determining a second number of the subset of the reference devices in a second state at the time;
and
determining, based at least in part on the first number and the second number, a probability value that the device should be in the first state.

2 more elements

A system comprising:

one or more processors;
and
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:
identifying, based at least in part on a degree of similarity between a reference usage pattern of a reference device of reference devices and a usage pattern associated with a device, the reference device for inclusion in a subset of the reference devices;
determining a first number of the subset of the reference devices in a first state at a time;
determining a second number of the subset of the reference devices in a second state at the time;
and
determining, based at least in part on the first number and the second number, a probability value that the device should be in the first state.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/133,308Filed 17 Sep 2018
Published: 19 Mar 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

H04L 67/535
Network services: tracking the activity of the user
G06F 3/0484
Interaction techniques based on graphical user interfaces [GUI]: for the control of specific functions or operations, e.g. selecting or…
G06F 18/2413
Relating to the classification model, e.g. parametric or non-parametric approaches: based on distances to training or reference patterns
G06N 5/047
Forward inferencing; Production systems: pattern matching networks; Rete networks