Machine-Learned Smart Home Configuration
AssigneeAdomi, Inc.
InventorsAlon Klein, Binyamin Gil
Life of this patent
Estimating the term…
Abstract
A central hub and database for a smart home environment enable the learning of states associated with items within the smart home and the training one or more machine-learned models associated with the items. After training the machine-learned models, the central hub can modify a state of an item based on the machine-learned model associated with the item. For instance, a window can be opened or shut, a light can be dimmed or turned off, and a door can be locked. Each state of the object can be associated with a set of conditions that, when satisfied, cause the central hub to change the state of the object using the corresponding machine-learned model, for instance without receiving an explicit input from a user.
Claims20
A system for a smart home comprising:
- a central hub comprising one or more hardware processors and communicatively coupled via one or more local networks with one or more sensors, one or more switches, and one or more items within the smart home, the central hub configured to:
- train, for each item of the one or more items within the smart home, a corresponding machine-learned model based on previous states of the item;
- identify one or more conditions associated with a machine-learned model and satisfied by a corresponding item within the smart home;
- and
- change a state of the corresponding item, the state selected based on the machine-learned model and the identified one or more conditions;
- and
- a database storing each trained machine-learned model.
A method comprising:
- training, for each item of one or more items within a smart home, a corresponding machine-learned model based on previous states of the item;
- storing each trained machine-learned model within a database associated with the smart home;
- identifying, by a central hub comprising one or more hardware processors, one or more conditions associated with a machine-learned model and satisfied by a corresponding item within the smart home, the central hub communicatively coupled via one or more local networks with one or more sensors, one or more switches, and the one or more items;
- and
- changing, by the central hub, a state of the corresponding item, the state selected based on the machine-learned model and the identified one or more conditions.
Dependencies are inferred from the claim text.