US 11,455,532 B2 · Single point facility utility sensing for monitoring welfare of a facility occupant

Abstract

The utility usage of a particular individual occupying a residence may give insight into the individual's current cognitive health and/or to enable provision of various services within the facility for the individual, particularly when monitoring patterns in utility usage over time. To enable accurate and non-invasive utility monitoring, a single-point utility sensor may be secured relative to a utility supply line, and generated signals may be utilized to monitor utility usage and to distinguish between utility fixtures. A centralized computing entity may identify frequency characteristics within the generated data, and may automatically generate one or more machine-learning algorithms to distinguish between utility usage events, without requiring substantial user input.

Claims19

Dependent claims

A system for detecting utility usage and distinguishing between utility fixtures within a facility, the system comprising:

at least one utility sensor secured to a utility supply line of a facility, wherein the at least one utility sensor is configured to generate time-series data based at least in part on detected utility usage;
and
an analytic computing entity in network communication with the at least one utility sensor, wherein the analytic computing entity comprises one or more memory storage areas and one or more processors collectively configured to:
transform at least a portion of the time-series data generated by the at least one utility sensor into converted data in a frequency domain;
compress the converted data into vector form via a neural network compression algorithm;
detect discrete utility usage events within the vector form utilizing an event detection algorithm;
cluster discrete utility usage events to generate labels for detected utility usage events;
and
train one or more machine-learning classifier algorithms based at least in part on clustered discrete utility usage events to classify utility usage events by a plurality of fixtures.

6 more elements

A computer-implemented method for detecting utility usage and distinguishing between utility fixtures within a facility, the method comprising:

receiving, via at least one processor, time-series data generated based at least in part on utility usage detected by at least one utility sensor secured to a utility line of a facility;
transforming, via the at least one processor, at least a portion of the time-series data generated by the at least one utility sensor into converted data in a frequency domain;
compressing, via the at least one processor, the converted data into vector form via a neural network compression algorithm;
detecting, via the at least one processor, discrete utility usage events within the vector form utilizing an event detection algorithm;
clustering, via the at least one processor, discrete utility usage events to generate labels for detected utility usage events;
and
training, via the at least one processor, one or more machine-learning classifier algorithms based at least in part on clustered discrete utility usage events to classify utility usage events by a plurality of fixtures.

4 more elements

A computer program product comprising a non-transitory computer readable medium having computer program instructions stored therein, the computer program instructions when executed by a processor, cause the processor to:

receive time-series data generated based at least in part on utility usage detected by at least one utility sensor secured to a utility line of a facility;
transform at least a portion of the time-series data generated by the at least one utility sensor into converted data in a frequency domain;
compress the converted data into vector form via a neural network compression algorithm;
detect discrete utility usage events within the vector form utilizing an event detection algorithm;
cluster discrete utility usage events to generate labels for detected utility usage events;
and
train one or more machine-learning classifier algorithms based at least in part on clustered discrete utility usage events to classify utility usage events by a plurality of fixtures.

4 more elements

Dependencies are inferred from the claim text.

Single point facility utility sensing for monitoring welfare of a facility occupant

Life of this patent

Single point facility utility sensing for monitoring welfare of a facility occupant

Life of this patent

Abstract

Claims19