Patent US10825318

Sensing peripheral heuristic evidence, reinforcement, and engagement system
[+] Show Details

US10825318

1. A computer-implemented method for training a machine learning module to identify abnormalities or anomalies in sensor data corresponding to conditions associated with individuals in home environments, comprising: (2) (5)

receiving, by a processor, historical sensor data detected by a plurality of sensors associated with a plurality of home environments;

receiving, by a processor, historical condition data indicating conditions associated with individuals in each of the plurality of home environments;

analyzing, by a processor, using the machine learning module, the historical sensor data detected by the plurality of sensors associated with the plurality of home environments and the historical condition data indicating conditions associated with individuals in each of the plurality of home environments, the historical sensor data comprising at least one of a body temperature, a heart rate, a breathing rate, a glucose/ketone level, medication adherence data, eye movement data, exercise data, body control data, fine motor control data, and health and/or nutrition data, and the historical condition data comprising data indicating at least one of a medical condition, a health condition, an urgent condition, and a cognitive condition;

identifying, by a processor, using the machine learning module, based upon the analysis, one or more abnormalities or anomalies in the historical sensor data detected by the plurality of sensors corresponding to conditions associated with the individuals in the home environments; and

modifying, by a processor, the machine learning module based upon the analysis and the identified one or more abnormalities or anomalies with corresponding conditions.

2. The computer-implemented method of claim 1, further comprising: (3) (4)

capturing current data detected by a plurality of sensors associated with a home environment;

analyzing, by a processor, the captured current data to identify one or more abnormalities or anomalies in the current data using the modified machine learning module;

comparing, by a processor, the one or more abnormalities or anomalies in the current data to the abnormalities or anomalies in the historical data detected by the plurality of sensors corresponding to conditions associated with the individuals in the home environments; and

determining, by a processor, based upon the comparison, a current condition associated with an individual in the home environment using the modified machine learning module.

3. The computer-implemented method of claim 2, further comprising: (0) (1)

6. The computer-implemented method of claim 2, wherein the current condition associated with the individual is a medical condition. (0)

7. The computer-implemented method of claim 2, wherein the current condition associated with the individual is an emergency medical condition, the method further comprising: (0) (1)

4. The computer-implemented method of claim 1, wherein the plurality of sensors associated with the plurality of home environments include one or more sensors configured to capture data indicative of electricity use by devices associated with the home environment. (1) (0)

5. The computer-implemented method of claim 4, wherein the data indicative of electricity use includes an indication of one or more of: (0) (5)

(i) which device is using electricity;

(ii) a time at which electricity is used by a particular device;

(iii) a date at which electricity is used by a particular device;

(iv) a duration of electricity use by a particular device; or

(v) a power source for the electricity use.

8. A computer system for training a machine learning module to identify abnormalities or anomalies in sensor data corresponding to conditions associated with individuals in home environments, comprising: (2) (2)

one or more processors; and

one or more memories storing non-transitory computer executable instructions that, when executed by the one or more processors, cause the computer system to: receive historical sensor data detected by a plurality of sensors associated with a plurality of home environments;

receive historical condition data indicating conditions associated with individuals in each of the plurality of home environments;

analyze, using the machine learning module, the historical sensor data detected by the plurality of sensors associated with the plurality of home environments and the historical condition data indicating conditions associated with individuals in each of the plurality of home environments, the historical sensor data comprising at least one of a body temperature, a heart rate, a breathing rate, a glucose/ketone level, medication adherence data, eye movement data, exercise data, body control data, fine motor control data, and health and/or nutrition data, and the historical condition data comprising data indicating at least one of a medical condition, a health condition, an urgent condition, and a cognitive condition;

identify, using the machine learning module, based upon the analysis, one or more abnormalities or anomalies in the historical data detected by the plurality of sensors corresponding to conditions associated with the individuals in the home environments; and

modify the machine learning module based upon the analysis and the identified one or more abnormalities or anomalies with corresponding conditions.

9. The computer system of claim 8, wherein the computer system further comprises one or more sensors associated with the home environment, wherein the one or more processors are configured to interface with the one or more sensors, and wherein the instructions, when executed by the one or more processors, further cause the computer system to: (1) (4)

capture current data detected by a plurality of sensors associated with a home environment;

analyze the captured current data to identify one or more abnormalities or anomalies in the current data using the modified machine learning module;

compare the one or more abnormalities or anomalies in the current data to the abnormalities or anomalies in the historical data detected by the plurality of sensors corresponding to conditions associated with the individuals in the home environments; and

determine, based upon the comparison, a current condition associated with an individual in the home environment using the modified machine learning module.

10. The computer system of claim 9, wherein the instructions, when executed by the one or more processors, further cause the computer system to: (0) (1)

11. The computer system of claim 8, wherein the plurality of sensors associated with the plurality of home environments include one or more sensors configured to capture data indicative of electricity use by devices associated with the home environment. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Patent US10825318

Sensing peripheral heuristic evidence, reinforcement, and engagement system

Patent Matrix® Search