System and method for adaptive indirect monitoring of subject for well-being in unattended setting

• US 10,311,694 B2
• Filed: 10/06/2015
• Issued: 06/04/2019
• Est. Priority Date: 02/06/2014
• Status: Active Grant

• Current Assignee: EmPowerYu, Inc.
• Original Assignee: EmPowerYu, Inc.
• Inventors: McIntosh, Laura Janet, Sieracki, Jeffrey Mark, Wagner, Kirk
• Primary Examiner(s): Waldron, Scott A.
• Assistant Examiner(s): Seck, Ababacar
• Application Number:
  US14/876,648
• Publication Number:
  US 20160027278A1
• Time in Patent Office: 1,337 Days
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0469 Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone G08B21/0476 takes precedence
• CPC Class Codes: G08B 21/0484 Arrangements monitoring consumption of a utility or use of an appliance which consumes a utility to detect unsafe condition, e.g. metering of water, gas or electricity, use of taps, toilet flush, gas stove or electric kettle

Abstract

A system is provided for event-based monitoring of a subject'"'"'s well-being within an unattended setting. A plurality of sensors are disposed within the setting for sensing disparate events, and an analytics processing portion is coupled to the sensors to collectively acquire sensing data therefrom, and map a plurality of sensed data points for a selected combination of disparate events to a conduct adaptively characterized for the subject. The mapping occurs according to a set of pre-established reference event patterns, relative to which each characterized conduct is screened for excessive aberration. The analytics processing portion actuates generation of a graphic user interface displaying at least one reporting page. The reporting page contains for each characterized conduct certain graphic indicia determined responsive to the screening thereof. At least one wirelessly coupled monitoring device actuates responsive to the analytics processing portion to render the graphic user interface for a remotely monitoring user.

Claims

1. A system for indirect event-based monitoring of a subject for well-being within a predefined unattended setting, comprising:

a plurality of sensors disposed within the predefined setting for respectively sensing data indicative of events disparately occurring within the predefined setting;

a record portion storing in computer readable memory a history of activity and state data corresponding to the events, the activity of the subject being defined by at least one corresponding event;

an analytical processing engine coupled to said sensors and record portion, said analytical processing engine including a monitoring update portion programmably configured on a processor for execution to;

collectively acquire the sensed data respectively from a selected combination of said sensors without video surveillance, wherein;

each of said sensors in the selected combination transduces a physically measurable condition,

at least one of said sensors in the selected combination indirectly detects activity of the subject, and is selected from the group consisting of;

light sensors, energy management sensors, power use sensors, entertainment device use sensors, contact sensors, drawer opening/closing sensors, work space sensors, lighting actuation sensors, home automation sensors, glass breakage sensors, water flow sensors, moisture sensors, and pressure sensors; and

,

each of said sensors in the selected combination is situated apart from the subject and independent of subject movement;

selectively detect the events from the sensed data according to at least one of a plurality of predetermined detection parameters, the detected events including at least one event directly sensed by a sensor configured therefor and at least one event indirectly inferred from at least one directly sensed event;

screen the detected events according to at least one screening parameter and selectively assign one of a plurality of response conditions for each of the detected events; and

,

actuate generation of a graphic user interface displaying at least one reporting page for access by at least one authorized person, said reporting page containing a graphically rendered activity portrait indicating the response condition adaptively updated for at least one detected event occurring within a selectively defined time window, and based in part on the activity indirectly detected by the at least one sensor;

at least one monitoring device coupled to said analytical processing engine, said monitoring device being configured to render said graphic user interface for a remotely disposed monitoring user responsive to said analytical processing engine.

2. The system as recited in claim 1, wherein said analytical processing engine further includes a system adjust portion for adjustably configuring said monitoring update portion, said system adjust portion being programmably configured on a processor for execution to:

selectively set each of said predetermined detection parameters applicable to the detected events; and

,

selectively designate the authorized person as a responder and assigning system access limits therefor.

3. The system as recited in claim 1, further comprising at least one monitoring device remotely coupled to said analytical processing engine by a wireless communications link, said monitoring device being actuated responsive to said analytics processing portion to render said graphic user interface for the authorized person.

4. The system as recited in claim 1, wherein said predetermined detection parameters include at least one of:

an event occurrence confidence level, frequency of occurrence for a directly sensed event;

a quantitative threshold for a sensed or derived parameter value corresponding to a detected event; and

,

a set of value ranges for a sensed or derived parameter value corresponding to a detected event, the set of value ranges delineating the plurality of response conditions assignable for the detected event.

5. The system as recited in claim 4, wherein said event occurrence confidence level is statistically computed for each detected event based on past history of activity related thereto.

6. The system as recited in claim 1, wherein the response conditions assignable for each detected event include at least:

normal and anomalous levels.

7. The system as recited in claim 6, wherein said monitoring update portion actuates said graphic user interface to generate notification of the anomalous level of response condition for a detected event responsive to a check for prior aberrant activity related to the detected event.

8. The system as recited in claim 1, wherein the detected events include at least one of:

an inferred out-of-home event, an inferred sleeping event, an inferred eating event, and an inferred quiet event;

each of said inferred events being derived based on a first directly sensed event with reference to corroborating occurrence of at least a second directly sensed event consistent therewith.

9. The system as recited in claim 8, wherein at least one of said inferred events is derived based in part on:

contents of a schedule calendar coupled to said analytical processing engine; and

,

communications from at least one location sensing mechanism remotely disposed from the predefined setting to said analytical processing engine.

10. A method for indirect event-based monitoring of a subject for well-being within a predefined unattended setting, comprising:

selectively installing and actuating a plurality of sensors within the predefined setting to respectively sense data indicative of disparate events occurring within the predefined setting;

storing in a computer readable memory record portion a history of activity and state data corresponding to the events, the activity of the subject being defined by at least one corresponding event;

actuating an analytical processing engine coupled to access said sensors and record portion, executing in said analytical processing engine a monitoring update portion to;

collectively acquire the sensed data respectively from a selected combination of said sensors without video surveillance, wherein;

each of said sensors in the selected combination transduces a physically measurable condition,

at least one of said sensors in the selected combination indirectly detects activity of the subject, and is selected from the group consisting of;

light sensors, energy management sensors, power use sensors, entertainment device use sensors, contact sensors, drawer opening/closing sensors, work space sensors, lighting actuation sensors, home automation sensors, glass breakage sensors, water flow sensors, moisture sensors, and pressure sensors; and

,

each of said sensors in the selected combination is situated apart from the subject and independent of subject movement;

selectively detect the events from the sensed data according to at least one of a plurality of predetermined detection parameters, the detected events including at least one event directly sensed by a sensor configured therefor and at least one event indirectly inferred from at least one directly sensed event;

screen the detected events according to at least one screening parameter and selectively assign one of a plurality of response conditions for each of the detected events; and

,

actuate generation of a graphic user interface displaying at least one reporting page for access by at least one authorized person, said reporting page containing a graphically rendered activity portrait indicating the response condition adaptively updated for at least one detected event occurring within a selectively defined time window, and based in part on the activity indirectly detected by the at least one sensor;

establishing at least one monitoring device coupled to said analytical processing engine; and

,

configuring said monitoring device for actuation responsive to said analytical processing engine to render said graphic user interface for a remotely disposed monitoring user.

11. The method as recited in claim 10, wherein said analytical processing engine executes a system adjust portion for adjustably configuring said monitoring update portion, said system adjust portion:

selectively setting each of said predetermined detection parameters applicable to the detected events; and

,

selectively designating the authorized person as a responder and assigning system access limits therefor.

12. The method as recited in claim 11, wherein said predetermined detection parameters include at least one of:

an event occurrence confidence level, frequency of occurrence for a directly sensed event;

a quantitative threshold for a sensed or derived parameter value corresponding to a detected event; and

,

a set of value ranges for a sensed or derived parameter value corresponding to a detected event, the set of value ranges delineating the plurality of response conditions assignable for the detected event.

13. The method as recited in claim 12, wherein said event occurrence confidence level is statistically computed for each detected event based on past history of activity related thereto.

14. The method as recited in claim 11, wherein:

the response conditions assignable for each detected event include at least;

normal and anomalous levels; and

,

said graphic user interface is actuated to generate notification of the anomalous level of response condition for a detected event responsive to a check for prior aberrant activity related to the detected event.

15. The method as recited in claim 11, wherein:

the detected events include at least one of;

an inferred out-of-home event, an inferred sleeping event, an inferred eating event, and an inferred quiet event;

each of said inferred events being derived based on a first directly sensed event with reference to corroborating occurrence of at least a second directly sensed event consistent therewith; and

,

at least one of said inferred events is derived based in part on;

contents of a schedule calendar coupled to said analytical processing engine; and

,

communications from at least one location sensing mechanism remotely disposed from the predefined setting to said analytical processing engine.

16. A system for indirect event-based monitoring of a subject for well-being within a monitored environment, comprising:

a plurality of sensors disposed within the monitored environment for respectively sensing data indicative of events disparately occurring within the monitored environment;

a record portion storing in computer readable memory a history of activity and state data corresponding to the events, the activity of the subject being defined by at least one corresponding event; and

,

an analytical processing engine coupled to said sensors and record portion, said analytical processing engine including a monitoring update portion programmably configured on a processor for execution to;

collectively acquire the sensed data respectively from a selected combination of said sensors without video surveillance, wherein;

each of said sensors in the selected combination transduces a physically measurable condition,

at least one of said sensors in the selected combination indirectly detects activity of the subject, and is selected from the group consisting of;

light sensors, energy management sensors, power use sensors, entertainment device use sensors, contact sensors, drawer opening/closing sensors, work space sensors, lighting actuation sensors, home automation sensors, glass breakage sensors, water flow sensors, moisture sensors, and pressure sensors; and

,

each of said sensors in the selected combination is situated apart from the subject and independent of subject movement;

selectively detect the events from the sensed data according to at least one of a plurality of predetermined detection parameters, the detected events including at least one event directly sensed by a sensor configured therefor and at least one event indirectly inferred from at least one directly sensed event;

screen the detected events according to at least one screening parameter and selectively assign one of a plurality of response conditions for each of the detected events, said response conditions including at least;

normal and anomalous levels;

actuate generation of a graphic user interface displaying a reporting page for access by a plurality of authorized persons, said reporting page containing a graphically rendered activity portrait concurrently indicating occurrences of at least one detected event and the response condition adaptively updated therefor within a selectively defined time window, and based in part on the activity indirectly detected by the at least one sensor; and

,

a system adjust portion for adjustably configuring said monitoring update portion, said system adjust portion being programmably configured on a processor for execution to;

selectively set each of said predetermined detection parameters applicable to the detected events; and

,

selectively designate the authorized persons as responders and selectively assign system access limits therefor; and

,

at least one monitoring device coupled to said analytical processing engine, said monitoring device being configured to render said graphic user interface for a remotely disposed monitoring user responsive to said analytical processing engine.

17. The system as recited in claim 16, further comprising at least one monitoring device remotely coupled to said analytical processing engine by a wireless communications link, said monitoring device being actuated responsive to said analytics processing portion to render said graphic user interface for one of the authorized persons.

18. The system as recited in claim 17, wherein said predetermined detection parameters include at least one of:

an event occurrence confidence level;

a frequency of occurrence for a directly sensed event;

a quantitative threshold for a sensed or derived parameter value corresponding to a detected event; and

,

a set of value ranges for a sensed or derived parameter value corresponding to a detected event, the set of value ranges delineating the plurality of response conditions assignable for the detected event.

19. The system as recited in claim 17, wherein:

the detected events include at least one of;

an inferred out-of-home event, an inferred sleeping event, an inferred eating event, and an inferred quiet event;

each of said inferred events being derived based on a first directly sensed event with reference to corroborating occurrence of at least a second directly sensed event consistent therewith;

at least one of said inferred events is derived based in part on;

contents of a schedule calendar coupled to said analytical processing engine;

communications from at least one location sensing mechanism remotely disposed from the monitored environment to said analytical processing engine; and

,

said monitoring update portion actuates said graphic user interface to generate notification of the anomalous level of response condition for a detected event responsive to a check for prior aberrant activity related to the detected event.