Granted Patent B1

US 11,633,103 · App. 16/536,588 · Granted Apr 25, 2023

Inventors: Geoffrey Nudd (San Francisco, CA); David Cristman (Walnut Creek, CA); Jonathan J. Hull (San Carlos, CA); Bala Krishna Nakshatrala (Los Angeles, CA)

Assignee: ClearCare, Inc.

A61B5/0022A61B5/165G06F9/542G06F17/18G06N20/10G08B21/0423G10L15/16G10L25/30G10L19/00

Abstract

Claims (41)

1. A system for providing in-home care for seniors, comprising:

a processor;

a memory;

an interface to receive a set of sensor outputs from sensors disposed within a living area of a senior according to a sensor floorplan; and

a machine learning subsystem configured to monitor the set of sensor outputs, map the set of sensor outputs to events associated with features of symptoms of depression, and apply a logistic regression classifier of a machine learning model trained to determine a likelihood that the senior has depression based on the set of sensor outputs, and generate an alert;

wherein determining the likelihood the senior has depression based on the set of sensor output from sensors disposed within the living area the senior includes:

identifying a first relationship between symptoms of depression and events, wherein the events are measurable physical or mental features associated with at least one of the symptoms of depression;

identifying a second relationship between the events and the set of sensor outputs based at least in part on the locations of each sensor and a sensor type of each sensor; and

identifying a third relationship of sensor transformations required to transform sensor data into a format indicative of events;

wherein the first relationship, the second relationship, and the third relationship is used to generate a normalized feature vector that is input to the logistic repression classifier of the machine learning model wherein the logistic regression classifier is trained to determine thresholds for identifying depression based on a training data set of a set of seniors.

2. The system of claim 1 , further comprising a user interface to configure parameters and warnings.

3. The system of claim 1 , further comprising a sensor installation subsystem to determine a number of required sensors, associated sensor types and sensor locations to monitor a psychological or medical condition of the senior.

4. The system of claim 1 , wherein at least one of the sensors is an Internet of Things (IOT) sensor device.

5. The system of claim 1 , wherein the sensor data is selected from:

a voice assistant appliance;

a video assistant appliance;

a smart phone;

a tablet computer;

a smart watch;

a smart appliance;

a personal computer; or

a home monitoring system.

6. The system of claim 1 , wherein the monitoring is performed according to a schedule.

7. A computer implemented method for providing in-home care for seniors, comprising:

receiving a set of sensor outputs from sensors disposed within a living area of a senior according to a sensor floorplan;

mapping the set of sensor outputs to events associated with features of symptoms of depression for the senior to generate an event vector for the senior;

classifying the event vector into a likelihood that the senior has depression based on the set of sensor outputs; wherein the mapping comprises:

identifying a first relationship between symptoms of depression and events, wherein the events are measurable physical or mental features associated with at least one of the symptoms;

identifying a second relationship between the events and the set of sensor outputs based at least in part on the locations of each sensor and a sensor type of each sensor; and

identifying a third relationship of sensor transformations required to transform sensor data into a format indicative of events;

wherein the first relationship, the second relationship, and the third relationship is used to generate a normalized feature vector that is input to a logistic regression classifier of a machine learning model wherein the logistic regression classifier is trained to determine thresholds for identifying depression based on a training data set of a set of seniors.

8. The method of claim 7 , wherein the sensors comprise sensors of user device of the senior and Internet of Thing (IOT) devices.

9. A computer implemented method for providing in-home care for seniors, comprising:

determining a sensor floor plan for a plurality of Internet of Thing (IOT) sensors to be installed in a living space of a senior to generate sensor data that correllates with symptoms of depression in seniors;

receiving a set of sensor outputs from a set of Internet of Thing (IOT) sensors installed in a living space of a senior according to the sensor floorplan;

mapping the set of sensor outputs to events associated with features of symptoms of depression for the senior to generate an event vector for the senior;

classifying the event vector into a likelihood that the senior has depression based on the set of sensor outputs; wherein the mapping comprises:

identifying a first relationship between symptoms of depression and events, wherein the events are measurable physical or mental features associated with at least one of the symptoms;

identifying a second relationship between the events and the set of sensor outputs based at least in part on the locations of each sensor and a sensor type of each sensor; and

identifying a third relationship of sensor transformations required to transform sensor data into a format indicative of events;

wherein the first relationship, the second relationship, and the third relationship is used to generate a normalized feature vector that is input to a classifier of a machine learning model wherein the classifier is trained to determine thresholds for identifying depression based on a training data set of a set of seniors.

Assignments (6)

Continuity (5)

Cited By (10)

US 12,367,876 US 12,393,974 US 12,412,574 US 12,437,865 US 12,444,499 US 12,475,502 US 12,518,871 US 12,548,649 US 12,621,667 US 12,635,904