# US 11,113,943 B2 · Systems and methods for predictive environmental fall risk identification

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,113,943 B2
- Document ID: US11113943B2
- Status: Granted
- Kind: B2
- Application number: 16/866,194
- Filed: 2020-05-04
- Published: 2020-11-12
- Granted: 2021-09-07
- Earliest claimed: 2019-05-07
- Assignees: Electronic Caregiver, Inc.
- Applicants: Electronic Caregiver, Inc.
- Inventors: Jacob R. Wright; Hannah S. Rich
- Web page: https://patentgrep.com/patent/US11113943B2

## CPC

- G08B 21/0423: {detecting deviation from an expected pattern of behaviour or schedule}
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 20/00: Machine learning
- G08B 21/0438: {Sensor means for detecting}
- G16H 40/67: for remote operation
- G16H 50/50: for simulation or modelling of medical disorders
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

In various exemplary embodiments, the present technology is directed to systems and methods for predictive environmental fall risk identification for a user.

## Claims

### Claim 1

A method for predictive environmental fall risk identification for a user, the method comprising:
receiving dynamic observations of an environmental map using a sensor;
determining the environmental map;
collecting a set of risk factors for the environmental map using the sensor;
assessing the set of risk factors for the environmental map for a user;
creating a first training set comprising the collected set of risk factors;
training an artificial neural network in a first stage using the first training set;
creating a second training set for a second stage of training comprising the first training set and the dynamic observations of the environmental map;
training the artificial neural network in the second stage using the second training set;
predicting a fall risk of the user using the artificial neural network; and
sending an alert to the user based on the dynamic observations of the environmental map and the fall risk of the user.

### Claim 2 (depends on 1)

The method recited in claim 1, further comprising:
identifying commonly occurring hazards that may cause a fall including one or more of poor lighting in a stairwell and water spills on tile floors.

### Claim 3 (depends on 1)

The method recited in claim 1, further comprising:
optimizing placement of the sensor, the optimizing of placement of the sensor including maximizing coverage to identify and detect both newly formed risks and time remained in a room by the user.

### Claim 4 (depends on 1)

The method recited in claim 1, wherein the assessing the set of risk factors for the environmental map for the user comprises risks associated with different rooms in the environmental map, risks associated with different rooms in the environmental map being better defined using machine-learning to yield predictive identifiers.

### Claim 5 (depends on 1)

The method recited in claim 1, wherein the sensor is a visual sensor.

### Claim 6 (depends on 1)

The method recited in claim 1, wherein the sensor is a radio frequency sensor.

### Claim 7 (depends on 1)

The method recited in claim 1, wherein the sensor is an audio sensor.

### Claim 8 (depends on 1)

The method recited in claim 1, wherein the sensor is a light detection and ranging sensor.

### Claim 9 (depends on 1)

The method recited in claim 1, wherein the fall risk of the user increases when the user travels from a carpet floor to a tile floor.

### Claim 10 (depends on 1)

The method recited in claim 1, wherein the fall risk of the user increases when the user travels from a rug floor to a carpet floor.

### Claim 11

A system for predictive environmental fall risk identification for a user, the system comprising:
a sensor, the sensor providing dynamic observations of an environmental map;
at least one processor; and
a memory storing processor-executable instructions, wherein the at least one processor is configured to implement the following operations upon executing the processor-executable instructions:
determining the environmental map;
collecting a set of risk factors for the environmental map using the sensor;
assessing the set of risk factors for the environmental map for the user;
creating a first training set comprising the collected set of risk factors;
training an artificial neural network in a first stage using the first training set;
creating a second training set for a second stage of training comprising the first training set and the dynamic observations of the environmental map;
training the artificial neural network in the second stage using the second training set;
predicting a fall risk of the user using the artificial neural network; and
sending an alert to the user based on the dynamic observations of the environmental map and the fall risk of the user.

### Claim 12 (depends on 11)

The system of claim 11, further comprising the processor-executable instructions including identifying commonly occurring hazards that may cause a fall including one or more of poor lighting in a stairwell and water spills on tile floors.

### Claim 13 (depends on 11)

The system of claim 11, further comprising the processor-executable instructions including optimizing placement of the sensor, the optimizing of placement of the sensor including maximizing coverage to identify and detect both newly formed risks and time remained in a room by the user.

### Claim 14 (depends on 11)

The system of claim 11, further comprising the processor-executable instructions including wherein the assessing the set of risk factors for the environmental map for the user comprises risks associated with different rooms in the environmental map, risks associated with different rooms in the environmental map being better defined using machine-learning to yield predictive identifiers.

### Claim 15 (depends on 11)

The system of claim 11, wherein the sensor is a visual sensor.

### Claim 16 (depends on 11)

The system of claim 11, wherein the sensor is a radio frequency sensor.

### Claim 17 (depends on 11)

The system of claim 11, wherein the sensor is an audio sensor.

### Claim 18 (depends on 11)

The system of claim 11, wherein the sensor is a light detection and ranging sensor.

### Claim 19 (depends on 11)

The system of claim 11, wherein the fall risk of the user increases when the user travels from a carpet floor to a tile floor.

### Claim 20 (depends on 11)

The system of claim 11, wherein the fall risk of the user increases when the user travels from a rug floor to a carpet floor.