# US 2019/0167156 A1 · Method for detecting and responding to falls by residents within a facility

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

- Number: US 2019/0167156 A1
- Document ID: US20190167156A1
- Status: Published application
- Kind: A1
- Application number: 16/257,046
- Filed: 2019-01-24
- Published: 2019-06-06
- Earliest claimed: 2016-06-17
- Assignees: Philips North America LLC
- Applicants: Philips North America LLC
- Inventors: Richard Heaton; Vikram Devdas; Dan Erichsen; Joe Edwards
- Web page: https://patentgrep.com/patent/US20190167156A1

## CPC

- A61B 5/1117: {Fall detection}
- A61B 5/01: Measuring temperature of body parts {; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue} (clinical contact thermometers G01K13/20)
- A61B 5/11: Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb {(A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721)}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- G08B 21/043: {detecting an emergency event, e.g. a fall}
- G08B 21/0446: {worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait}
- G08B 25/001: {Alarm cancelling procedures or alarm forwarding decisions, e.g. based on absence of alarm confirmation}
- G08B 25/016: {Personal emergency signalling and security systems (emergency non-personal manually actuated alarm activators G08B25/12)}
- G08B 29/186: {Fuzzy logic; neural networks}
- G16Z 99/00: Subject matter not provided for in other main groups of this subclass
- H04W 4/023: {using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds}
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- G01P 15/00: Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
- G01P 15/0891: {with indication of predetermined acceleration values (G01P15/135 takes precedence)}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- H04M 3/5116: {for emergency applications}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G16Z: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G01P: MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT (measuring or recording blood flow A61B5/02, A61B8/06; monitoring speed or deceleration of electrically-propelled vehicles B60L3/00; vehicle lighting systems adapted to indicate speed B60Q1/54; determining position or course in navigation, measuring ground distance in geodesy or surveying G01C; combined measuring devices for measuring two or more variables of movement G01C23/00; measuring velocity of sound G01H; measuring velocity of light G01J7/00; measuring direction or velocity of solid objects by reception or emission of radiowaves or other waves and based on propagation effects, e.g. Doppler effect, propagation time, direction of propagation, G01S; measuring speed of nuclear radiation G01T; measuring acceleration of gravity G01V; {measuring or recording the speed of trains B61L23/00; speed indicators incorporated in motor vehicles B60K35/00; measuring frequency or phase G01R; traffic control G08G})
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

One variation of a method for detecting and responding to falls by residents within a facility includes: at a wearable device worn by a resident, writing sensor data from a sensor integrated into the wearable device to a buffer, inputting sensor data into a compressed fall detection model—defining a compressed form of a complete fall detection model and stored locally on the wearable device—to detect a fall event at a first time, and transmitting a corpus of sensor data from the buffer and a cue for confirmation of the fall event to a local wireless hub in response to detecting the fall event; and, remotely from the wearable device, inputting the corpus of sensor data into the complete fall detection model—stored remotely from the wearable device—to confirm the fall event and dispatching a care provider to assist the resident in response to confirming the fall event.

## Claims

### Claim 1

A method for detecting and responding to fall events, the method comprising:
at a wearable device worn by a resident:
at a first time period, recording a first series of sensor data from a sensor integrated into the wearable device;
detecting a fall event during the first time period based on the first series of sensor data and a compressed fall detection model, the compressed fall detection model comprising a first neural network defining a first quantity of nodes; and
in response to detecting the fall event, broadcasting a portion of the first series of sensor data; and
at the computer system remote from the wearable device:
receiving the portion of the first series of sensor data;
confirming the fall event during the first time period based on the portion of the first series of sensor data and a complete fall detection model, the complete fall detection model comprising a second neural network defining a second quantity of nodes greater than the first quantity of nodes; and
in response to confirmation of the fall event, dispatching a care provider to assist the resident.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
detecting the fall event during the first time period based on the first series of sensor data and the compressed fall detection model further comprises:
calculating a first confidence score for an occurrence of the fall event during the first time period based on the first series of sensor data and the compressed fall detection model; and
in response to the first confidence score exceeding a local threshold score, detecting the fall event during the first time period; and
confirming the fall event during the first time period based on the portion of the first series of sensor data and the complete fall detection model further comprises:
calculating a second confidence score for the occurrence of the fall event during the first time period based on the portion first series of sensor data and the complete fall detection model; and
in response to the second confidence score exceeding a global threshold score, confirming the fall event during the first time period.

### Claim 3 (depends on 1)

The method of claim 1, wherein:
recording the first series of sensor data from a sensor integrated into the wearable device further comprises storing the first series of sensor data at a buffer on the wearable device; and
broadcasting the portion of the first series of sensor data further comprises broadcasting the portion of the first series of sensor data from the buffer.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
detecting the fall event during the first time period based on the first series of sensor data and the compressed fall detection model further comprises, detecting the fall event during the first time period based on the first series of sensor data and the compressed fall detection model, the compressed fall detection model comprising the first neural network defining a first quantity of nodes and characterized by a first memory footprint; and
confirming the fall event during the first time period based on the portion of the first series of sensor data and the complete fall detection model further comprises, confirming the fall event during the first time period based on the portion of the first series of sensor data and the complete fall detection model, the complete fall detection model comprising the second quantity of nodes greater than the first quantity of nodes and characterized a second memory footprint greater than the first memory footprint.

### Claim 5 (depends on 1)

The method of claim 1, further comprising, at a local wireless hub remote from the wearable device and the computer system:
receiving the portion of the first series of sensor data; and
transmitting the portion of the first series of sensor data to the computer system remote from the wearable device and the local wireless hub.

### Claim 6 (depends on 5)

The method of claim 5, further comprising, at the local wireless hub:
confirming the fall event during the first time period based on the portion of the first series of sensor data and an intermediate fall detection model, the intermediate fall detection model comprising a third quantity of nodes greater than the first quantity of nodes and less than the second quantity of nodes; and
in response to confirmation of the fall event, transmitting the portion of the first series of sensor data to the computer system remote from the wearable device and the local wireless hub.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
at the computer system remote from the wearable device, the computer system comprising a local wireless hub:
receiving the portion of the first series of sensor data;
confirming the fall event during the first time period based on the portion of the first series of sensor data and the complete fall detection model; and
in response to confirmation of the fall event, dispatching the care provider to assist the resident.

### Claim 8 (depends on 1)

The method of claim 1:
further comprising:
at the wearable device, broadcasting a beacon signal; and
at a local wireless hub, calculating a location of the resident based on a known location of the local wireless hub in response to receipt of the beacon signal from the wearable device; and
wherein dispatching the care provider to assist the resident comprises:
generating a notification comprising a prompt to assist the resident and a pointer to the location of the wearable device; and
transmitting the notification to a computing device associated with the care provider.

### Claim 9

A method for detecting and responding to fall events, the method comprising, at a computer system remote from a wearable device:
receiving a first series of sensor data recorded at a sensor integrated into the wearable device and recorded during a first time period, the first series of sensor data indicating a fall event during the first time period based on a compressed fall detection model stored on the wearable device, the compressed fall detection model comprising a first neural network defining a first quantity of nodes;
confirming the fall event during the first time period based on the first series of sensor data and a complete fall detection model, the complete fall detection model comprising a second neural network defining a second quantity of nodes greater than the first quantity of nodes; and
in response to confirming the fall event:
identifying a location of the wearable device; and
dispatching a care provider to assist the resident at the location of the wearable device.

### Claim 10 (depends on 9)

The method of claim 9, wherein receiving the first series of sensor data further comprises receiving the first series of sensor data from the wearable device.

### Claim 11 (depends on 9)

A method of claim 9, wherein receiving the first series of sensor data further comprises receiving the first series of sensor data from a local wireless gateway.

### Claim 12 (depends on 11)

The method of claim 11, wherein receiving the first series of sensor data from the local wireless gateway further comprises receiving the first series of sensor data from the local wireless gateway, the first series of sensor data indicating the fall event during the first time period based on the compressed fall detection model stored on the wearable device and an intermediate fall detection model stored on the local wireless gateway, and the intermediate fall detection model comprising a third neural network defining a third quantity of nodes greater than the first quantity of nodes and less than the second quantity of nodes.

### Claim 13 (depends on 9)

The method of claim 9, wherein dispatching the care provider to assist the resident at the location of the wearable device further comprises, at a second time transmitting a notification to a computing device associated with the care provider, the notification comprising the location of the wearable device and a prompt to assist the resident.

### Claim 14 (depends on 13)

The method of claim 13, further comprising, deescalating a priority of the notification at the computing device in response to receipt of an input to clear the notification within a threshold duration following the second time at the computing device.

### Claim 15 (depends on 9)

The method of claim 9, wherein dispatching the care provider to assist the resident at the location of the wearable device further comprises, at a second time, transmitting a notification to a set of computing devices, each computing device associated with a care provider and located within a threshold distance of the location of the wearable device, the notification comprising the location of the wearable device and a prompt to assist the resident.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
in response to detecting that a first computing device associated with the care provider arrived at the location of the wearable device at a third time;
calculating a duration of time between the second time and the third time; and
generating an incident report comprising the duration of time.

### Claim 17

A method for detecting and responding to fall events, the method comprising:
at a wearable device worn by a resident:
at a first time period, recording a first series of sensor data from a sensor integrated into the wearable device;
calculating a first confidence score for an occurrence of a fall event during the first time period based on the first series of sensor data and a compressed fall detection model, the compressed fall detection model comprising a first neural network defining a first quantity of nodes, characterized by a first memory footprint, and defining a compressed form of a complete fall detection model; and
in response to the first confidence score exceeding a local threshold score, transmitting the first series of sensor data to a computer system remote from the wearable device; and
at the computer system remote from the wearable device:
calculating a second confidence score for the occurrence of the fall event during the first time period based on the first series of sensor data and the complete fall detection model, the complete fall detection model comprising a second quantity of nodes greater than the first quantity of nodes and characterized by a second memory footprint greater than the first memory footprint; and
in response to the second confidence score exceeding a global threshold score, dispatching a care provider to assist the resident.

### Claim 18 (depends on 17)

The method of claim 17, wherein transmitting the first series of sensor data to the computer system remote from the wearable device further comprises:
wirelessly connecting to a local wireless hub;
transmitting the first series of sensor data to the computer system remote from the wearable device via the local wireless hub; and
disconnecting from the local wireless hub.

### Claim 19 (depends on 17)

The method of claim 17, further comprising:
in response to the wearable device detecting the first fall event, issuing a fall alarm for a care provider to assist the resident at approximately the first time; and
in response to dispatching the care provider to assist the resident, clearing the fall alarm at the wearable device.

### Claim 20 (depends on 17)

The method of claim 17, wherein:
calculating the first confidence score for the occurrence of the fall event during the first time period based on the first series of sensor data and the compressed fall detection model further comprises calculating the first confidence score for the occurrence of the fall event during the first time period based on the first series of sensor data and the compressed fall detection model, the compressed fall detection model comprising the first neural network defining the first quantity of nodes, characterized by the first memory footprint, defining the compressed form of the complete fall detection model, and stored locally on the wearable device; and
calculating the second confidence score for the occurrence of the fall event during the first time period based on the first series of sensor data and the complete fall detection model further comprises calculating the second confidence score for the occurrence of the fall event during the first time period based on the first series of sensor data and the complete fall detection model, the complete fall detection model comprising the second quantity of nodes greater than the first quantity of nodes, characterized by the second memory footprint greater than the first memory footprint, and stored locally on the computer system remote from the wearable device.