# US 12,217,871 B2 · Method and system for privacy-preserving health monitoring

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

- Number: US 12,217,871 B2
- Document ID: US12217871B2
- Status: Granted
- Kind: B2
- Application number: 17/408,490
- Filed: 2021-08-23
- Published: 2021-12-09
- Granted: 2025-02-04
- Earliest claimed: 2019-11-02
- Assignees: Altum View Systems Inc.
- Applicants: AltumView Systems Inc.
- Inventors: Andrew Tsun-Hong Au; Dong Zhang; Chi Chung Chan; Jiannan Zheng
- Web page: https://patentgrep.com/patent/US12217871B2

## CPC

- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/1117: {Fall detection}
- A61B 5/112: {Gait analysis}
- A61B 5/1128: {using image analysis (A61B5/1127 takes precedence)}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- G06T 1/00: General purpose image data processing
- G06T 3/18: Image warping, e.g. rearranging pixels individually
- G06T 11/00: Two-dimensional [2D] image generation
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/23: {Recognition of whole body movements, e.g. for sport training}
- G08B 5/222: {Personal calling arrangements or devices, i.e. paging systems (selective calling systems and call receivers H04W84/00, H04W68/00)}
- G08B 21/043: {detecting an emergency event, e.g. a fall}
- G08B 21/0476: {Cameras to detect unsafe condition, e.g. video cameras}
- G08B 29/186: {Fuzzy logic; neural networks}
- G16H 30/40: for processing medical images, e.g. editing
- A61B 5/1116: {Determining posture transitions}
- A61B 5/1123: {Discriminating type of movement, e.g. walking or running (A61B5/1116, A61B5/112 take precedence)}
- A61B 5/1127: {using markers}
- A61B 5/1176: {Recognition of faces}
- A61B 5/7267: {involving training the classification device}
- A61B 2503/08: Elderly
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06T 2210/22: Cropping
- G06V 20/44: {Event detection}
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS

## Abstract

Various embodiments of a health-monitoring system are disclosed. In one aspect, this health-monitoring system includes a server and a set of health-monitoring sensors communicatively coupled to the server. In some embodiments, the server is configured to establish a new profile for a person to be monitored by: receiving a new profile request for establishing the new profile; generating a unique person-ID for the received new profile request; creating a new entry including the unique person-ID for the person in a profile database; and transmitting the unique person-ID along with the profile photos of the person to the set of health-monitoring sensors. Moreover, each health-monitoring sensor in the set of sensors is configured to establish the new profile by adding a new entry for the person in a person-ID dictionary of the health-monitoring sensor based on the received person-ID and the profile photos of the person.

## Claims

### Claim 1

A method for monitoring individuals in a distributed health-monitoring system including a server and a set of distributed health-monitoring sensors, the method comprising:
receiving, at the server, a new profile request for establishing a new profile of a person to be monitored by the distributed health-monitoring system;
generating a unique person-ID for the received new profile request;
creating a new entry for the person in a profile database on the server, wherein the new entry includes at least the unique person-ID;
transmitting the unique person-ID along with one or more profile photos of the person to the set of distributed health-monitoring sensors; and
on each health-monitoring sensor in the set of distributed health-monitoring sensors, adding a new entry for the person in an associated person-ID dictionary based on the received person-ID and the one or more profile photos of the person.

### Claim 2 (depends on 1)

The method of claim 1, wherein the new profile request includes at least an identity of the person and one or more profile photos of the person.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the unique person-ID for the received new profile request includes:
generating a unique integer value for the person; and
associating the unique integer value with the identity of the person and the one or more profile photos of the person.

### Claim 4 (depends on 2)

The method of claim 2, wherein the new entry for the person in the profile database on the server includes two or more of the following:
the identity of the person;
the unique person-ID of the person; and
the one or multiple profile photos of the person.

### Claim 5 (depends on 1)

The method of claim 1, wherein adding a new entry for the person in the associated person-ID dictionary based on the received person-ID and the one or more profile photos includes:
extracting one or more facial feature vectors of the person based on the received one or more profile photos; and
creating a new entry for the person in the associated person-ID dictionary by including both the extracted facial feature vectors and the unique person-ID of the person, wherein the new entry for the person does not include an actual identity of the person.

### Claim 6 (depends on 5)

The method of claim 5, wherein the method further comprises identifying a new person during a health-monitoring process by:
detecting a new person using a health-monitoring sensor in the set of distributed health-monitoring sensors;
extracting a facial-feature vector of the detected new person based on a face image of the detected person;
comparing the extracted facial-feature vector against the set of stored facial feature vectors in the person-ID dictionary; and
when a match between the extracted facial-feature vector and a stored facial feature vector is found, outputting the matched unique person-ID associated with the stored facial feature vector indicating that the detected new person has been identified.

### Claim 7 (depends on 6)

The method of claim 6, wherein the method further comprises tracking the detected new person during the health-monitoring process using the matched unique person-ID and a sequence of face images of the detected person.

### Claim 8 (depends on 6)

The method of claim 6, wherein if the extracted facial-feature vector does not match any stored facial feature vector in the person-ID dictionary, generating an “unknown person” tag for the detected new person indicating that the detected new person cannot be identified.

### Claim 9 (depends on 6)

The method of claim 6, wherein the health-monitoring process is a fall-detection process, and wherein the method further comprises:
determining that the detected new person is involved in a fall;
generating a fall alarm for the detected new person;
transmitting the fall alarm along with the unique person-ID of the detected new person to the server; and
determining the identity of the detected new person based on the unique person-ID of the detected new person at the server.

### Claim 10 (depends on 1)

The method claim 1, wherein the method further comprises removing an established profile from the distributed health-monitoring system by:
receiving, at the server, a profile removal request to remove an established profile of a requested person from the distributed health-monitoring system;
searching the profile database on the server to locate the unique person-ID associated with the requested person;
transmitting the located unique person-ID along with the profile removal request to the set of distributed health-monitoring sensors: and
on each health-monitoring sensor in the set of distributed health-monitoring sensors, removing an associated entry of the requested person from the associated person-ID dictionary based on the located unique person-ID of the requested person.

### Claim 11 (depends on 10)

The method claim 10, wherein the method further comprises:
receiving at the server, an acknowledgement from each health-monitoring sensor indicating that the profile of the requested person has been successfully removed from the health-monitoring sensor; and
removing the entry of the requested person from the profile database.

### Claim 12 (depends on 10)

The method claim 10, wherein the profile removal request includes at least an identity of the requested person, and wherein searching the profile database to locate the unique person-ID associated with the requested person includes:
translating the identity of the requested person into an unique integer value; and
comparing the unique integer value to the set of stored unique person-IDs in the profile database on the server.

### Claim 13

A health-monitoring system, comprising:
a server; and
a set of health-monitoring sensors communicatively coupled to the server,
wherein the server is configured to:
receive a new profile request for establishing a new profile of a person to be monitored by the health-monitoring system;
generate a unique person-ID for the received new profile request;
create a new entry for the person in a profile database, wherein the new entry includes at least the unique person-ID; and
transmit the unique person-ID along with one or more profile photos of the person to the set of health-monitoring sensors; and
wherein each health-monitoring sensor in the set of health-monitoring sensors is configured to add a new entry for the person in an associated person-ID dictionary of the health-monitoring sensor based on the received person-ID and the one or more profile photos of the person.

### Claim 14 (depends on 13)

The health-monitoring system of claim 13, wherein the new profile request includes at least an identity, such as the name of the person and one or more profile photos of the person, and wherein the server is configured to generate the unique person-ID by:
generating a unique integer value for the person; and
associating the unique integer value with the identity of the person and the one or more profile photos of the person.

### Claim 15 (depends on 13)

The health-monitoring system of claim 13, wherein the new entry for the person in the profile database includes two or more of the following:
the identity of the person;
the unique person-ID of the person; and
the one or multiple profile photos of the person.

### Claim 16 (depends on 13)

The health-monitoring system of claim 13, wherein each health-monitoring sensor is configured to add a new entry for the person in the associated person-ID dictionary by:
extracting one or more facial feature vectors of the person based on the received one or more profile photos; and
creating a new entry for the person in the associated person-ID dictionary by including both the extracted facial feature vectors and the unique person-ID of the person, wherein the new entry for the person does not include an actual identity of the person.

### Claim 17 (depends on 16)

The health-monitoring system of claim 16, wherein a given health-monitoring sensor in the set of health-monitoring sensors is further configured to identify a new person during a health-monitoring process by:
detecting a new person through a face-detection operation;
extracting a facial-feature vector of the detected new person based on a face image of the detected person;
comparing the extracted facial-feature vector against the set of stored facial feature vectors in the person-ID dictionary; and
when a match between the extracted facial-feature vector and a stored facial feature vector is found, outputting the matched unique person-ID associated with the stored facial feature vector indicating that the detected new person has been identified.

### Claim 18 (depends on 17)

The health-monitoring system of claim 17, wherein the health-monitoring system is a fall-detection system,
wherein the given health-monitoring sensor is further configured to:
determine that the detected new person is involved in a fall;
generate a fall alarm for the detected new person; and
transmit the fall alarm along with the unique person-ID of the detected new person to the server; and
wherein the server is further configured to determine the identity of the detected new person based on the received unique person-ID of the detected new person.

### Claim 19

A fall-detection system, comprising:
a server; and
a set of distributed fall-detection sensors communicatively coupled to the server, wherein each of the set of distributed fall-detection sensors includes a camera;
wherein the server is configured to:
receive a new profile request for establishing a new profile of a person to be monitored by the fall-detection system;
generate a unique person-ID for the received new profile request;
create a new entry for the person in a profile database, wherein the new entry includes at least the unique person-ID; and
transmit the unique person-ID along with one or more profile photos of the person to the set of distributed fall-detection sensors; and
wherein each fall-detection sensor in the set of distributed fall-detection sensors is configured to add a new entry for the person in an associated person-ID dictionary of the fall-detection sensor based on the received person-ID and the one or more profile photos of the person.

### Claim 20 (depends on 19)

The fall-detection system of claim 19, wherein the new profile request includes at least an identity of the person and one or more profile photos of the person, and wherein the server is configured to generate the unique person-ID by:
generating a unique integer value for the person; and
associating the unique integer value with the identity of the person and the one or more profile photos of the person.

### Claim 21 (depends on 19)

The fall-detection system of claim 19,
wherein the server is further configured to:
receive a profile removal request to remove an established profile of a requested person from the fall-detection system;
search the profile database on the server to locate the unique person-ID associated with the requested person;
transmit the located unique person-ID along with the profile removal request to the set of distributed fall-detection sensors: and
wherein each fall-detection sensor in the set of distributed fall-detection sensors is configured to remove an associated entry of the requested person from the associated person-ID dictionary based on the located unique person-ID of the requested person.

### Claim 22 (depends on 21)

The fall-detection system of claim 21, wherein the server is further configured to:
receive an acknowledgement from each fall-detection sensor in the set of distributed fall-detection sensors indicating that the profile of the requested person has been successfully removed from the fall-detection sensor; and
remove the entry of the requested person from the profile database on the server.