# US 12,182,239 B2 · Apparatus and method of performing user authentication

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

- Number: US 12,182,239 B2
- Document ID: US12182239B2
- Status: Granted
- Kind: B2
- Application number: 17/268,987
- Filed: 2020-10-06
- Published: 2022-09-08
- Granted: 2024-12-31
- Earliest claimed: 2019-10-28
- Assignees: Kt&G Corporation
- Applicants: Kt&G Corporation
- Inventors: Paul Joon Sunwoo; Jin Soo Seong
- Web page: https://patentgrep.com/patent/US12182239B2

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 21/45: Structures or tools for the administration of authentication
- G06N 20/00: Machine learning
- G06V 10/96: Management of image or video recognition tasks
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- A24F 40/53: Monitoring, e.g. fault detection
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A24F: SMOKERS' REQUISITES; MATCH BOXES; SIMULATED SMOKING DEVICES (inhaling appliances for medical purposes, shaped like cigars, cigarettes or pipes A61M15/06)

## Abstract

A user authentication apparatus trains a user authentication model by using biometric data of a user which was used in previous user authentication as training data, and performs user authentication by using the trained user authentication model.

## Claims

### Claim 1

A method of performing user authentication, the method comprising:
obtaining biometric data;
performing user authentication based on the biometric data;
adding the biometric data to training data after the performing the user authentication;
training, by using the training data, a user authentication model that is a machine learning model configured to perform the user authentication; and
performing the user authentication based on new biometric data by using the user authentication model,
wherein the adding comprises:
adding success biometric data to the training data, the success biometric data being the biometric data that succeeded in the user authentication; and
adding previous biometric data to the training data, and
wherein the adding of the previous biometric data to the training data comprises adding a predetermined number of pieces of the previous biometric data obtained within a predetermined period before the success biometric data is obtained to the training data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the adding of the previous biometric data to the training data comprises adding a predetermined number of pieces of the previous biometric data obtained immediately before the success biometric data is obtained to the training data.

### Claim 3 (depends on 1)

The method of claim 1, wherein the adding of the previous biometric data to the training data comprises adding a plurality of pieces of the previous biometric data which are sequentially obtained to the training data, and
wherein each of a time interval between adding a piece of the previous biometric data to the training data and adding another piece of the previous biometric data to the training data and a time interval between adding the success biometric data to the training data and adding a piece of the previous biometric data, obtained immediately before the success biometric data, to the training data is less than or equal to a predetermined time interval.

### Claim 4 (depends on 1)

The method of claim 1, wherein the adding comprises adding similar biometric data to the training data, the similar biometric data being biometric data having a similarity equal to or greater than a first reference value with reference data.

### Claim 5 (depends on 4)

The method of claim 4, wherein the performing of the user authentication comprises determining that the user authentication succeeded based on a similarity between the reference data and the obtained biometric data being equal to or greater than second reference value,
wherein the second reference value is greater than the first reference value.

### Claim 6 (depends on 4)

The method of claim 4, wherein the reference data is biometric data of a user obtained in advance for the user authentication, and
wherein the adding further comprises adding the reference data to the training data.

### Claim 7 (depends on 1)

The method of claim 1, further comprising determining whether the user authentication model needs to be trained, based on a user recognition rate of the user authentication model or the number of the training data.

### Claim 8

An apparatus for performing user authentication, the apparatus comprising:
a sensor configured to obtain biometric data;
a memory configured to store at least one program; and
a controller configured to perform user authentication by executing the at least one program,
wherein the at least one program comprises instructions to implement operations of:
performing the user authentication based on the obtained biometric data;
adding the biometric data to training data after performing the user authentication;
training, by using the training data, a user authentication model that is a machine learning model configured to perform the user authentication; and
performing the user authentication based on new biometric data by using the user authentication model,
wherein the adding comprises:
adding success biometric data to the training data, the success biometric data being the biometric data that succeeded in the user authentication; and
adding previous biometric data to the training data, and
wherein the adding of the previous biometric data to the training data comprises adding a predetermined number of pieces of the previous biometric data obtained within a predetermined period before the success biometric data is obtained to the training data.

### Claim 9 (depends on 8)

The apparatus of claim 8, further comprising:
a battery; and
a heater configured to receive power from the battery and heat an aerosol generating material,
wherein the controller controls power supplied from the battery to the heater.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the controller controls the power delivered to the heater, based on a result of the user authentication.

### Claim 11 (depends on 9)

The apparatus of claim 9, further comprising an input interfacing element configured to obtain a user input for controlling the apparatus,
wherein the controller is configured to add biometric data, obtained by the input interfacing element after succeeding in the user authentication, to the training data.