# US 2021/0342430 A1 · Identity verification using task-based behavioral biometrics

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

- Number: US 2021/0342430 A1
- Document ID: US20210342430A1
- Status: Published application
- Kind: A1
- Application number: 16/864,834
- Filed: 2020-05-01
- Published: 2021-11-04
- Earliest claimed: 2020-05-01
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Abdelkader M'Hamed BENKREIRA; Andrea MONTEALEGRE; Daniel MARSCH; Nagaraju GADDIGOPULA; William PRIOR; Phoebe ATKINS
- Web page: https://patentgrep.com/patent/US20210342430A1

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/36: by graphic or iconic representation
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- H04W 12/06: Authentication
- H04W 12/68: Gesture-dependent or behaviour-dependent
- G06N 3/08: Learning methods
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A system may receive a request to verify an identity of a user. The system may transmit information that identifies a task to be performed via user interaction with a client device and information that identifies behavioral data to be collected by the client device in connection with performance of the task, wherein the task requires at least one of: movement of the client device, interaction with a user interface of the client device using a gesture, or interaction with a user interface of the client device using a cursor. The system may receive the behavioral data and may perform identity verification associated with the user based on the behavioral data and the task. The system may transmit an indication of a recommended action to be performed with respect to the user and the client device based on performing the identity verification.

## Claims

### Claim 1

A method, comprising:
receiving, by a system, a request to verify an identity of a user;
transmitting, by the system, information that identifies a task to be performed via user interaction with a client device and information that identifies behavioral data to be collected by the client device in connection with performance of the task,
wherein the task requires at least one of:
movement of the client device,
interaction with a user interface of the client device using a gesture, or
interaction with a user interface of the client device using a cursor;
receiving, by the system, the behavioral data, wherein the behavioral data is collected by the client device during performance of the task via user interaction with the client device,
wherein the behavioral data includes at least one of acceleration data, pressure data, or temperature data;
performing, by the system, identity verification associated with the user based on the behavioral data and the task,
wherein the identity verification is performed using a machine learning model that identifies patterns associated with the behavioral data and the task; and
transmitting, by the system, an indication of a recommended action to be performed with respect to the user and the client device based on performing the identity verification.

### Claim 2 (depends on 1)

The method of claim 1, wherein the task involves movement of the client device, and wherein the behavioral data includes two or more of the acceleration data, the pressure data, or the temperature data.

### Claim 3 (depends on 1)

The method of claim 1,
wherein the task comprises a formation of a signature through one of: movement of the client device, interaction with the user interface of the client device using the gesture, or interaction with the user interface of the client device using the cursor, and
wherein the behavioral data includes the acceleration data obtained from the formation of the signature.

### Claim 4 (depends on 1)

The method of claim 1,
wherein the task comprises responding to a graphic being displayed on the client device by shaking the client device through one of: movement of the client device, interaction with the user interface of the client device using the gesture, or interaction with the user interface of the client device using the cursor.

### Claim 5 (depends on 1)

The method of claim 1, wherein the task requires interaction with the user interface of the client device using the gesture or the cursor, and wherein the behavioral data is collected while the task is being performed.

### Claim 6 (depends on 1)

The method of claim 1,
wherein the task involves completing a maze through one of: movement of the client device, interaction with the user interface of the client device using the gesture, or interaction with the user interface of the client device using the cursor, and
wherein the behavioral data is associated with completing the maze.

### Claim 7 (depends on 1)

The method of claim 1,
wherein the task involves identifying a location through interaction with a map displayed on the client device, and
wherein the behavioral data is associated with the interaction with the map.

### Claim 8

A system, comprising:
memory; and
one or more processors, communicatively coupled to the memory, configured to:
transmit information that identifies behavioral data to be collected by a client device in connection with performance of an identity verification task to be performed via user interaction with the client device,
wherein the identity verification task requires at least one of:
movement of the client device, or
interaction with a user interface of the client device using a gesture or a cursor;
receive the behavioral data, wherein the behavioral data is collected by the client device during performance of the identity verification task via the user interaction with the client device;
provide the behavioral data and a task identifier, that identifies the identity verification task, as a feature set that is input to a machine learning model;
receive output from the machine learning model; and
cause a recommended action to be performed with respect to verifying an identity of a user of the client device based on the output from the machine learning model.

### Claim 9 (depends on 8)

The system of claim 8, wherein the behavioral data relates to at least one of:
position,
speed,
direction,
directional acceleration,
force acceleration,
pressure, or
temperature.

### Claim 10 (depends on 8)

The system of claim 8, wherein the behavioral data includes multiple parameters that are included in the feature set that is input to the machine learning model.

### Claim 11 (depends on 8)

The system of claim 8, wherein the identity verification task includes answering a knowledge-based authentication question by moving the client device or interacting with the user interface of the client device using the gesture or the cursor.

### Claim 12 (depends on 11)

The system of claim 11, wherein the one or more processors are further configured to receive an answer to the knowledge-based authentication question, wherein the recommended action is based on the answer to the knowledge-based authentication question.

### Claim 13 (depends on 8)

The system of claim 8, wherein the recommended action includes one of:
approving access, by the client device, to a resource,
denying access, by the client device, to the resource,
sending an additional task, or
requesting additional data from the client device.

### Claim 14 (depends on 8)

The system of claim 8, wherein the output from the machine learning model is determined based on a degree of similarity of the feature set and at least one of:
one or more other feature sets associated with the user, or
a threshold number of feature sets analyzed in connection with the identity verification task or one or more other tasks.

### Claim 15

A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
transmit information that identifies:
a task to be performed to verify an identity of a user of a client device, and
behavioral data to be collected by the client device during performance of the task,
wherein the task requires at least one of:
movement of the client device, or
interaction with a user interface of the client device using a gesture or a cursor;
receive the behavioral data, wherein the behavioral data includes at least one of an acceleration parameter, a speed parameter, a force parameter, a directional parameter, a position parameter, a pressure parameter, or a temperature parameter;
generate a feature set based on the behavioral data;
determine an identity verification score based on a degree of similarity of the feature set and one or more other feature sets associated with the user; and
cause a recommended action to be performed with respect to the client device based on the identity verification score.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the task is selected from a set of tasks,
wherein the set of tasks comprises related tasks.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
transmit information that causes the client device to display a visual associated with the task.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the task includes answering a knowledge-based authentication question by moving the client device or interacting with the user interface of the client device using the gesture or the cursor.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receive an answer to the knowledge-based authentication question, wherein the recommended action is based on the answer to the knowledge-based authentication question.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the recommended action includes one of:
approving, by the client device, submission of information,
denying, by the client device, submission of information,
approving, by the client device, a transaction,
denying, by the client device, a transaction,
sending an additional task, or
requesting additional data from the client device.
