# US 2023/0275885 A1 · Methods and processes for utilizing information collected for enhanced verification

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

- Number: US 2023/0275885 A1
- Document ID: US20230275885A1
- Status: Published application
- Kind: A1
- Application number: 18/311,092
- Filed: 2023-05-02
- Published: 2023-08-31
- Earliest claimed: 2018-05-07
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Timur SHERIF; Benjamin LINDQUIST
- Web page: https://patentgrep.com/patent/US20230275885A1

## CPC

- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)}
- G06F 21/45: Structures or tools for the administration of authentication
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/025: Extracting rules from data
- G06N 20/00: Machine learning
- H04W 12/06: Authentication
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- H04L 63/083: {using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226)}
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- H04L 63/0876: {based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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 for verifying a user identity. The system comprises one or more memory devices storing instructions and one or more processors configured to execute the instructions. The processors are configured to receive information associated with an account of a user. The processors are further configured to generate a first profile, where the first profile being related to the user. The processors also receive an indication that the account is accessed by an accessor through an accessor device; and receive, from the accessor device, identity data comprising a plurality of data subsets associated with the accessor. The processors are configured to store the data subsets in respective clusters. The processors are further configured generate cluster analyses by analyzing the data subsets in respective clusters; and output the cluster analyses to node instances that weighs the cluster analyses outputs. The processors also generate a second profile, the second profile related to the accessor and being based on the received identity data and weighted cluster analysis. And the processors are configured to determine a likelihood factor that the accessor is the user based on a comparison of the first profile and the second profile.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system for verifying a user identify, the system comprising:
one or more processors programmed with instructions that, when executed by the one or more processors, causes operations comprising:
in connection with a request to access an account of a user, obtaining, from an accessor device of an accessor, verification data comprising accessor data subsets associated with the accessor;
storing the accessor data subsets in respective clusters, wherein the clusters are nonlinear neural network computational elements;
generating cluster analyses by analyzing the accessor data subsets in the clusters;
providing the cluster analyses to node instances to obtain weighted results, wherein the node instances are nonlinear neural network computation elements based on the clusters; and
determining a likelihood factor that the accessor is the user based on the weighted results.

### Claim 22 (depends on 21)

The system of claim 21, the operations further comprising:
generating a first profile, related to the user, based on information associated with the account of the user; and
generating a second profile, related to the accessor, based on (i) the verification data obtained from the accessor device and (ii) the weighted results,
wherein determining the likelihood factor comprises determining the likelihood factor that the accessor is the user based on a comparison of the first and second profiles.

### Claim 23 (depends on 22)

The system of claim 22, the operations further comprising:
modifying a user profile associated with the user with data from the second profile based on a confirmation that the accessor is the user, the confirmation being based on the likelihood factor.

### Claim 24 (depends on 22)

The system of claim 22, wherein the cluster analyses are weighted based on a set of rules of the first profile to obtain the weighted results.

### Claim 25 (depends on 21)

The system of claim 21, wherein obtaining the verification data comprises obtaining identity data collected via one or more sensors of the accessor device.

### Claim 26 (depends on 21)

The system of claim 21, wherein obtaining the verification data comprises obtaining, from the accessor device, (i) accessor data comprising at least one of username, password, typing pattern, typing cadence, typing error rate, mouse movement, mouse scrolling rate, mouse clicking rate, mouse clicking error rate, frequency of mouse use, finger pressure, finger error rate, biometrics, or reading rate, and (ii) accessor device data comprising at least one of software version, browser type, or connection speed.

### Claim 27

A method comprising:
in connection with a request to access an account of a user, obtaining, from an accessor device of an accessor, verification data comprising data subsets associated with the accessor;
storing the data subsets in one or more clusters, wherein the one or more clusters are nonlinear neural network computational elements;
generating cluster analyses by analyzing the data subsets in the one or more clusters;
providing the cluster analyses to node instances to obtain weighted results, wherein the node instances are nonlinear neural network computation elements based on the one or more clusters; and
determining a likelihood factor that the accessor is the user based on the weighted results.

### Claim 28 (depends on 27)

The method of claim 27, further comprising:
generating a first profile, related to the user, based on information associated with the account of the user; and
generating a second profile, related to the accessor, based on (i) the verification data obtained from the accessor device and (ii) the weighted results,
wherein determining the likelihood factor comprises determining the likelihood factor that the accessor is the user based on a comparison of the first and second profiles.

### Claim 29 (depends on 28)

The method of claim 28, further comprising:
confirming that that the accessor is the user based on the likelihood factor exceeding a likelihood threshold.

### Claim 30 (depends on 29)

The method of claim 29, further comprising:
modifying a user profile associated with the user with data from the second profile based on the confirmation that the accessor is the user.

### Claim 31 (depends on 28)

The method of claim 28, wherein the cluster analyses are weighted based on a set of rules of the first profile to obtain the weighted results.

### Claim 32 (depends on 27)

The method of claim 27, wherein obtaining the verification data comprises obtaining identity data collected via one or more sensors of the accessor device.

### Claim 33 (depends on 27)

The method of claim 27, wherein obtaining the verification data comprises obtaining, from the accessor device, (i) accessor data comprising at least one of username, password, typing pattern, typing cadence, typing error rate, mouse movement, mouse scrolling rate, mouse clicking rate, mouse clicking error rate, frequency of mouse use, finger pressure, finger error rate, biometrics, or reading rate, and (ii) accessor device data comprising at least one of software version, browser type, or connection speed.

### Claim 34

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause operations comprising:
in connection with a request to access an account of a user, receiving, from an accessor device of an accessor, verification data comprising data subsets associated with the accessor;
generating cluster analyses by analyzing the data subsets based on one or more clusters, wherein the one or more clusters are nonlinear neural network computational elements;
providing the cluster analyses to node instances to obtain weighted results, wherein the node instances are nonlinear neural network computation elements based on the one or more clusters; and
determining a likelihood factor that the accessor is the user based on the weighted results.

### Claim 35 (depends on 34)

The media of claim 34, the operations further comprising:
generating a first profile, related to the user, based on information associated with the account of the user; and
generating a second profile, related to the accessor, based on (i) the verification data obtained from the accessor device and (ii) the weighted results,
wherein determining the likelihood factor comprises determining the likelihood factor that the accessor is the user based on a comparison of the first and second profiles.

### Claim 36 (depends on 35)

The media of claim 35, the operations further comprising:
confirming that that the accessor is the user based on the likelihood factor exceeding a likelihood threshold.

### Claim 37 (depends on 36)

The media of claim 36, the operations further comprising:
modifying a user profile associated with the user with data from the second profile based on the confirmation that the accessor is the user.

### Claim 38 (depends on 35)

The media of claim 35, wherein the cluster analyses are weighted based on a set of rules of the first profile to obtain the weighted results.

### Claim 39 (depends on 34)

The media of claim 34, wherein obtaining the verification data comprises obtaining identity data collected via one or more sensors of the accessor device.

### Claim 40 (depends on 34)

The media of claim 34, wherein obtaining the verification data comprises obtaining, from the accessor device, (i) accessor data comprising at least one of username, password, typing pattern, typing cadence, typing error rate, mouse movement, mouse scrolling rate, mouse clicking rate, mouse clicking error rate, frequency of mouse use, finger pressure, finger error rate, biometrics, or reading rate, and (ii) accessor device data comprising at least one of software version, browser type, or connection speed.
