# US 2021/0243189 A1 · System, method, and computer program product for controlling access to online actions

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

- Number: US 2021/0243189 A1
- Document ID: US20210243189A1
- Status: Published application
- Kind: A1
- Application number: 16/781,028
- Filed: 2020-02-04
- Published: 2021-08-05
- Earliest claimed: 2020-02-04
- Assignees: Visa International Service Association
- Applicants: Visa International Service Association
- Inventors: Robert Chifamba; Krishnaram Muthusamy
- Web page: https://patentgrep.com/patent/US20210243189A1

## CPC

- H04L 63/0892: {by using authentication-authorization-accounting [AAA] servers or protocols}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- H04L 63/083: {using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226)}
- H04L 63/0884: {by delegation of authentication, e.g. a proxy authenticates an entity to be authenticated on behalf of this entity vis-à-vis an authentication entity}
- H04L 63/102: {Entity profiles}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Provided are computer-implemented methods that may include receiving, via a communication network, a request to perform an online action from a user device; retrieving data associated with a number of times the user device performed the online action within at least one time interval; determining whether a dataset associated with a number of times a plurality of user devices have performed the online action within the at least one time interval is normally distributed; and determining a standard deviation associated with the number of times the user device performed the online action within the at least one time interval in response to determining that the dataset is normally distributed, and performing a control operation associated with the request to conduct the online action based on a threshold of standard deviation. Systems and computer program products are also provided.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving, with at least one processor and via a communication network, a request to perform an online action from a user device;
retrieving, with at least one processor, data associated with a number of times the user device performed the online action within at least one time interval;
determining, with at least one processor, whether a dataset associated with a number of times a plurality of user devices have performed the online action within the at least one time interval is normally distributed;
determining, with at least one processor, a standard deviation associated with the number of times the user device performed the online action within the at least one time interval in response to determining that the dataset is normally distributed; and
performing, with at least one processor, a control operation associated with the request to conduct the online action based on a threshold of standard deviation.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
calculating, with at least one processor, at least one value of a percentile associated with the number of times the user device performed the online action within the at least one time interval based on at least one value of the number of times the online action has been performed by the user device within the at least one time interval,
wherein performing the control operation associated with the request to conduct the online action based on the threshold of standard deviation comprises:
performing, with at least one processor, the control operation associated with the request to conduct the online action based on the threshold of standard deviation and the percentile associated with the number of times the user device performed the online action.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the online action comprises at least one of:
an online action associated with a user login process;
an online action associated with a forgotten password process;
an online action associated with a purchase transaction; or
an online action associated with an addition of user information to a user account.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the request comprises at least one identity attribute associated with the user device and an identification attribute associated with the online action, and
wherein retrieving the data associated with the number of times the online action has been performed by the user device within the at least one time interval comprises:
retrieving the data associated with the number of times the online action has been performed by the user device within the at least one time interval based on the at least one identity attribute associated with the user device and the identification attribute associated with the online action.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
calculating the at least one value of the number of times the user device performed the online action within the at least one time interval; and
storing the at least one value of the number of times the user device performed the online action within the at least one time interval within a data structure.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein determining whether the dataset associated with the number of times the plurality of user devices have performed the online action within the at least one time interval is normally distributed comprises:
determining whether the dataset associated with the number of times the plurality of user devices have performed the online action within the at least one time interval is normally distributed based on a selected normality check method.

### Claim 7 (depends on 2)

The computer-implemented method of claim 2, further comprising:
calculating at least one value of a median of the number of times the user device performed the online action within the at least one time interval,
wherein calculating the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval comprises:
calculating the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval based on the at least one value of the median of the number of times the user device performed the online action within the at least one time interval.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein performing the control operation associated with the request to conduct the online action comprises:
performing the control operation associated with the request to conduct the online action based on determining the standard deviation is within a predetermined Gaussian range.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein performing the control operation associated with the request to conduct the online action comprises:
performing the control operation associated with the request to conduct the online action based on determining the standard deviation is within a predetermined Gaussian range for a type of online action associated with the online action.

### Claim 10

A system comprising:
at least one processor programmed or configured to:
receive via a communication network, a request to perform an online action from a user device, wherein the request comprises at least one identity attribute associated with the user device and an identification attribute associated with the online action;
retrieve data associated with a number of times the online action has been performed by the user device within at least one time interval based on the at least one identity attribute associated with the user device and the identification attribute associated with the online action;
determine whether a dataset associated with a number of times a plurality of user devices have performed the online action within the at least one time interval is normally distributed;
determine a standard deviation associated with the number of times the user device performed the online action within the at least one time interval in response to determining that the dataset is normally distributed; and
perform a control operation associated with the request to conduct the online action based on a threshold of standard deviation.

### Claim 11 (depends on 10)

The system of claim 10, wherein the at least one processor is further programmed or configured to:
calculate at least one value of a percentile associated with the number of times the user device performed the online action within the at least one time interval based on at least one value of the number of times the online action has been performed by the user device within the at least one time interval, and
wherein, when performing the control operation associated with the request to conduct the online action based on the threshold of standard deviation, the at least one processor is programmed or configured to:
perform the control operation associated with the request to conduct the online action based on the threshold of standard deviation and the percentile associated with the number of times the user device performed the online action.

### Claim 12 (depends on 10)

The system of claim 10, wherein the at least one processor is further programmed or configured to:
calculate the at least one value of the number of times the user device performed the online action within the at least one time interval; and
store the at least one value of the number of times the user device performed the online action within the at least one time interval within a data structure.

### Claim 13 (depends on 10)

The system of claim 10, wherein, when determining whether the dataset associated with the number of times the plurality of user devices have performed the online action within the at least one time interval is normally distributed, the at least one processor is programmed or configured to:
determine whether the dataset associated with the number of times the plurality of user devices have performed the online action within the at least one time interval is normally distributed based on a selected normality check method.

### Claim 14 (depends on 11)

The system of claim 11, wherein the at least one processor is further programmed or configured to:
calculate at least one value of a median of the number of times the user device performed the online action within the at least one time interval; and
wherein, when calculating the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval, the at least one processor is programmed or configured to:
calculate the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval based on the at least one value of the median of the number of times the user device performed the online action within the at least one time interval.

### Claim 15 (depends on 10)

The system of claim 10, wherein, when performing the control operation associated with the request to conduct the online action, the at least one processor is programmed or configured to:
perform the control operation associated with the request to conduct the online action based on determining the standard deviation is within a predetermined Gaussian range.

### Claim 16 (depends on 10)

The system of claim 10, wherein, when performing the control operation associated with the request to conduct the online action, the at least one processor is programmed or configured to:
perform the control operation associated with the request to conduct the online action based on determining the standard deviation is within a predetermined Gaussian range for a type of online action associated with the online action.

### Claim 17

A computer program product comprising at least one non-transitory computer-readable medium including one or more instructions that, when executed by at least one processor, cause the at least one processor to:
receive via a communication network, a request to perform an online action from a user device, wherein the request comprises at least one identity attribute associated with the user device and an identification attribute associated with the online action;
retrieve data associated with a number of times the online action has been performed by the user device within at least one time interval based on the at least one identity attribute associated with the user device and the identification attribute associated with the online action;
determine whether a dataset associated with a number of times a plurality of user devices have performed the online action within the at least one time interval is normally distributed based on a selected normality check method;
determine a standard deviation associated with the number of times the user device performed the online action within the at least one time interval in response to determining that the dataset is normally distributed; and
perform a control operation associated with the request to conduct the online action based on a threshold of standard deviation.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the one or more instructions further cause the at least one processor to:
calculate at least one value of a percentile associated with the number of times the user device performed the online action within the at least one time interval based on at least one value of the number of times the online action has been performed by the user device within the at least one time interval, and
wherein the one or more instructions that cause the at least one processor to perform the control operation associated with the request to conduct the online action based on the threshold of standard deviation cause the at least one processor to:
perform the control operation associated with the request to conduct the online action based on the threshold of standard deviation and the percentile associated with the number of times the user device performed the online action.

### Claim 19 (depends on 18)

The computer program product of claim 18, wherein the one or more instructions further cause the at least one processor to:
calculate at least one value of a median of the number of times the user device performed the online action within the at least one time interval; and
wherein the one or more instructions that cause the at least one processor to calculate the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval, cause the at least one processor to:
calculate the at least one value of the percentile associated with the number of times the user device performed the online action within the at least one time interval based on the at least one value of the median of the number of times the user device performed the online action within the at least one time interval.

### Claim 20 (depends on 17)

The computer program product of claim 17, wherein the one or more instructions that cause the at least one processor to perform the control operation associated with the request to conduct the online action cause the at least one processor to:
perform the control operation associated with the request to conduct the online action based on determining the standard deviation is within a predetermined Gaussian range.
