Data Processing System with Machine Learning Engine to Provide Profile Generation and Event Control Functions

Patent metadata

Field	Value
Publication number	US-2018357563-A1
Application number	US-201715620926-A
Country	US
Kind code	A1
Filing date	Jun 13, 2017
Priority date	Jun 13, 2017
Publication date	Dec 13, 2018
Grant date	—

Abstract

Systems for generating profiles based on machine learning data and controlling one or more devices or events are provided. In some examples, a computing platform may generate machine learning datasets based on data from various sources. The machine learning datasets may be used to generate a plurality of profiles, each profile providing a framework to meet particular goals. A user may request implementation of a profile and the computing platform may identify a first profile and associate the first profile with the user. The user may request authorization for an event and the computing platform may evaluate the event to determine whether one or more rules of the plurality of rules associated with the profile have been violated. If not, the computing platform may execute a first control to authorize the event. If so, the computing platform may execute a second control preventing processing of the event (e.g., disabling functionality of one or more devices).

First claim

What is claimed is:

1 . A profile generation and event control computing platform, comprising:
at least one processor; a communication interface communicatively coupled to the at least one processor; and memory storing computer-readable instructions that, when executed by the at least one processor, cause the profile generation and event control computing platform to:
generate a plurality of profiles based on one or more machine learning datasets;
identify a first profile of the plurality of profiles for a first user, the first profile including a first plurality of rules associated with the first profile;
associate the identified first profile with the first user, associating the identified first profile with the first user including identifying one or more controls, the one or more controls being based on the first plurality of rules associated with the first user profile;
receive a request to authorize an event by the first user;
determine, based on the first user profile of the first user, whether the event for which authorization is requested violates one or more rules of the first plurality of rules;
responsive to determining that the request for which authorization is requested violates one or more rules of the first plurality of rules, executing a first control of the one or more controls to deny authorization and prevent execution of the event; and
responsive to determining that the event for which authorization is requested does not violate one or more rules of the plurality of rules, executing a second control of the one or more controls to authorize and execute the event.

2 . The profile generation and event control computing platform of claim 1 , further including instructions that, when executed, cause the profile generation and event control computing platform to:
generate the plurality of machine learning datasets.

3 . The profile generation and event control computing platform of claim 2 , wherein generating the plurality of machine learning datasets includes:
receiving data from a plurality of sources, the data including data related to a plurality of users and a plurality of events; analyzing the data over a period of time; and linking event data to a level of success.

4 . The profile generation and event control computing platform of claim 1 , wherein determining, whether the event for which authorization is requested violates one or more rules of the first plurality of rules further includes:
transmitting a request to capture an image associated with an item associated with the event; receiving the requested image; and analyzing the image to determine whether the event for which authorization is requested violates the one or more rules of the first plurality of rules.

5 . The profile generation and event control computing platform of claim 4 , wherein the captured image includes a price of the item associated with the event.

6 . The profile generation and event control computing platform of claim 4 , wherein the captured image is received from a mobile device of the first user.

7 . The profile generation and event control computing platform of claim 1 , wherein executing the first control of the one or more controls includes disabling functionality of a mobile payment system on a mobile device of the first user.

8 . The profile generation and event control computing platform of claim 1 , wherein executing the second control of the one or more controls includes processing the event.

9 . The profile generation and event control computing platform of claim 1 , wherein the plurality of profiles each include a framework outlining a percentage associated with a plurality of categories.

10 . A method, comprising:
at a computing platform comprising at least one processor, memory, and a communication interface:
generating, by the at least one processor, a plurality of profiles based on one or more machine learning datasets;
identifying, by the at least one processor a first profile of the plurality of profiles for a first user, the first profile including a first plurality of rules associated with the first profile;
associating, by the at least one processor, the identified first profile with the first user, associating the identified first profile with the first user including identifying one or more controls, the one or more controls being based on the first plurality of rules associated with the first user profile;
receiving, by the at least one processor and via the communication interface, a request to authorize an event by the first user;
determining, by the at least one processor and based on the first user profile of the first user, whether the event for which authorization is requested violates one or more rules of the first plurality of rules; and
responsive to determining whether the event for which authorization is requested violates one or more rules of the first plurality of rules, executing one of a first control and a second control.

11 . The method of claim 10 , further including:
responsive to determining that the request for which authorization is requested violates one or more rules of the first plurality of rules, executing the first control of the one or more controls to deny authorization and prevent execution of the event.

12 . The method of claim 10 , further including:
responsive to determining that the event for which authorization is requested does not violate one or more rules of the plurality of rules, executing the second control of the one or more controls to authorize and execute the event.

13 . The method of claim 10 , further including:
generating, by the at least one processor, the plurality of machine learning datasets.

14 . The method of claim 13 , wherein generating the plurality of machine learning datasets includes:
receiving data from a plurality of sources, the data including data related to a plurality of users and a plurality of events; analyzing the data over a period of time; and linking event data to a level of success.

15 . The method of claim 10 , wherein determining, whether the event for which authorization is requested violates one or more rules of the first plurality of rules further includes:
transmitting, by the at least one processor and via the communication interface, a request to capture an image associated with an item associated with the event; receiving, by the at least one processor and via the communication interface, the requested image; and analyzing, by the at least one processor, the image to determine whether the event for which authorization is requested violates the one or more rules of the first plurality of rules.

16 . The method of claim 15 , wherein the captured image includes a price of the item associated with the event.

17 . The method of claim 10 , wherein executing the first control of the one or more controls includes disabling functionality of a mobile payment system on a mobile device of the first user.

18 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:
generate a plurality of profiles based on one or more machine learning datasets; identify a first profile of the plurality of profiles for a first user, the first profile including a first plurality of rules associated with the first profile; associate the identified first profile with the first user, associating the identified first profile with the fi

Assignees

• Bank Of America

Inventors

• Kurian Manu
• Roscoe Paul

Classifications

• H04L63/1416

  Event detection, e.g. attack signature detection · CPC title

• H04L63/102

  Entity profiles · CPC title

• H04L63/1425

  Traffic logging, e.g. anomaly detection · CPC title

• G06N99/005 Primary

  Physics · mapped topic

• G06N20/00 Primary

  Machine learning · CPC title