Granted Patent B2

US 12,555,408 · App. 18/519,890 · Granted Feb 17, 2026

Inventors: Michael Mossoba (Arlington, VA); Gaurang J. Bhatt (Hendron, VA)

Assignee: Capital One Services, LLC

G06V40/169G06Q20/28G06Q20/389G06Q30/0202G06V20/52

Abstract

Claims (70)

1 . A method of customizing a person experience, comprising:

receiving, from a computing device positioned in a facility, one or more first video streams, captured by a first camera positioned at a location in the facility, the one or more first video streams capturing a person in the facility;

accessing a database storing customer profiles, wherein each of the customer profiles comprises identity information, facial identification information, and account information;

identifying, from the database, an identity of the person by parsing the one or more first video streams to identify one or more audio or visual cues of the person;

determining, based on the identity of the person, that the person has taken one or more previous actions at the facility;

analyzing the one or more previous actions at the facility to identify a pattern of personal activity at the facility;

predicting, based on the identified pattern of personal activity in the one or more previous actions, an anticipated action for the person at the facility, wherein the anticipated action is associated with an account; and

prompting, based on predicting the anticipated action and before the facility is instructed to begin preparing for a transaction, an application, of a client device of the person, to push a notification that suggests the transaction to the person.

2 . The method of claim 1 , further comprising notifying the computing device positioned in the facility to initiate one or more actions to address the anticipated action.

3 . The method of claim 2 , further comprising:

confirming that the person remains in the facility by:

receiving one or more second video streams captured by a second camera positioned at a second location in the facility; and

parsing the one or more second video streams to confirm that the person remains in the facility.

4 . The method of claim 3 , wherein the second location is proximate a point-of-sale terminal.

5 . The method of claim 1 , wherein predicting the anticipated action for the person at the facility comprises:

identifying a current day of the week;

identifying a current time of the current day; and

generating a prediction based on the identified pattern of personal activity in the one or more previous actions, the current day of the week, and the current time of the current day.

6 . The method of claim 1 , further comprising:

receiving a confirmation in response to the person viewing a confirmation message at a point-of-sale terminal; and

transmitting the confirmation to the computing device positioned in the facility.

7 . The method of claim 1 , wherein identifying the identity of the person comprises:

analyzing one or more facial features of the person; and

determining the identity of the person based on the one or more facial features.

8 . The method of claim 1 , further comprising:

receiving, from the client device and before the facility is instructed to begin preparing for the transaction, information regarding an approval of the transaction via the application.

9 . A system comprising:

one or more processors; and

memory having programming instructions stored thereon, which, when executed by the one or more processors, performs operations comprising:

receiving one or more first video streams, captured by a first camera positioned at a location in a facility, of a person in the facility;

identifying an identity of the person by parsing the one or more first video streams to identify one or more audio or visual cues of the person;

determining, based on the identity of the person, that the person has taken one or more previous actions at the facility;

analyzing the one or more previous actions at the facility to identify a pattern of personal activity at the facility;

predicting, based on the identified pattern of personal activity, an anticipated action for the person at the facility; and

prompting, based on predicting the anticipated action and before the facility is instructed to begin preparing for a transaction, an application, of a client device of the person, to push a notification that suggests the transaction to the person.

10 . The system of claim 9 , wherein the operations further comprise:

generating a prediction model for predicting anticipated actions by learning, via one or more machine learning models, personalized habits at the facility.

11 . The system of claim 9 , wherein the operations further comprise:

notifying a computing device positioned in the facility to initiate one or more actions to address the anticipated action.

12 . The system of claim 9 , wherein the operations further comprise:

confirming that the person remains in the facility by:

receiving, from a computing device positioned in the facility, one or more second video streams captured by a second camera positioned at a second location in the facility; and

parsing the one or more second video streams to confirm that the person remains in the facility.

13 . The system of claim 12 , wherein the second location is proximate a point-of-sale terminal.

14 . The system of claim 9 , wherein predicting the anticipated action of the person at the facility comprises:

identifying a current day of a week;

identifying a current time of the current day; and

generating a prediction based on the current day of the week and the current time of the current day.

15 . One or more non-transitory computer readable media including one or more instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving, from a computing device positioned in a facility, one or more first video streams, captured by a first camera positioned at a location in the facility, of a person in the facility;

identifying an identity of the person by parsing the one or more first video streams to identify one or more audio or visual cues of the person;

determining, based on the identity of the person, that the person has taken one or more previous actions at the facility;

analyzing the one or more previous actions at the facility to identify a pattern of personal activity at the facility;

predicting, based on the identified pattern of personal activity, an anticipated action for the person at the facility; and

prompting, based on predicting the anticipated action and before the facility is instructed to begin preparing for a transaction, an application, of a client device of the person, to push a notification that suggests the transaction to the person.

16 . The one or more non-transitory computer readable media of claim 15 , wherein the operations further comprise:

generating a prediction model for predicting anticipated actions by learning, via one or more machine learning models, personalized spending habits at a facility.

17 . The one or more non-transitory computer readable media of claim 15 , wherein the anticipated action of the person at the facility comprises:

identifying a current day of the week;

identifying a current time of the current day; and

generating a prediction based on the one or more previous actions, the current day of the week, and the current time of the current day.

18 . The one or more non-transitory computer readable media of claim 15 , wherein the operations further comprise:

notifying the computing device positioned in the facility to initiate one or more actions to address the anticipated action.

19 . The one or more non-transitory computer readable media of claim 18 , wherein the operations further comprise:

confirming that the person remains in the facility by:

receiving, from the computing device positioned in the facility, one or more second video streams captured by a second camera positioned at a second location in the facility; and

parsing the one or more second video streams to confirm that the person remains in the facility.

20 . The one or more non-transitory computer readable media of claim 15 , wherein identifying the identity of the person comprises:

analyzing one or more facial features of the person; and

determining the identity of the person based on the one or more facial features.

Assignments (1)

Continuity (4)

References Cited (28)