Granted Patent B1

US 12,271,746 · App. 17/970,392 · Granted Apr 8, 2025

Inventors: Mohsen Sardari (Burlingame, CA); Anna Bloom (Park City, UT); Jonathan Lamberts (Denver, CO); Ran Lin (Foster City, CA); Khilesh Mistry (Oakland, CA); Sagnik Mazumder (Belmont, CA)

Assignee: Block, Inc.

G06F9/453G06Q20/3276

Abstract

Claims (49)

1. A method implemented by at least one computing device of a payment service, the method comprising:

receiving, by the at least one computing device, contextual information regarding an interaction between the payment service and a user device associated with a user;

determining, by the at least one computing device and based at least in part on inputting the contextual information into a trained machine learning (ML) model, at least one of a propensity metric or a value metric for the user, wherein the trained ML model is trained based on one or more propensity signals;

dynamically configuring, by the at least one computing device and based at least in part on the propensity metric, a user interface to enable the user to access data associated with a user account, wherein the configuring comprises arranging user interface elements on the user interface in a layout personalized for the user and based at least in part on the propensity metric, wherein each user interface element represents content particular to a service offered by the payment service, the payment service offering multiple services including the service;

based at least in part on receiving an indication of an interaction with a user interface element, associating an applet corresponding to a selected service with which the user interface element is associated with the user account, the applet configured to initialize an onboarding flow associated with enabling the user to access or add the selected service to the user account; and

in response to the applet initializing the onboarding flow, launching the onboarding flow associated with the selected service, wherein content included in the onboarding flow is customized based at least in part on the contextual information associated with the user or the selected service.

2. The method of claim 1 , further comprising:

selecting, by the at least one computing device, a booklet that is relevant to the user for a specified product that is relevant to the user from a plurality of booklets based on respective booklet engagement information associated with the plurality of booklets, wherein the respective booklet engagement information associated with the plurality of booklets is determined at least in part by inputting the contextual information into at least a second trained ML model for booklet analysis; and

outputting, by the at least one computing device, a recommendation for the specified product to a device associated with the user, wherein the recommendation is based on the booklet for the specified product and for the user.

3. The method of claim 2 , further comprising:

receiving the contextual information regarding the interaction between the payment service and the user device, the contextual information comprising at least one of an internet protocol (IP)-based transaction signal, an IP-based instrument link signal, or an IP-based fraud event signal; and

generating the booklet that is relevant to the user based on respective booklet engagement information based on the second trained ML model, wherein the booklet is generated based on one or more of text-based attributes, image-based attributes, video-based attributes, or booklet content identified by the second trained ML model.

4. The method of claim 1 , wherein the propensity metric corresponds to a likelihood of use of the service offered by the payment service, a value of the service offered by the payment service, and a risk associated with the service offered by the payment service.

5. The method of claim 1 , wherein the contextual information comprises social networking signals associated with the user.

6. The method of claim 1 , wherein the one or more propensity signals include historical user onboarding information.

7. The method of claim 1 , wherein the contextual information decays in strength after a period of time.

8. A system associated with a payment service comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions cause the one or more processors to perform acts comprising:

receiving contextual information regarding an interaction between the payment service and a user device associated with a user;

determining, based at least in part on inputting the contextual information into a trained machine learning (ML) model, at least one of a propensity metric or a value metric for the user, wherein the trained ML model is trained based on one or more propensity signals;

dynamically configuring, based at least in part on the propensity metric, a user interface to enable the user to access data associated with a user account, wherein the configuring comprises arranging user interface elements on the user interface in a layout personalized for the user and based at least in part on the propensity metric, wherein each user interface element represents content particular to a service offered by the payment service, the payment service offering multiple services including the service;

based at least in part on receiving an indication of an interaction with a user interface element, associating an applet corresponding to a selected service with which the user interface element is associated with the user account, the applet configured to initialize an onboarding flow associated with enabling the user to access or add the selected service to the user account; and

in response to the applet initializing the onboarding flow, launching the onboarding flow associated with the selected service, wherein content included in the onboarding flow is customized based at least in part on the contextual information associated with the user or the selected service.

9. The system of claim 8 , the acts further comprising:

selecting a booklet that is relevant to the user for a specified product that is relevant to the user from a plurality of booklets based on respective booklet engagement information associated with the plurality of booklets, wherein the respective booklet engagement information associated with the plurality of booklets is determined at least in part by inputting the contextual information into at least a second trained ML model for booklet analysis; and

outputting a recommendation for the specified product to a device associated with the user, wherein the recommendation is based on the booklet for the specified product and for the user.

10. The system of claim 9 , the acts further comprising:

receiving the contextual information regarding the interaction between the payment service and the user device, the contextual information comprising at least one of an internet protocol (IP)-based transaction signal, an IP-based instrument link signal, or an IP-based fraud event signal; and

generating the booklet that is relevant to the user based on respective booklet engagement information based on the second trained ML model, wherein the booklet is generated based on one or more of text-based attributes, image-based attributes, video-based attributes, or booklet content identified by the second trained ML model.

11. The system of claim 8 , wherein the propensity metric corresponds to a likelihood of use of the service offered by the payment service, a value of the service offered by the payment service, and a risk associated with the service offered by the payment service.

12. The system of claim 8 , wherein the contextual information comprises social networking signals associated with the user.

13. The system of claim 8 , wherein the one or more propensity signals include historical user onboarding information.

14. The system of claim 8 , wherein the contextual information decays in strength after a period of time.

15. One or more non-transitory computer-readable media storing instructions executable by one or more processors that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:

receiving contextual information regarding an interaction between a payment service and a user device associated with a user;

determining, based at least in part on inputting the contextual information into a trained machine learning (ML) model, at least one of a propensity metric or a value metric for the user, wherein the trained ML model is trained based on one or more propensity signals;

dynamically configuring, based at least in part on the propensity metric, a user interface to enable the user to access data associated with a user account, wherein the configuring comprises arranging user interface elements on the user interface in a layout personalized for the user and based at least in part on the propensity metric, wherein each user interface element represents content particular to a service offered by the payment service, the payment service offering multiple services including the service;

based at least in part on receiving an indication of an interaction with a user interface element, associating an applet corresponding to a selected service with which the user interface element is associated with the user account, the applet configured to initialize an onboarding flow associated with enabling the user to access or add the selected service to the user account; and

in response to the applet initializing the onboarding flow, launching the onboarding flow associated with the selected service, wherein content included in the onboarding flow is customized based at least in part on the contextual information associated with the user or the selected service.

16. The one or more non-transitory computer-readable media of claim 15 , the acts further comprising:

selecting a booklet that is relevant to the user for a specified product that is relevant to the user from a plurality of booklets based on respective booklet engagement information associated with the plurality of booklets, wherein the respective booklet engagement information associated with the plurality of booklets is determined at least in part by inputting the contextual information into at least a second trained ML model for booklet analysis; and

outputting a recommendation for the specified product to a device associated with the user, wherein the recommendation is based on the booklet for the specified product and for the user.

17. The one or more non-transitory computer-readable media of claim 16 , the acts further comprising:

receiving the contextual information regarding the interaction between the payment service and the user device, the contextual information comprising at least one of an internet protocol (IP)-based transaction signal, an IP-based instrument link signal, or an IP-based fraud event signal; and

generating the booklet that is relevant to the user based on respective booklet engagement information based on the second trained ML model, wherein the booklet is generated based on one or more of text-based attributes, image-based attributes, video-based attributes, or booklet content identified by the second trained ML model.

18. The one or more non-transitory computer-readable media of claim 15 , wherein the propensity metric corresponds to a likelihood of use of the service offered by the payment service, a value of the service offered by the payment service, and a risk associated with the service offered by the payment service.

19. The one or more non-transitory computer-readable media of claim 15 , wherein the contextual information comprises social networking signals associated with the user.

20. The one or more non-transitory computer-readable media of claim 15 , wherein the one or more propensity signals include historical user onboarding information.

Assignments (1)

References Cited (12)

Cited By (3)

US 12,443,940 US 12,567,084 US 12,614,204