Granted Patent B2

US 12,373,876 · App. 18/451,008 · Granted Jul 29, 2025

Inventors: Abhay Kumar (San Francisco, CA); Dan Hipschman (San Francisco, CA); Rong Yan (Palo Alto, CA); John Berian James (San Francisco, CA); Gian Perrone (San Francisco, CA); Mai Leduc (San Francisco, CA)

Assignee: Block, Inc.

G06Q30/0631G06Q20/20G06Q30/0205G06Q30/0206G06Q30/0253G06Q30/0264G06Q30/0255G06Q30/0268

Abstract

Claims (83)

1. A method comprising:

receiving, from merchant computing devices associated with a plurality of merchants associated with a payment processing system, transaction data associated with transactions performed between the plurality of merchants and buyers;

training a first model to generate profiles, wherein the first model is trained using at least one of:

merchant data associated with the plurality of merchants;

buyer data associated with the buyers; or

the transaction data associated with the transactions;

receiving an indication of a transaction between a buyer of the buyers and a merchant of the plurality of merchants, wherein the transaction comprises a selection of an item for purchase by the buyer from the merchant;

comparing information associated with the buyer to the profiles;

determining that the information associated with the buyer does not correspond to an individual profile of the profiles;

determining, using a second model and based on the first model and the indication of the transaction, that a characteristic of the transaction corresponds to a profile of the profiles with a confidence score that is above a predetermined threshold, wherein the second model is a probabilistic model and wherein the characteristic is associated with at least one of the buyer, the merchant, or the transaction;

causing presentation, via a graphical user interface (GUI) displayed on a merchant computing device associated with the merchant, of a plurality of selectable icons corresponding to a plurality of items offered for purchase by the merchant;

generating, based at least in part on a portion of the transaction data being associated with one or more other merchants of the plurality of merchants that offer the item for purchase and a determination that the characteristic corresponds to the profile, a recommendation for the buyer to purchase at least one additional item with the item that the buyer has already selected for purchase; and

in response to generating the recommendation, causing a rendering of a new selectable icon corresponding to a combination of the item and the at least one additional item, wherein the new selectable icon is presented temporarily and not permanently with the plurality of selectable icons.

2. The method of claim 1 , wherein the profiles are first profiles and further comprising:

retraining the first model based at least in part on at least one of additional transaction data, additional merchant data, or additional buyer data;

generating second profiles using the retrained first model; and

generating the recommendation based at least in part on the characteristic corresponding to a second profile of the second profiles.

3. The method of claim 1 , wherein the transaction data includes at least one of a description of one or more items selected by the buyers in association with the transactions, pricing information associated with the one or more items, payment information associated with the transactions, geographic information associated with the transactions, time information associated with the transactions, date information associated with the transactions, or buyer identifying information associated with the transactions.

4. The method of claim 1 , wherein the merchant computing device includes an instance of a merchant application installed thereon for configuring the merchant computing device as a point-of-sale (POS) terminal to communicate data over one or more networks to the payment processing system.

5. The method of claim 1 , wherein the recommendation comprises a first recommendation, the method further comprising:

generating, using the first model or a third model, a second recommendation to merge two or more profiles of the profiles.

6. The method of claim 1 , further comprising:

detecting one or more of (1) an interaction with an icon of the plurality of selectable icons, (2) a scan of a barcode associated with the item, or (3) an input to a buyer device of the buyer,

wherein determining that the buyer has selected the item for purchase is based at least in part on one of the interaction, the scan, or the input.

7. The method of claim 1 , wherein generating the recommendation is further based at least in part on applying a third model to at least the portion of the transaction data associated with the one or more other merchants of the plurality of merchants or another portion of the transaction data associated with the one or more other merchants of the plurality of merchants.

8. The method of claim 1 , wherein the characteristic is associated with an indication in the profile that the buyer has purchased a second additional item in a historical transaction if offered the at least one additional item in a promotion or as part of a bundle with a first item.

9. The method of claim 1 , wherein the recommendation comprises a first recommendation, wherein the at least one additional item comprises an alternative to a preferred item, and the method further comprising:

determining an inventory of the merchant;

determining to generate a second recommendation to purchase the preferred item in addition to the item that the buyer has already selected for purchase;

determining that the preferred item is not in the inventory of the merchant;

refraining from generating the second recommendation to purchase the preferred item; and

sending a suggestion to the merchant computing device, to add the preferred item to the inventory, wherein generating the first recommendation for the buyer to purchase the at least one additional item is further based at least in part on determining that the preferred item is not in the inventory.

10. A system 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, from merchant computing devices associated with a plurality of merchants associated with a payment processing system, transaction data associated with transactions performed between the plurality of merchants and buyers;

training a first model to generate profiles, wherein the first model is trained using at least one of:

merchant data associated with the plurality of merchants;

buyer data associated with the buyers; or

the transaction data associated with the transactions;

receiving an indication of a transaction between a buyer of the buyers and a merchant of the plurality of merchants, wherein the transaction comprises a selection of an item for purchase by the buyer from the merchant;

comparing information associated with the buyer to the profiles;

determining that the information associated with the buyer does not correspond to an individual profile of the profiles;

determining, using a second model and based on the first model and the indication of the transaction, that a characteristic of the transaction corresponds to a profile of the profiles with a confidence score that is above a predetermined threshold, wherein the second model is a probabilistic model, and wherein the characteristic is associated with at least one of the buyer, the merchant, or the transaction;

causing presentation, via a graphical user interface (GUI) displayed on a merchant computing device associated with the merchant, of a plurality of selectable icons corresponding to a plurality of items offered for purchase by the merchant;

generating, based at least in part on a portion of the transaction data being associated with one or more other merchants of the plurality of merchants that offer the item for purchase and a determination that the characteristic corresponds to the profile, a recommendation for the buyer to purchase at least one additional item with the item that the buyer has already selected for purchase; and

in response to generating the recommendation, causing a rendering of a new selectable icon corresponding to a combination of the item and the at least one additional item, wherein the new selectable icon is presented temporarily and not permanently with the plurality of selectable icons.

11. The system of claim 10 , wherein the profiles are first profiles and the acts further comprising:

retraining the first model based at least in part on at least one of additional transaction data, additional merchant data, or additional buyer data;

generating second profiles; and

generating the recommendation based at least in part on the characteristic corresponding to a second profile of the second profiles.

12. The system of claim 10 , wherein the transaction data includes at least one of a description of one or more items selected by the buyers in association with the transactions, pricing information associated with the one or more items, payment information associated with the transactions, geographic information associated with the transactions, time information associated with the transactions, date information associated with the transactions, or buyer identifying information associated with the transactions.

13. The system of claim 10 , wherein the merchant computing device includes an instance of a merchant application installed thereon for configuring the merchant computing device as a point-of-sale (POS) terminal to communicate data over one or more networks to the payment processing system.

14. The system of claim 10 , wherein the recommendation comprises a first recommendation, the acts further comprising:

generating, using the first model or a third another model, a second recommendation to merge two or more profiles of the profiles.

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

detecting one or more of (1) an interaction with an icon of the plurality of selectable icons (2) a scan of a barcode associated with the item, or (3) an input to a buyer device of the buyer,

wherein determining that the buyer has selected the item for purchase is based at least in part on one of the interaction, the scan, or the input.

16. 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, from merchant computing devices associated with a plurality of merchants associated with a payment processing system, transaction data associated with transactions performed between the plurality of merchants and buyers;

training a first model to generate profiles, wherein the first model is trained using at least one of:

merchant data associated with the plurality of merchants;

buyer data associated with the buyers; or

the transaction data associated with the transactions;

receiving an indication of a transaction between a buyer of the buyers and a merchant of the plurality of merchants, wherein the transaction comprises a selection of an item for purchase by the buyer from the merchant;

comparing information associated with the buyer to the profiles;

determining that the information associated with the buyer does not correspond to an individual profile of the profiles;

determining, using a second model and based on the first model and the indication of the transaction, that a characteristic of the transaction corresponds to a profile of the profiles with a confidence score that is above a predetermined threshold, wherein the second model is a probabilistic model, and wherein the characteristic is associated with at least one of the buyer, the merchant, or the transaction;

causing presentation, via a graphical user interface (GUI) displayed on a merchant computing device associated with the merchant, of a plurality of selectable icons corresponding to a plurality of items offered for purchase by the merchant;

generating, based at least in part on a portion of the transaction data being associated with one or more other merchants of the plurality of merchants that offer the item for purchase and a determination that the characteristic corresponds to the profile, a recommendation for the buyer to purchase at least one additional item than with the item that the buyer has already selected for purchase; and

in response to generating the recommendation, causing a rendering of a new selectable icon corresponding to a combination of the item and the at least one additional item, wherein the new selectable icon is presented temporarily and not permanently with the plurality of selectable icons.

17. The one or more non-transitory computer-readable media of claim 16 , wherein generating the recommendation is further based at least in part on applying a third model to at least the portion of the transaction data associated with the one or more other merchants of the plurality of merchants or another portion of the transaction data associated with the one or more other merchants of the plurality of merchants.

18. The one or more non-transitory computer-readable media of claim 16 , wherein the characteristic is associated with an indication in the profile that the buyer has purchased a second additional item in a historical transaction if offered the at least one additional item in a promotion or as part of a bundle with a first item.

19. The one or more non-transitory computer-readable media of claim 16 , wherein the recommendation comprises a first recommendation, wherein the at least one additional item comprises an alternative to a preferred item, and the acts further comprising:

determining an inventory of the merchant;

determining to generate a second recommendation to purchase the preferred item in addition to the item that the buyer has already selected for purchase;

determining that the preferred item is not in the inventory of the merchant;

refraining from generating the second recommendation to purchase the preferred item; and

sending a suggestion to the merchant computing device, to add the preferred item to the inventory, wherein generating the first recommendation for the buyer to purchase the at least one additional item is further based at least in part on determining that the preferred item is not in the inventory.

20. The one or more non-transitory computer-readable media of claim 16 , wherein the profiles are first profiles and the acts further comprising:

retraining the first model based at least in part on at least one of additional transaction data, additional merchant data, or additional buyer data:

generating second profiles using the retrained first model; and

generating the recommendation based at least in part on the characteristic corresponding to a second profile of the second profiles.

Assignments (2)

Continuity (6)

References Cited (303)