Determining purchase suggestions for an online shopping concierge platform

Patent metadata

Field	Value
Publication number	US-12561725-B2
Application number	US-202318212122-A
Country	US
Kind code	B2
Filing date	Jun 20, 2023
Priority date	Jun 20, 2023
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

The present disclosure is directed to determining purchase suggestions for an online shopping concierge platform. In particular, the methods and systems of the present disclosure may receive, from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; determine, based at least in part on one or more machine learning (ML) models and the data indicating the interaction(s), a likelihood that the customer will purchase a particular item if presented, at a specific time, with a suggestion to purchase the particular item; and generate and communicate data describing a graphical user interface (GUI) comprising at least a portion of a listing of one or more purchase suggestions including the suggestion to purchase the particular item.

First claim

What is claimed is:

1 . A method, performed at a computer system comprising a processor and a computer-readable medium, comprising:
receiving, via a communication interface of the computer system and from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; receiving, via a communication interface of the computer system and from a retailer computing system, item data indicating inventory levels of items available at a retailer location and timing information associated with the inventory levels, the timing information comprising at least one of: a time an item was last found at the retailer location, a time an item was last not found at the retailer location, or a rate at which the item is found; determining, by the computer system based at least in part on one or more first machine learning (ML) models, and the item data indicating inventory levels of items available at the retailer location and timing information associated with the inventory levels, a likelihood of each item will be available at different times; determining, by the computer system and based at least in part on one or more second ML models and the data indicating the one or more interactions, and the determined likelihood of a particular item will be available at different times, a likelihood that the customer will purchase a particular item if presented, at a specific time when the particular item is determined by the first ML models as likely available, with a suggestion to purchase the particular item; determining, by the computer system and based at least in part on the likelihood that the customer will purchase the particular item, to include the suggestion to purchase the particular item in a listing of one or more purchase suggestions to be presented to the customer at the specific time; generating, by the computer system, data describing a graphical user interface (GUI) comprising at least a portion of the listing of the one or more purchase suggestions including the suggestion to purchase the particular item; and communicating, via the communication interface and to the computing device associated with the customer, the data describing the GUI such that the computing device associated with the customer renders and displays, at the specific time, the at least a portion of the listing of the one or more purchase suggestions including the suggestion to purchase the particular item.

2 . The method of claim 1 , comprising:
determining, by the computer system, based at least in part on the one or more ML models, and for each item type of a plurality of different and distinct item types available via the online shopping concierge platform, a likelihood that one or more items of the item type will be repurchased a given amount of time after a previous purchase; and ranking, by the computer system, the listing of the one or more purchase suggestions including the suggestion to purchase the particular item and one or more suggestions to purchase one or more items of the plurality of different and distinct item types based at least in part on their determined likelihoods of being repurchased at the specific time.

3 . The method of claim 2 , wherein determining the likelihood that the one or more items of the item type will be repurchased comprises determining the likelihood that the one or more items of the item type will be repurchased based at least in part on data indicating a plurality of different and distinct interactions with the online shopping concierge platform by a plurality of different and distinct customers of the online shopping concierge platform.

4 . The method of claim 3 , comprising identifying, by the computer system, the plurality of different and distinct customers based at least in part on a determination, by the computer system, that the plurality of different and distinct customers are customers of one or more retailers associated with the online shopping concierge platform that offer the particular item.

5 . The method of claim 3 , comprising identifying, by the computer system, the plurality of different and distinct customers based at least in part on a determination, by the computer system, that the plurality of different and distinct customers are associated with a customer cohort sharing one or more characteristics with the customer.

6 . The method of claim 3 , comprising weighting, by the computer system, the determined likelihoods based at least in part on a determination, by the computer system, of a degree of similarity between the customer and the plurality of different and distinct customers.

7 . The method of claim 3 , wherein determining the likelihood that one or more items of the item type will be repurchased comprises determining the likelihood based at least in part on one or more of a maximum time between purchases of the item type by the plurality of different and distinct customers, a minimum time between purchases of the item type by the plurality of different and distinct customers, an average time between purchases of the item type by the plurality of different and distinct customers, a median time between purchases of the item type by the plurality of different and distinct customers, or a standard deviation of time between purchases of the item type by the plurality of different and distinct customers.

8 . The method of claim 1 , comprising updating, by the computer system, at least one of the one or more ML models based at least in part on data indicating whether the customer invoked the suggestion to purchase the particular item.

9 . The method of claim 8 , wherein responsive to invoking, by the customer, the suggestion to purchase the particular item, generating, by the computer system, data describing a graphical user interface (GUI) indicating the particular item has been designated for purchase by the customer via the online shopping concierge platform.

10 . The method of claim 1 , comprising determining, by the computer system and based at least in part on the one or more ML models and the specific time, one or more features of the particular item to modify in the suggestion from a previous purchase by the customer of the particular item via the online shopping concierge platform.

11 . The method of claim 1 , wherein determining the likelihood that the customer will purchase the particular item comprises determining the likelihood based at least in part on an expiration date determined by the computer system for an item, previously purchased by the customer via the online shopping concierge platform, of a same item type as the particular item.

12 . The method of claim 1 , wherein determining the likelihood that the customer will purchase the particular item comprises determining the likelihood based at least in part on an inventory level, determined by the computer system, for the particular item.

13 . The method of claim 1 , wherein determining the likelihood that the customer will purchase the particular item comprises determining the likelihood based at least in part on data received, by the computer system, from one or more smart appliances associated with the customer.

14 . The method of claim 1 , wherein determining the likelihood that the customer will purchase the particular item comprises determining the likelihood based at least in part on a frequency with which the customer shops via the online shopping concierge platform.

15 . The method of claim 1 , comprising generating, by the computer system, at least one of the one or more

Assignees

• Maplebear Inc

Inventors

• Mccoleman Ryan
• Scheibelhut Brent
• Oberemk Mark
• Maharaj Shaun Navin

Classifications

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0613

  using intermediate agents · CPC title

• G06Q30/0641

  utilising user interfaces specially adapted for shopping · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title