Generating a suggested shopping list by populating a template shopping list of item categories with item types and quantities based on a set of collection rules

Patent metadata

Field	Value
Publication number	US-12482030-B2
Application number	US-202318113870-A
Country	US
Kind code	B2
Filing date	Feb 24, 2023
Priority date	Feb 24, 2023
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

An online system generates a template shopping list for a user by accessing a machine learning model trained based on historical order information associated with the user, applying the model to predict likelihoods of conversion for item categories by the user, and populating the template shopping list with one or more item categories based on the predicted likelihoods. The system ranks one or more item types associated with each item category in the template shopping list and determines a set of collection rules associated with one or more item categories/types based on the historical order information. The system generates a suggested shopping list by populating each item category in the template shopping list with one or more item types and a quantity of each item type based on the ranking and rules and sends the suggested shopping list and rules for display to a client device associated with the user.

First claim

What is claimed is:

1 . A method comprising, at a computer system comprising a processor and a computer-readable medium:
generating, for a user of an online system, a template shopping list comprising a set of ranked item categories, wherein generating the template shopping list comprises:
accessing a machine learning model trained to predict a likelihood of conversion for an item category by the user, wherein the machine learning model is trained based at least in part on historical order information associated with the user,
applying the machine learning model to one or more attributes of the user and each item category of a plurality of item categories to predict the likelihood of conversion for each item category of the plurality of item categories by the user,
ranking, based at least in part on the likelihood of conversion predicted for each item category of the plurality of item categories, the plurality of item categories to generate a ranked list of item categories,
selecting, using the likelihood of conversion predicted for each item category of the plurality of item categories, the set of ranked item categories from the ranked list of item categories, and
populating the template shopping list with the set of ranked item categories;
for each item category of the set of ranked item categories from the template shopping list, applying the machine learning model to one or more additional attributes of the user and each item type of a set of item types associated with each item category to predict an additional likelihood of conversion for each item type of the set of item types by the user; for each item category of the set of ranked item categories from the template shopping list, ranking the set of item types based at least in part on the additional likelihood of conversion for each item type of the set of item types to generate a ranked set of item types; determining, based at least in part on the historical order information associated with the user, a set of collection rules associated with one or more of: an item category and an item type; generating a suggested shopping list by populating each item category of the set of ranked item categories from the template shopping list with the set of ranked item types and information describing a quantity of each item type of the set of ranked item types based at least in part on the ranking and the set of collection rules; and sending the suggested shopping list and the set of collection rules for display at a user interface of a device associated with the user, wherein a first area of the user interface includes the set of ranked item categories, information describing a quantity of the set of ranked item types for each item category, and a collection rule of the set of collection rules associated with each item category, and a second area of the user interface includes, for each item category of the set of ranked item categories, the set of ranked item types, information describing a quantity of each item type of the set of ranked item types, and a collection rule of the set of collection rules associated with each item type of the set of ranked item types.

2 . The method of claim 1 , wherein the set of collection rules describes one or more selected from the group consisting of: a quantity of item types associated with an item category to be collected in an order for the user, a quantity of an item type to be collected in an order for the user, a quality of item types associated with an item category to be collected in an order for the user, a quality of an item type to be collected in an order for the user, a budget for item types associated with an item category to be collected in an order for the user, and a budget associated with an item type to be collected in an order for the user.

3 . The method of claim 1 , further comprising:
storing the template shopping list and the set of collection rules in association with user-identifying information associated with the user.

4 . The method of claim 1 , further comprising:
receiving a request from the device associated with the user to modify one or more of: one or more item categories of the plurality of item categories, the set of item types, and the set of collection rules; and modifying, based at least in part on the request from the device associated with the user, the one or more of: the one or more item categories, the set of item types, and the set of collection rules.

5 . The method of claim 1 , further comprising:
receiving a request from the device associated with the user to accept one or more of: the template shopping list, the suggested shopping list, and the set of collection rules.

6 . The method of claim 1 , further comprising:
responsive to receiving a request from the device associated with the user to accept the suggested shopping list and the set of collection rules, sending the suggested shopping list and the set of collection rules to a device associated with a picker servicing a new order for the user; receiving a notification from the device associated with the picker that an item type included in the suggested shopping list does not satisfy one or more collection rules of the set of collection rules; updating the suggested shopping list to include an additional item type and information describing a quantity of the additional item type based at least in part on the ranking of the set of item types and the set of collection rules; and sending the updated suggested shopping list for display at a user interface of the picker device associated with the picker.

7 . The method of claim 1 , wherein the historical order information associated with the user comprises: a time at which the user placed a previous order, a total number of items included in a previous order placed by the user, a total amount spent by the user on a previous order, a name of an item type previously ordered by the user, an item category associated with an item type previously ordered by the user, a quantity of an item type previously ordered by the user, a price associated with an item type previously ordered by the user, a sale associated with an item type previously ordered by the user, a discount associated with an item type previously ordered by the user, a stock keeping unit (SKU) associated with an item type previously ordered by the user, a serial number associated with an item type previously ordered by the user, a model associated with an item type previously ordered by the user, a size of an item type previously ordered by the user, a dimension of an item type previously ordered by the user, a color of an item type previously ordered by the user, a quality of an item type previously ordered by the user, a brand associated with an item type previously ordered by the user, a seasonality associated with an item type previously ordered by the user, a freshness of an item type previously ordered by the user, one or more ingredients included in an item type previously ordered by the user, one or more materials included in an item type previously ordered by the user, a manufacturing location associated with an item type previously ordered by the user, feedback associated with a previous order placed by the user, a refund for a previous order placed by the user, and an instruction associated with a previous order placed by the user.

8 . The method of claim 1 , wherein the one or more attributes of the user and each item category of the plurality of item categories comprise one or more selected from the group consisting of: a tenure of the user with the online system, a platform used by the user to access the online system, a geographical region associated with the user, an average amount the user spends on each order, an average

Assignees

• Maplebear Inc

Inventors

• Zhang Xuan
• Gudla Vinesh Reddy
• Tenneti Tejaswi
• Wang Haixun

Classifications

• G06Q30/0619

  Neutral agent · CPC title

• G06Q30/0631

  Recommending goods or services · CPC title

• G06Q30/0633 Primary

  Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087) · CPC title