Recommending recipes using time-horizon based user ingredient pool

Patent metadata

Field	Value
Publication number	US-2022215061-A1
Application number	US-202117142038-A
Country	US
Kind code	A1
Filing date	Jan 5, 2021
Priority date	Jan 5, 2021
Publication date	Jul 7, 2022
Grant date	—

Abstract

An online recommendation system can choose recipes to recommend to a customer based on a set of ingredients the customer is inferred to have on hand (a customer pantry model). For example, the recommendation system can look at recent or historical purchases made by the customer and determine what items the customer still has available based on an assumed shelf life for the purchased items. Using the customer pantry model, the recommendation system selects recipes based on overlapping ingredients between recipe's ingredient lists and ingredients available to the customer (including the customer pantry model and their current shopping cart). In some implementations, the recommendation system first selects a set of candidate recipes based on the overlap, then selects the final set of recipes to recommend based on a score optimization (for example, performed using a machine learning model).

First claim

What is claimed is:

1 . A method for recommending recipes to a user, the method comprising:
maintaining, at a recipe recommendation system, a recipe database comprising a plurality of recipes, each recipe including an ingredients list comprising a set of items required to prepare the recipe; determining, based on a purchase history of the user and an expected shelf life of one or more items in the purchase history, a user pantry model, the user pantry model comprising a set of items inferred to be available to the user; determining, from the plurality of recipes, a set of candidate recipes by, for each of the plurality of recipes:
identifying, based on a comparison of the ingredients list for the recipe with the user pantry model, a set of missing ingredients comprising one or more items in the ingredients list not included in the user pantry model, and
selecting the recipe as a candidate recipe based on the set of missing ingredients;
scoring each of the set of candidate recipes by applying a machine learning model to the candidate recipe, where the machine learning model is trained to generate a score of recommending the candidate recipe to the user; selecting, based on the scored candidate recipes, one or more candidate recipes to recommend to the user; and sending, from the recipe recommendation system to a user device associated with the user, the one or more selected candidate recipes for display to the user.

2 . The method of claim 1 , wherein determining the user pantry model for the user comprises:
identifying a set of recently purchased items from the purchase history of the user; and selecting one or more items of the set of recently purchased items for inclusion in the user pantry model based on a historical purchase frequency of the item in the purchase history of the user.

3 . The method of claim 1 , wherein determining the user pantry model for the user is based on one or more tags associated with items in the purchase history.

4 . The method of claim 1 , further comprising:
receiving, from a user device associated with the user, a request for a graphical user interface comprising recommended recipes; and wherein sending the one or more selected candidate recipes for display to the user comprises generating the graphical user interface comprising recommended recipes based on the one or more selected candidate recipes.

5 . The method of claim 4 , wherein the generated graphical user interface comprising recommended recipes includes an identification of one or more missing ingredients for each of the selected candidate recipes.

6 . The method of claim 1 , wherein the set of missing ingredients comprises one or more items in the ingredients list not included in either the user pantry model or a current order of the user.

7 . The method of claim 1 , wherein the analysis of the set of missing ingredients is based on a number of missing ingredients in the set of missing ingredients, a total number of ingredients in the ingredients list of the recipe, and one or more weights of ingredients of the ingredients list.

8 . The method of claim 1 , wherein the ingredients list of each recipe further comprises a set of substitute ingredients that could replace one or more ingredients when preparing the recipe.

9 . The method of claim 8 , further comprising:
determining, for each of the plurality of recipes, a set of substitute ingredients that could replace one or more ingredients of the ingredients list when preparing the recipe; and including the set of substitute ingredients in the ingredients list for the recipe.

10 . The method of claim 1 , wherein the machine learning model is trained to predict a likelihood that the user would take an action in response to a recommendation of a recipe.

11 . A non-transitory computer readable storage medium comprising instructions which, when executed by a processor, cause the processor to perform the steps of:
maintaining, at a recipe recommendation system, a recipe database comprising a plurality of recipes, each recipe including an ingredients list comprising a set of items required to prepare the recipe; determining, based on a purchase history of the user and an expected shelf life of one or more items in the purchase history, a user pantry model, the user pantry model comprising a set of items inferred to be available to the user; determining, from the plurality of recipes, a set of candidate recipes by, for each of the plurality of recipes:
identifying, based on a comparison of the ingredients list for the recipe with the user pantry model, a set of missing ingredients comprising one or more items in the ingredients list not included in the user pantry model, and
selecting the recipe as a candidate recipe based on the set of missing ingredients;
scoring each of the set of candidate recipes by applying a machine learning model to the candidate recipe, where the machine learning model is trained to generate a score of recommending the candidate recipe to the user; selecting, based on the scored candidate recipes, one or more candidate recipes to recommend to the user; and sending, from the recipe recommendation system to a user device associated with the user, the one or more selected candidate recipes for display to the user.

12 . The computer readable storage medium of claim 11 , wherein determining the user pantry model for the user comprises:
identifying a set of recently purchased items from the purchase history of the user; and selecting one or more items of the set of recently purchased items for inclusion in the user pantry model based on a historical purchase frequency of the item in the purchase history of the user.

13 . The computer readable storage medium of claim 11 , wherein determining the user pantry model for the user is based on one or more tags associated with items in the purchase history.

14 . The computer readable storage medium of claim 11 , wherein the instructions, when executed by the processor, further cause the processor to perform the steps of:
receiving, from a user device associated with the user, a request for a graphical user interface comprising recommended recipes; and wherein sending the one or more selected candidate recipes for display to the user comprises generating the graphical user interface comprising recommended recipes based on the one or more selected candidate recipes.

15 . The computer readable storage medium of claim 14 , wherein the generated graphical user interface comprising recommended recipes includes an identification of one or more missing ingredients for each of the selected candidate recipes.

16 . The computer readable storage medium of claim 11 , wherein the set of missing ingredients comprises one or more items in the ingredients list not included in either the user pantry model or a current order of the user.

17 . The computer readable storage medium of claim 111 , wherein the analysis of the set of missing ingredients is based on a number of missing ingredients in the set of missing ingredients, a total number of ingredients in the ingredients list of the recipe, and one or more weights of ingredients of the ingredients list.

18 . The computer readable storage medium of claim 11 , wherein the ingredients list of each recipe further comprises a set of substitute ingredients that could replace one or more ingredients when preparing the recipe.

19 . The computer readable storage medium of claim 18 , wherein the instructions, when executed by the processor, further

Assignees

• Maplebear Inc

Inventors

• Nigul Leho

Classifications

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06Q30/0601

  Electronic shopping [e-shopping] · CPC title

• G06Q30/0282

  Rating or review of business operators or products · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title