Maplebear Inc.

Manmeet Singh

Tejaswi Tenneti

Sharath Rao Karikurve

Tyler Russell Tate

Taesik Na

Reza Sadri

Zhihong Xu

Guanghua Shu

Wideet Shende

An online system maintains item embeddings for items. As a number of items maintained by the online system increases, maintaining a single index of the item embeddings is increasingly difficult. To increase scalability, the online system partitions item embeddings into multiple indices, with each index corresponding to a value of a specific attribute maintained by the online system for items. For example, an online system generates indices that each correspond to a different warehouse offering items. To expedite retrieval of item embeddings, the online system allocates each index to one of a number of shards. When the online system receives a query, the online system determines an embedding for the query and retrieves an index from a shard based on metadata received with the query. Based on distances between the query for the embedding and the item embeddings in the retrieved index, the online system selects one or more items.

Distributed approximate nearest neighbor service architecture for retrieving items in an embedding space

An online concierge shopping system identifies recipes to users to encourage them to include items from the recipes in orders. The online concierge system maintains user embeddings for users and recipe embeddings for recipes. For users who have not placed orders, recipes are recommended based on global user interactions with recipes. Users who have previously ordered items from recipes are suggested recipes selected based on a similarity of their user embedding to recipe embeddings. Users who have purchased items but not from recipes are compared to a set of similar users based on the user embeddings, and recipes with which users of the set of similar users interacted are used for identifying recipes to the users. A recipe graph may be maintained by the online concierge system to identify similarities between recipes for expanding candidate recipes to suggest to users.

Method, medium, and system for personalized recommendation of recipes based on embeddings for a user and for stored recipes

Method and medium for personalized recommendation of recipes including based on embeddings for a user and for stored recipes

Growing community of inventors

Santa Clara, CA, United States of America

Manmeet Singh