Google Inc.

Anurag Vyas

Krzysztof Duleba

Monica Chawathe Lenart

Finnegan Southey

Anandsudhakar Kesari

Yanli Cai

Arsalan Mosenia

Techniques of providing category recommendations include a category recommendation system that provides users recommended categories based on implicit data (e.g., user-item interactions) and/or explicit data (e.g., queries, user information). The recommendations can be personalized or non-personalized (i.e., depending if user embeddings are used), queried or non-queried (i.e., depending on whether query embeddings are used), or personalized and queried (if both user and query embeddings are used). In any of these cases, there is an offline mode and a serving mode. In the offline mode, a category embedding is generated from an aggregation of item embeddings associated with a candidate category. In the serving mode, the candidate category is selected for display on a user device based on a similarity between the category embedding and either, or both, of the user embedding and the query embedding.

Category recommendation with implicit item feedback

Provided are systems and methods for selecting a hierarchical location corresponding to a geographic location of a client computer. In some embodiments, a request for location information may be received from a client computer. The request may include a token that enables determination of geolocation data based on the token. The geolocation data may include a list of hierarchical locations, such as a postal code, a city, a state, and a county, and each hierarchical location may be associated with a confidence measure. The hierarchical locations may be iteratively traversed from smallest to largest. If the confidence measure of a selected hierarchical location is greater than a threshold, the hierarchical location may be provided as the location information. If the confidence measure of the selected hierarchical location is less than the threshold, the next hierarchical location may be selected and the associated confidence measure compared to the threshold.

Systems and methods for confidence-based selection of hierarchical locations

Growing community of inventors

Sunnyvale, CA, United States of America

Anurag Vyas