Google Inc.

Daria Antonova

Kedar Dhamdhere

Bilgehan Uygar Oztekin

Finnegan Southey

Zhenyu Mao

A method of processing a search query includes, for each search context of a plurality of search contexts, for each scoring primitive of a plurality of scoring primitives, and for a set of previously executed search queries that are consistent with the search context, determining a correlation between the scoring primitive and actual user selections of results of the previously executed search queries by a plurality of users. For each search context, machine learning is performed on the correlations to identify a predicted performance function comprising a weighted subset of the scoring primitives that meet predefined predictive quality criteria. Executing a user submitted search query includes associating the user submitted search query with a respective search context, and ordering at least a portion of the search results in accordance with the predicted performance function for the search context for the user submitted search query.

Growing community of inventors

Mountain View, CA, United States of America

Daria Antonova