Facebook, Inc.

Brinda Mehta

Melissa Rose Winstanley

Eric Ringger

David M Goldblatt

Daniel Cabral Francisco

Krishna Jayaram Kalpathy

Evan John Rocha

Prerna Totla

In one embodiment, a method includes receiving a search query from a client system of a first user; parsing the search query into n-grams, and calculating confidence-scores for entities in a set of query-analysis-entities based on the n-grams, each confidence-score representing a probability that one or more of the n-grams are intended to reference a respective entity; determining a set of search results matching the search query, and calculating entity-frequencies corresponding to entities in a set of results-analysis-entities based on a histogram analysis of the set of search results; calculating a filter-score entities in a set of prospective-entities, which includes entities from the set of query-analysis-entities and the set of results-analysis-entities, based on the respective confidence-score and entity-frequency; and sending, to the client system, suggested filters corresponding to entities having a filter-score greater than a threshold filter-score, the suggested filters being selectable to modify the set of search results.

Suggesting filters for search on online social networks

Growing community of inventors

San Jose, CA, United States of America

Brinda Mehta