CPC G06F 16/245 (2019.01) [G06F 16/2228 (2019.01); G06F 16/319 (2019.01); G06N 5/025 (2013.01); G06N 20/00 (2019.01)] | 20 Claims |
1. A computer-implemented method, comprising:
before receiving, at a search system, a subsequent query that is associated with at least one or more features:
generating, using a predictive model and by the search system, data indicating a predicted relevance of a particular item of content to a query that is associated with the one or more features, wherein the data indicating the predicted relevance is generated by the predictive model based at least on the particular item of content; and
storing, by the search system and in a record entry of a database for a search index, data that associates at least the particular item of content with the data indicating the predicted relevance generated by the predictive model;
receiving, at the search system, the subsequent query that is associated with at least the one or more features;
in response to receiving the subsequent query:
accessing, by the search system, the record entry of the database for the search index to identify the particular item and the data indicating the predicted relevance that was previously generated by the predictive model based at least on the one or more features associated with the subsequent query;
selecting, using the data indicating the predicted relevance, the particular item of content; and
providing data identifying the particular item of content in response to the subsequent query.
|