METHOD OF IDENTIFYING TEMPORAL DEMAND OF QUERIES AND METADATA TO GIVE BETTER AUTOCOMPLETE QUERIES AND IMPROVED SEARCH RESULTS

摘要

Embodiments describe systems and methods for identifying temporal demand for queries and using metadata to modify autocomplete results. In one embodiment, a record of historical queries is stored by a system and analyzed to identify periodic or repeated events where demand for autocomplete results associated with one or more categories deviates from normal demand. A temporal model based on this record is used to adjust autocomplete search results during subsequent time periods associated with the repeated events.

主权项

1. A networked system comprising an autocomplete system, the networked system further comprising:
one or more computer processors and storage devices configured to: store a record of received user inputs in an autocomplete database as part of an autocomplete model; associate each user input of the record of received user inputs with one or more categories and with one of a plurality of time segments of a repeated considered time period in order to to build a temporal model capturing temporal demand for the one or more categories, wherein the plurality of time segments comprises a boosted time segment, and wherein during the boosted time segment a first category of the one or more autocomplete categories is associated with a deviation from an average number of user inputs for the repeated considered time period; receive a partial user input from a first client system during the boosted time segment of the repeated considered time period; and create a set of autocomplete results using the temporal model, wherein the set of autocomplete results is based at least in part on an identification of the partial user input being received during the boosted time segment.