-
公开(公告)号:US10410270B2
公开(公告)日:2019-09-10
申请号:US15389441
申请日:2016-12-22
Applicant: GOOGLE INC.
Inventor: Karthic Neelands Epker , Ying Liu , Alan Howard Davis
IPC: G06Q30/06 , G06Q50/12 , H04L12/26 , G06F16/2458 , G06F16/951 , G06Q50/14
Abstract: A search system extracts, for each property known to the system, historical information comprising data for itineraries associated with a partner system associated with the property. The search system determines, for each property-itinerary combination, an update frequency comprising based on historical information data. The search system extracts a history of user impressions of itineraries comprising the property. The search system determines a relative impression weight for each itinerary, an absolute impression weight for the property, and an expected impression weight of each property-itinerary combination. For each current property-itinerary combination, the search system determines a utility value based on the expected update frequency and expected impression weight to satisfy bandwidth constraints for each partner system. The search system schedules, for each partner system, queries for property-itinerary combinations having values greater than threshold utility value.
-
公开(公告)号:US20180182012A1
公开(公告)日:2018-06-28
申请号:US15389441
申请日:2016-12-22
Applicant: GOOGLE INC.
Inventor: Karthic Neelands Epker , Ying Liu , Alan Howard Davis
CPC classification number: G06Q30/0625 , G06F16/2471 , G06F16/951 , G06Q30/0623 , G06Q50/12 , G06Q50/14 , H04L43/0876 , H04L43/16
Abstract: A search system extracts, for each property known to the system, historical information comprising data for itineraries associated with a partner system associated with the property. The search system determines, for each property-itinerary combination, an update frequency comprising based on historical information data. The search system extracts a history of user impressions of itineraries comprising the property. The search system determines a relative impression weight for each itinerary, an absolute impression weight for the property, and an expected impression weight of each property-itinerary combination. For each current property-itinerary combination, the search system determines a utility value based on the expected update frequency and expected impression weight to satisfy bandwidth constraints for each partner system. The search system schedules, for each partner system, queries for property-itinerary combinations having values greater than threshold utility value.
-