发明名称 Systems and methods for event tracking using time-windowed counters
摘要 Some embodiments include tracking events and classifying assets within a computer system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset can be classified based on comparison of the first signal value and the second signal value. The time series can be based on at least one time window including time intervals. Counters to determine a number of occurrences of an event type can be associated with the time intervals. Each of the counters can be incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
申请公布号 US9558279(B2) 申请公布日期 2017.01.31
申请号 US201514668030 申请日期 2015.03.25
申请人 Facebook, Inc. 发明人 Agashe Bhalchandra Suresh;Shklarski Gil;Stein Christopher Alexander;Tchervenski Nickolay Vladimirov
分类号 G06F15/18;G06F17/30;G06N5/02;G06N99/00;G06Q50/00 主分类号 G06F15/18
代理机构 Perkins Coie LLP 代理人 Perkins Coie LLP
主权项 1. A computer-implemented method, comprising: generating, by a computer system and based on an event log of the computer system, a time series of occurrence counts of an event type in the event log, wherein the time series is associated with at least an asset trackable by the computer system, wherein the time series includes a series of occurrence counts and spans a time window that is divided into time intervals, and the occurrence counts track numeric counts of one or more events of the event type in the event log respectively during the time intervals, wherein the asset is a social network object trackable by a social networking system; wherein generating the time series includes incrementing at least one of the occurrence counts when an instance of the event type involving the asset occurs within a time interval corresponding to the at least one occurrence counter and the instance of the event type has a unique characteristic previously unaccounted for in the time series before the time interval; computing, by the computer system, a first signal value based on a first subset of the time series; computing, by the computer system, a second signal value based on a second subset of the time series, wherein the second subset is different from the first subset; classifying, by the computer system, the asset into a category based on a comparison of the first signal value and the second signal value; and modifying, based on the category, a policy in the computer system for a user account of the social networking system or a social networking service of the computer system to interact with the asset.
地址 Menlo Park CA US