发明名称 IDENTIFYING SOURCES OF ANOMALIES IN MULTI-VARIABLE METRICS USING LINEARIZATION
摘要 The present disclosure is directed toward systems and methods for identifying contributing factors associated with a multi-variable metric anomaly. One or more embodiments described herein identify one or more contributing factors that led to an anomaly in a multi-variable metric by calculating linearizing weights such that the total deviation in the multi-variable metric can be written as a weighted sum of deviations for dimension elements associated with the multi-variable metric.
申请公布号 US2017111432(A1) 申请公布日期 2017.04.20
申请号 US201514886453 申请日期 2015.10.19
申请人 Adobe Systems Incorporated 发明人 Saini Shiv Kumar;Sinha Ritwik;Rimer Michael;N Anandhavelu
分类号 H04L29/08;G06F11/34;G06Q30/02 主分类号 H04L29/08
代理机构 代理人
主权项 1. In a digital medium environment for digitally collecting and analyzing analytics data of a network application, a method for identifying one or more sources of an anomaly of a use or performance of the network application, comprising: identifying, by one or more processors, an anomaly associated with a multi-variable metric; querying actual values for each of one or more dimension elements in a dimension associated with the multi-variable metric; querying expected values for each of the one or more dimension elements in the dimension associated with the multi-variable metric; calculating, by the one or more processors, a linearizing weight for each of the one or more dimension elements in the dimension associated with the multi-variable metric; determining, by the one or more processors, a weighted deviation for each of the one or more dimension elements in the dimension, by calculating a quantity of the actual value minus the expected value, multiplied by the calculated linearizing weight; and identifying, by the one or more processors, dimension elements based on the determined weighted deviations.
地址 San Jose CA US