发明名称 |
Continuous anomaly detection based on behavior modeling and heterogeneous information analysis |
摘要 |
The present disclosure describes a continuous anomaly detection method and system based on multi-dimensional behavior modeling and heterogeneous information analysis. A method includes collecting data, processing and categorizing a plurality of events, continuously clustering the plurality of events, continuously model building for behavior and information analysis, analyzing behavior and information based on a holistic model, detecting anomalies in the data, displaying an animated and interactive visualization of a behavioral model, and displaying an animated and interactive visualization of the detected anomalies. |
申请公布号 |
US8887286(B2) |
申请公布日期 |
2014.11.11 |
申请号 |
US201314034008 |
申请日期 |
2013.09.23 |
申请人 |
|
发明人 |
Dupont Laurent;Charnock Elizabeth B.;Roberts Steve;Amesefe Eli Yawo;Schon Keith Eric;Oehrle Richard Thomas |
分类号 |
H04L29/06;G06F21/50;G06F21/55;G06F21/00 |
主分类号 |
H04L29/06 |
代理机构 |
Maldjian Law Group LLC |
代理人 |
Maldjian Law Group LLC ;Maldjian John |
主权项 |
1. A data-driven method of continuous anomaly detection based on behavioral modeling and heterogeneous information analysis that does not require definition of a set of rules or definition of anomalous patterns, the method comprising:
collecting heterogeneous, structured and unstructured, text-bearing and non-text-bearing sociological data that includes data on human behavior; processing and categorizing a plurality of events in quasi-real-time; clustering the plurality of events from the sociological data in quasi-real-time; building predictive models of at least one of individual behavior and collective behavior in quasi-real-time for behavior and information analysis; analyzing behavior and information based on a multidimensional, normalcy-based behavioral model; detecting behavioral anomalies in the collected sociological data; displaying an animated and interactive visualization of the multidimensional, normalcy-based behavioral model; and displaying an animated and interactive visualization of the detected behavior-based and time-based anomalies, wherein different types of anomalies are detected based on the results of data analysis and individual and collective behavior modeling, wherein a monitoring or anomaly detection system provides a source of anomalies, wherein baseline patterns are computed with respect to different referentials and used as a source of anomalies corresponding to deviations from the baseline patterns, and wherein rankings of individuals against behavioral traits are a source of anomalies corresponding to abnormal behavior. |
地址 |
|