Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021061090 - TIME-SERIES ANOMALY DETECTION USING AN INVERTED INDEX

Publication Number WO/2021/061090
Publication Date 01.04.2021
International Application No. PCT/US2019/052437
International Filing Date 23.09.2019
IPC
G06F 11/30 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
30Monitoring
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06Q 10/04 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
G06F 16/20 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
G06F 11/34 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
30Monitoring
34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation
CPC
G06F 11/3072
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
30Monitoring
3065Monitoring arrangements determined by the means or processing involved in reporting the monitored data
3072where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
G06F 11/3452
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
30Monitoring
34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; ; Recording or statistical evaluation of user activity, e.g. usability assessment
3452Performance evaluation by statistical analysis
G06F 2201/835
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2201Indexing scheme relating to error detection, to error correction, and to monitoring
835Timestamp
G06F 2201/86
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2201Indexing scheme relating to error detection, to error correction, and to monitoring
86Event-based monitoring
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06Q 10/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
Applicants
  • GOOGLE LLC [US]/[US]
Inventors
  • TAROPA, Emanuel
  • DENA, Dragos
Agents
  • GROVER, Melanie
  • BELLERMANN, Mark R.W.
  • BENNETT, Daniel M.
  • BRAKE, R. Edward
  • FORD, Timothy D.
  • HUGHES, William G.
  • KEY, Joseph F.
  • SODERBERG, J. Richard
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) TIME-SERIES ANOMALY DETECTION USING AN INVERTED INDEX
(FR) DÉTECTION D'ANOMALIE DE SÉRIES CHRONOLOGIQUES À L'AIDE D'UN INDEX INVERSÉ
Abstract
(EN)
Implementations identify anomalous events from indexed events. An example system receives s dimension(s) for events, a test start time and a test duration defining a test interval. The system may identify a set of events matching the dimension(s). The set includes events occurring within a test interval or within one of at least two reference intervals. The system generates, for the test interval and the reference intervals, an aggregate value for each unique combination of dimension values in the set of events. The system selects at least one of the unique combination of dimension values for anomaly detection based on a comparison of the aggregate values for the reference intervals and the test interval, and performs anomaly detection on a historical time series for the selected unique combination of dimension values. The system may report any of the selected unique combination of dimension values identified as an anomaly.
(FR)
Des modes de réalisation identifient des événements anormaux à partir d'événements indexés. Un système donné à titre d'exemple reçoit s dimension(s) pour des événements, un temps de début de test et une durée de test définissant un intervalle de test. Le système peut identifier un ensemble d'événements correspondant à la ou les dimensions. L'ensemble comprend des événements se produisant dans un intervalle de test ou dans l'un d'au moins deux intervalles de référence. Le système génère, pour l'intervalle de test et les intervalles de référence, une valeur agrégée pour chaque combinaison unique de valeurs de dimension dans l'ensemble d'événements. Le système sélectionne au moins l'une de la combinaison unique de valeurs de dimension pour une détection d'anomalie sur la base d'une comparaison des valeurs agrégées pour les intervalles de référence et l'intervalle de test, et effectue une détection d'anomalie sur une série chronologique historique pour la combinaison unique sélectionnée de valeurs de dimension. Le système peut reporter l'une quelconque de la combinaison unique sélectionnée de valeurs de dimension identifiées comme une anomalie.
Latest bibliographic data on file with the International Bureau