Provided is a process, including: obtaining a first training dataset, training a first machine
learning model on the first training dataset, obtaining a set of candidate question sequences …

Provided is process, including: obtaining interaction-event records; determining, based on at
least some of the interac tion-event records, sets of event-risk scores, wherein: at least some …

US11567914B2 - Framework and method for the automated determination of classes and
anomaly detection methods for time series - Google Patents US11567914B2 - Framework and …

Techniques are disclosed to predict experience degradation in a microservice-based
application comprising a plurality of microservices. Quality of service metrics are derived for …

Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt
statistical properties of count data in a novel algorithm to uncover records exhibiting high risk …

US11641665B2 - Resource utilization retrieval and modification - Google Patents US11641665B2
- Resource utilization retrieval and modification - Google Patents Resource utilization retrieval …

GOON 5/04(2006.01) GO6N 20/00(2019.01) GOOF 16/20(2019.01) GOOF 11/22(2006.01)
G06F 11/26(2006.01) GOOF 11/34(2006.01) G05B 23/02(2006.01) H04L …

US11610580B2 - System and method for determining reasons for anomalies using cross
entropy ranking of textual items - Google Patents US11610580B2 - System and method for …

US11630822B2 - Multiple devices for updating repositories - Google Patents
US11630822B2 - Multiple devices for updating repositories - Google Patents Multiple …

Anomaly detection tools can provide information (eg, graphs, charts, tables, etc.) related to
performance metrics for various Information Technology (IT) infrastructure assets such as …