US 11,921,609 B2
Data anomaly detection
Roman Batoukov, Redmond, WA (US); Richard Wydrowski, Bellevue, WA (US); Sai Sankalp Arrabolu, Kirkland, WA (US); Zeqiang Wang, Redmond, WA (US); Lech Gudalewicz, Sammamish, WA (US); Keiji Kanazawa, Seattle, WA (US); Benjamin J. Lofton, Seattle, WA (US); Thomas W. Potthast, Sammamish, WA (US); Suren Aghajanyan, Bellevue, WA (US); Khoa Tran, Redmond, WA (US); and Jian Zhang, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC., Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 13, 2022, as Appl. No. 17/744,620.
Prior Publication US 2022/0269908 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 3/04855 (2022.01); G06F 9/54 (2006.01); G06F 11/07 (2006.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)
CPC G06F 11/3447 (2013.01) [G06F 3/04855 (2013.01); G06F 9/542 (2013.01); G06F 11/0709 (2013.01); G06F 11/0781 (2013.01); G06F 11/0793 (2013.01); G06F 18/2148 (2023.01); G06F 18/2178 (2023.01); G06N 20/00 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A system comprising:
a memory area associated with a computing device, the memory area storing a plurality of anomaly detection algorithms and including computer-executable instructions; and
a processor that executes the computer-executable instructions to:
select an anomaly detection algorithm from the plurality of the anomaly detection algorithms based on a type of workload, and process data with the selected anomaly detection algorithm to detect an anomaly;
calibrate the selected anomaly detection algorithm based at least in part on user feedback; and
receive a user input, from a single slider element, to adjust an alert setting for the plurality of anomaly detection algorithms.