US 11,740,998 B2
Machine learned decision guidance for alerts originating from monitoring systems
Vidar V. Vikjord, Tromso (NO); and Jan-Ove Karlberg, Tromso (NO)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 17, 2019, as Appl. No. 16/656,414.
Application 16/656,414 is a continuation of application No. 15/495,255, filed on Apr. 24, 2017, granted, now 10,482,000.
Prior Publication US 2020/0050532 A1, Feb. 13, 2020
Int. Cl. G06F 11/00 (2006.01); G06F 11/36 (2006.01); G06N 5/045 (2023.01); G06N 20/00 (2019.01); G06N 7/01 (2023.01)
CPC G06F 11/366 (2013.01) [G06F 11/362 (2013.01); G06N 5/045 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for automatically determining whether a detected issue in a computing system is a bug, comprising:
receiving, in association with a source code test, information about the detected issue;
generating a feature vector for the detected issue based on the information received;
providing the feature vector to an evaluation component, the evaluation component including at least one machine learning model trained to determine whether the feature vector is indicative of a bug of a given type;
determining, at the evaluation component, a probability that feature vector is indicative of the bug of the given type by analyzing the feature vector; and
receiving an output from the evaluation component, the output indicating a probability that the detected issue is a result of a bug of the given type.