US 10,893,064 B2
Identifying service issues by analyzing anomalies
Vinod Mukundan Menon, Bothell, WA (US); Rahul Nigam, Bothell, WA (US); Mark Gilbert, Issaquah, WA (US); and Srigopal Chitrapu, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Apr. 24, 2019, as Appl. No. 16/393,343.
Prior Publication US 2020/0344252 A1, Oct. 29, 2020
Int. Cl. G06F 16/906 (2019.01); G06N 20/00 (2019.01); H04L 29/06 (2006.01); G06F 16/2457 (2019.01)
CPC H04L 63/1425 (2013.01) [G06F 16/24578 (2019.01); G06F 16/906 (2019.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
1. A data processing system comprising:
a processor; and
a memory in communication with the processor, the memory storing instructions that when executed by the processor, cause the processor to perform functions of:
collecting data from a computing environment via a network, the data including telemetry data and change event data;
inputting the telemetry data into a first machine-learning (ML) model to identify a plurality of anomalies in the computing environment based at least in part on the telemetry data;
obtaining the identified plurality of anomalies as an output from the first ML model;
grouping the plurality of anomalies into one or more clusters;
classifying each of the one or more clusters based on a plurality of dimensions, the plurality of dimensions being determined by a second ML model,
assigning a weight to each dimension of the plurality of dimensions for each of the one or more clusters;
aggregating the weights assigned to each dimension to calculate a score for each of the one or more clusters;
generating a ranking for each of the one or more clusters based in part on the calculated score;
based on the ranking, identifying at Last one of the one or more clusters as an error requiring attention; and
transmitting data relating to the at least one of the one or more clusters for notifying a user,
wherein the plurality of dimensions includes a dimension for change events.