US 12,131,142 B2
Artificial intelligence driven configuration management
Dustin Garvey, Exeter, NH (US); Amit Ganesh, San Jose, CA (US); Uri Shaft, Fremont, CA (US); Prasad Ravuri, San Jose, CA (US); Long Yang, Redwood City, CA (US); Sampanna Shahaji Salunke, Dublin, CA (US); Sumathi Gopalakrishnan, Fremont, CA (US); Timothy Mark Frazier, Livermore, CA (US); and Shriram Krishnan, Oakland, CA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on May 27, 2021, as Appl. No. 17/332,649.
Application 17/332,649 is a continuation of application No. 16/854,635, filed on Apr. 21, 2020, granted, now 11,023,221.
Application 16/854,635 is a continuation of application No. 16/042,971, filed on Jul. 23, 2018, granted, now 10,664,264, issued on May 26, 2020.
Claims priority of provisional application 62/566,235, filed on Sep. 29, 2017.
Prior Publication US 2021/0286611 A1, Sep. 16, 2021
Int. Cl. G06F 8/65 (2018.01); G06F 8/60 (2018.01); G06F 8/61 (2018.01); G06F 9/50 (2006.01); G06F 16/906 (2019.01); G06N 5/022 (2023.01); G06N 20/00 (2019.01)
CPC G06F 8/65 (2013.01) [G06F 8/60 (2013.01); G06F 8/61 (2013.01); G06F 9/5055 (2013.01); G06F 16/906 (2019.01); G06N 20/00 (2019.01); G06N 5/022 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
applying a machine learning model that generates a set of clusters for target resources in a cloud environment, wherein applying the machine learning model includes selecting, by the machine learning model based on learned patterns in deployments of the target resources, a set of configuration parameters to drive clustering of the target resources in the cloud environment;
identifying for a particular cluster in the set of clusters, based on varying configuration settings of at least a subset of the configuration parameters for target resources in the cloud environment assigned to the particular cluster, a representative node that represents a set of recommended configuration settings for target resources assigned to the particular cluster, wherein the representative node is identified by excluding at least one configuration parameter from the subset of configuration parameters and averaging values for at least the subset of the configuration parameters; and
configuring, in the cloud environment, at least one target resource assigned to the particular cluster to match the set of recommended configuration settings.