| CPC G06F 11/1461 (2013.01) [G06F 16/215 (2019.01); G06N 20/00 (2019.01); G06F 2201/84 (2013.01)] | 20 Claims |

|
1. A computer-implemented method of prioritizing backups of container data for a data protection program in an enterprise-scale Kubernetes cluster network, comprising:
deploying a plurality of containers wherein each container is a portable, self-sufficient data structure encapsulating at least one application and operating environment;
implementing a Docker container format and container management layer to automate the deploying step;
defining attributes of each container of the plurality of containers storing the container data, the attributes comprising container size, ownership, creation time, location, applications, datastore size, and provision type;
training a machine learning (ML) model to determine a backup priority of the plurality of containers based on operating parameters, characteristics, and labels of the attributes;
classifying, with respect to the backup priority, each container of the plurality of containers storing the container data, and based on the defined attributes of each container;
generating a priority score for each container based on the classifying;
tagging each container with a priority tag based on the generated priority score, wherein the priority tag is added as payload information to a Kubernetes host payload generated by the data protection program; and
backing up, by the data protection program, the container data in a backup order of the plurality of containers as determined by the priority tag of each container.
|