Systems and methods for end-to-end automation of network infrastructure development changes

A computer program product for end-to-end automation of network infrastructure development changes, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to:

• collect and archive data comprising feature logs, resource logs, and events in a central historical data storage;
• normalize the data and correlate events to specific features, wherein correlating events to specific features comprises locating differences in pre and post-deployment feature performance, including resource utilization, and maintaining a history of the data in the central historical data storage;
• train an artificial intelligence (AI) model to further analyze the feature logs and compare the feature logs to pre-deployment performance to check overall impact on a production server resource utilization;
• predict an impact based on historical data and assign a probability rating of an incident based on AI model analysis;
• employ a virtual assistant to receive continuous feedback from a deployment and update records upon a deployment confirmation;
• and
• track, via a data monitor, an information technology service management (ITSM) queue and sync the ITSM queue with a development operations (DevOps) queue, informing a DevOps team for the probability rating of the incident;
• wherein the code further causes the apparatus to:
• employ a robotic process automation (RPA) model for the steps of identification, analysis, design, development, testing, and implementation and automate an end-to-end process.

A method for end-to-end automation of network infrastructure development changes, the method comprising:

• collecting and archive data comprising feature logs, resource logs, and events in a central historical data storage;
• normalizing the data and correlate events to specific features, wherein correlating events to specific features comprises locating differences in pre and post-deployment feature performance, including resource utilization, and maintaining a history of the data in the central historical data storage;
• training an artificial intelligence (AI) model to further analyze the feature logs and compare the feature logs to pre-deployment performance to check overall impact on a production server resource utilization;
• predicting an impact based on historical data and assign a probability rating of an incident based on AI model analysis;
• employing a virtual assistant to receive continuous feedback from a deployment and update records upon a deployment confirmation;
• tracking, via a data monitor, an information technology service management (ITSM) queue and sync the ITSM queue with a development operations (DevOps) queue, informing a DevOps team for the probability rating of the incident;
• and
• employing a robotic process automation (RPA) model for the steps of identification, analysis, design, development, testing, and implementation and automate an end-to-end process.