US 12,294,503 B2
Self-learning automated information technology change risk prediction
Arun A. Ayachitula, Dobbs Ferry, NY (US); Rohit Khandekar, Jersey City, NJ (US); and Upendra Sharma, Hartsdale, NY (US)
Assigned to Kyndryl, Inc., New York, NY (US)
Filed by Kyndryl, Inc., New York, NY (US)
Filed on Jun. 8, 2023, as Appl. No. 18/331,361.
Prior Publication US 2024/0414064 A1, Dec. 12, 2024
Int. Cl. H04L 41/16 (2022.01); H04L 41/0604 (2022.01); H04L 41/0866 (2022.01)
CPC H04L 41/16 (2013.01) [H04L 41/0609 (2013.01); H04L 41/0866 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
inputting, by a processor, a change request of a change ticket to a first machine learning model, the first machine learning model determining at least one word pair in the change request, the change request being a modification in an information technology (IT) environment;
classifying, by the processor, the at least one word pair into a change category for the IT environment using a second machine learning model, the change category identifying a type of the modification to be executed in the IT environment to successfully resolve the change request;
determining, by the processor, a likelihood of causing a problem in the IT environment as a result of executing the modification to successfully resolve the change request as requested in the change ticket, wherein the likelihood of causing the problem in the IT environment is associated with a linkage between the change ticket and an incident ticket; and
in response to determining the likelihood of causing the problem in the IT environment as the result of executing the modification to successfully resolve the change request as requested in the change ticket, automatically performing, by the processor, an action to prevent the modification of the change request in the IT environment that is requested in the change ticket.