US 12,461,784 B2
Cloud data migration using machine learning prediction models
Hemant Chandrakant Patil, Pune (IN); Sarang Padmakar Joshi, Pune (IN); Mihir S. Nanal, Pune (IN); and Pradnya Desai, Mumbai (IN)
Assigned to ACCENTURE GLOBAL SOLUTIONS LIMITED, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Apr. 14, 2023, as Appl. No. 18/300,676.
Prior Publication US 2024/0345887 A1, Oct. 17, 2024
Int. Cl. G06F 9/50 (2006.01)
CPC G06F 9/5038 (2013.01) [G06F 9/5072 (2013.01); G06F 2209/501 (2013.01); G06F 2209/5019 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of managing content during data migration, the method comprising:
receiving, at a prediction machine learning (ML) model, a first dataset including real-time system parameters for a legacy application, the first dataset including tabular data;
determining, at the prediction ML model and based on sampled process times, an estimated time for execution of the data migration of the first dataset;
determining, based on the estimated time and a given checkpoint duration, an estimated number of segments into which the first dataset can be segmented, where a segment refers to a discrete segment of the first dataset expected to migrate during the given checkpoint duration;
determining, based on the number of segments, an estimated segment size for each segment;
determining a degree of data skew for each column;
selecting a first column associated with the smallest data skew as a segmentation column;
automatically generating a code that describes the estimated number of segments, the estimated segment size, and the selected first column; and
executing the data migration of the first dataset based on the generated code.