US 12,265,837 B2
Machine learning to emulate software applications
Nirmit V Desai, Yorktown Heights, NY (US); Jae-Wook Ahn, Nanuet, NY (US); Tova Roth, Woodmere, NY (US); Dinesh C. Verma, New Castle, NY (US); Douglas M. Freimuth, New York, NY (US); Seraphin Bernard Calo, Cortlandt Manor, NY (US); Anshu Kak, Englewood Cliffs, NJ (US); Steven A Waite, Racine, WI (US); and Roger Hollander, Austin, TX (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Apr. 18, 2023, as Appl. No. 18/302,237.
Prior Publication US 2024/0354132 A1, Oct. 24, 2024
Int. Cl. G06F 9/455 (2018.01); G06N 3/02 (2006.01); G06N 3/08 (2023.01)
CPC G06F 9/45508 (2013.01) [G06N 3/02 (2013.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for emulating an application, comprising:
generating a log template to match one or more patterns in a set of application logs collected from an original application;
learning semantic state representations for the original application from the log template;
training a classifier to predict a next action template based on a sequence of prior action templates;
training a regressor to generate a parameter value for a template based on a sequence of prior action templates and a particular semantic state of the original application; and
deploying the classifier, the regressor, and the log template to a remote computer system for execution to emulate the original application.