US 12,093,255 B2
System and method for machine learning for system deployments without performance regressions
Irene Rogan Shaffer, Cambridge, MA (US); Remmelt Herbert Lieve Ammerlaan, Cambridge, MA (US); Gilbert Antonius, Cambridge, MA (US); Marc T. Friedman, Seattle, WA (US); Abhishek Roy, Bellevue, WA (US); Lucas Rosenblatt, Somerville, MA (US); Vijay Kumar Ramani, Boston, MA (US); Shi Qiao, Mercer Island, WA (US); Alekh Jindal, Sammamish, WA (US); Peter Orenberg, Braintree, MA (US); H M Sajjad Hossain, Waltham, MA (US); Soundararajan Srinivasan, Cambridge, MA (US); Hiren Shantilal Patel, Bothell, WA (US); and Markus Weimer, Kirkland, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 30, 2023, as Appl. No. 18/345,789.
Application 18/345,789 is a continuation of application No. 16/840,205, filed on Apr. 3, 2020, granted, now 11,748,350.
Claims priority of provisional application 62/979,808, filed on Feb. 21, 2020.
Prior Publication US 2023/0342359 A1, Oct. 26, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 16/2453 (2019.01); G06F 16/901 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/24542 (2019.01) [G06F 11/3466 (2013.01); G06F 16/9024 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
selecting a first subset of query sets from a plurality of query sets based on a difference, determined by a difference model, in a performance metric between a default query model and an optimized query model corresponding to each query set of the plurality of query sets;
retraining, based on execution data generated by executing the first subset of query sets, the difference model to generate a retrained difference model; and
deploying, to a query optimizer, optimized query models corresponding to a second subset of query sets selected, from the first subset, based on updated performance metric differences determined by the retrained difference model.