US Patent Issued to MICROSOFT TECHNOLOGY LICENSING on Oct. 7 for "Adapting learned cardinality estimators to data and workload drifts" (Washington Inventors)

ALEXANDRIA, Va., Oct. 8 -- United States Patent no. 12,437,522, issued on Oct. 7, was assigned to MICROSOFT TECHNOLOGY LICENSING LLC (Redmond, Wash.).

"Adapting learned cardinality estimators to data and workload drifts" was invented by Yao Lu (Redmond, Wash.), Srikanth Kandula (Redmond, Wash.) and Beibin Li (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method of updating a trained cardinality estimation model includes receiving a cardinality estimation model with cardinality labels and detecting a drift in underlying data or predicates of the cardinality estimation model. The type of the detected drift is determined and new test queries that mimic test queries for the detected drift are s...