ALEXANDRIA, Va., March 5 -- United States Patent no. 12,242,982, issued on March 4, was assigned to TAMR INC. (Cambridge, Mass.).

"Method of using clusters to train supervised entity resolution in big data" was invented by George Anwar Dany Beskales (Waltham, Mass.), Pedro Giesemann Cattori (Cambridge, Mass.), Alexandra V. Batchelor (Cambridge, Mass.), Brian A. Long (Somerville, Mass.) and Nikolaus Bates-Haus (Littleton, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Record clustering is performed by learning from verified clusters which are used as the source of training data in a deduplication workflow utilizing supervised machine learning."

The patent was filed on June 25, 2021, under Application N...