ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,554,753, issued on Feb. 17, was assigned to MICROSOFT TECHNOLOGY LICENSING LLC (Redmond, Wash.).

"Technical data enrichment through language models" was invented by Andy Daniel Martinez (Pembroke Pines, Fla.), Pramod Kumar Sharma (Seattle), Zhihui Guo (Redmond, Wash.) and Liang Du (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure provides a mechanism for the enrichment of sparse datasets using language models. By training language models on the specific distribution of known values in a dataset, missing values can be predicted, and the predicted values added, thereby resulting in a more complete dataset. This method also fac...