US Patent Issued to AT&T Intellectual Property I on May 12 for "Using deep learning models to obfuscate and optimize communications" (Texas, Indiana, Wisconsin Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,099, issued on May 12, was assigned to AT&T Intellectual Property I LP (Atlanta).

"Using deep learning models to obfuscate and optimize communications" was invented by William R. Trost (Mequon, Wis.), Daniel Solero (Rockwall, Texas) and Brian Miles (Pittsboro, Ind.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Concepts and technologies are disclosed herein for using deep learning models to obfuscate and optimize communications. A request can be received in a first language, from a user device, and at a first computing device storing a first neural network. The request can be translated using the first neural network into a modified request in a cust...