ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,530,348, issued on Jan. 20, was assigned to Zoom Communications Inc. (San Jose, Calif.).

"Optimized large language model inference from structured data via intermediate documents" was invented by Shweta Kamble (San Jose, Calif.), Jatinder Kaur (San Jose, Calif.) and Sharad Mathur (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for optimized LLM inference from structured data via intermediate documents ("LLMs") are disclosed. In an example method, a computing device accesses a database including a set of collections. The computing device generates one or more documents based on a first collection of the set of collections. The...