US Patent Issued to GOOGLE on Sept. 15 for "Converting video semantics into language for real-time query and information retrieval" (California Inventor)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,414, issued on Sept. 15, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Converting video semantics into language for real-time query and information retrieval" was invented by Dongeek Shin (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations utilize a LLM to generate content responsive to a user query directed to a video and cause audio data for the generated content to be rendered as a response to the user query. Implementations extract a subset of frames from all frames of the video as key frame(s) for the video, and utilize a vision-language model in generating a natural language description for the key frame(s)...