US Patent Issued to Clearview AI on May 27 for "Methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval" (New York Inventor)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,315,220, issued on May 27, was assigned to Clearview AI Inc. (New York).

"Methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval" was invented by Zhi Liu (New York).

According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure provides novel methods and systems for indexing embedding vectors representing disjoint classes at above-billion scale for fast high-recall retrieval. The disclosed methods and systems solved above-billion scale image (e.g., face image) search problems by building a new vector database, the new Nearest Neighbor Database (NNDB) based on a novel architec...