ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,770,174, issued on Oct. 20, was assigned to Maplebear Inc. (San Francisco).
"Search relevance model using self-adversarial negative sampling" was invented by Yuqing Xie (Toronto), Taesik Na (Seattle) and Saurav Manchanda (Seattle).
According to the abstract* released by the U.S. Patent & Trademark Office: "To train an embedding-based model to determine relevance between items and queries, an online system generates training data from previously received queries and interactions with results for the queries. The training data includes positive training examples including a query and an item with which a user performed a specific interaction after providing the query. To generate negat...