[null,null,["最后更新时间 (UTC):2024-11-11。"],[[["Recommender systems leverage embedding models to identify items similar to a user's preferences or a given item."],["The system finds relevant items by searching for embeddings that are close to the user or item embedding in the embedding space, effectively solving a nearest neighbor problem."],["For large-scale retrieval, efficiency can be improved by precomputing top candidates or using approximate nearest neighbor search techniques like ScaNN."]]],[]]