在深入探究之前，您需要了解以下术语：
内容项（也称为文档）
系统推荐的实体。在 Google Play 商店中，相应内容是指要安装的应用。对于 YouTube，内容为视频。
查询（也称为“上下文”）
系统用于提供建议的信息。查询可以是以下项的组合：
- 用户信息
- 用户的 ID
- 用户之前互动过的商品
- 其他背景信息
- 时段
- 用户的设备
嵌入
从离散集（在此示例中为查询集或推荐项集）到矢量空间（称为嵌入空间）的映射。许多推荐系统依赖于了解查询和推荐项的适当嵌入表示法。
术语
如未另行说明，那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可，并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情，请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC)：2022-09-27。
[null,null,["最后更新时间 (UTC)：2022-09-27。"],[[["\u003cp\u003eRecommendation systems predict user preferences by suggesting relevant items like apps or videos.\u003c/p\u003e\n"],["\u003cp\u003eThese systems leverage user data, including past interactions and contextual information, to personalize recommendations.\u003c/p\u003e\n"],["\u003cp\u003eEmbeddings are mathematical representations of queries and items, enabling the system to identify similarities and make predictions.\u003c/p\u003e\n"]]],[],null,["# Terminology\n\n\u003cbr /\u003e\n\nBefore we dive in, there are a few terms that you should know:\n\n### Items (also known as documents)\n\nThe entities a system recommends. For the Google Play store, the items are apps\nto install. For YouTube, the items are videos.\n\n### Query (also known as context)\n\nThe information a system uses to make recommendations. Queries can be a\ncombination of the following:\n\n- user information\n - the id of the user\n - items that users previously interacted with\n- additional context\n - time of day\n - the user's device\n\n### Embedding\n\nA mapping from a discrete set (in this case, the set of queries, or the set of\nitems to recommend) to a vector space called the embedding space. Many\nrecommendation systems rely on learning an appropriate\n[embedding](/machine-learning/glossary#embeddings) representation of\nthe queries and items."]]