“全能選手”召回表徵算法實踐

{"type":"doc","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","marks":[{"type":"strong"}],"text":"導讀"},{"type":"text","text":"： 本文主要分享 \"全能選手\" 召回表徵算法實踐。首先簡單介紹下業務背景："}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"網易嚴選人工智能部，主要有三個方向：NLP、搜索推薦、供應鏈，我們主要負責搜索推薦。搜索推薦與營銷端的業務場景密切相關，管理着嚴選最大的流量入口。我們團隊的主要目標是優化轉化率和GMV相關指標，具體業務是搜索、推薦、廣告 ( 包含內部資源位廣告以及外部的DPS廣告 )。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/24\/f9\/2431516eba421ce2a1e60ffc444e4af9.png","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"如圖所示，在這些個性化場景下是我們具備的能力矩陣。剛接到邀請的時候我是想聊一聊在嚴選業務場景下的個性化相關事情，但是我們業務基本都做了2~3年，想在短時間聊完，只能介紹我們做了哪些工作以及取得什麼樣的業務價值。但是每個人的業務場景差異較大，我們這邊最優的實現方案在其他場景可能並不是最優方案，大家聽完之後，可能沒有太大的收穫。與其這樣，還不如聚焦在一個小模塊上詳細聊一下，所以今天就選召回表徵這個部分，也就引出了本次分享主題：\"全能選手\"召回表徵算法實踐，主要內容包括："}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"bulletedlist","content":[{"type":"listitem","attrs":{"listStyle":null},"content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"問題定義：召回表徵究竟是要解決什麼問題"}]}]},{"type":"listitem","attrs":{"listStyle":null},"content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"模型價值：召回表徵的價值或收益是什麼"}]}]},{"type":"listitem","attrs":{"listStyle":null},"content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"迭代實現：一步步迭代演化的過程"}]}]},{"type":"listitem","attrs":{"listStyle":null},"content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"業務落地：業務落地的案例"}]}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":2},"content":[{"type":"text","text":"01 問題定義"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","marks":[{"type":"strong"}],"text":"1. 模型目標"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/c8\/fb\/c8cc4992a6352e7a7178e83e6b1b11fb.png","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}}]}