From dc2075dcf1806b1137ec4f5aba390df65f054985 Mon Sep 17 00:00:00 2001 From: Lv Feng Date: Fri, 14 Oct 2016 19:33:34 +0800 Subject: [PATCH] Update 20160817 Building a Real-Time Recommendation Engine with Data Science.md --- ...lding a Real-Time Recommendation Engine with Data Science.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sources/tech/20160817 Building a Real-Time Recommendation Engine with Data Science.md b/sources/tech/20160817 Building a Real-Time Recommendation Engine with Data Science.md index c52692efa3..8d05028063 100644 --- a/sources/tech/20160817 Building a Real-Time Recommendation Engine with Data Science.md +++ b/sources/tech/20160817 Building a Real-Time Recommendation Engine with Data Science.md @@ -1,3 +1,4 @@ + 用数据科学搭建一个实时推荐引擎 ====================== @@ -32,7 +33,6 @@ Neo4j 已经伴随我两年了，但实际上我已经使用 Neo4j 和 Cypher ![](https://s3.amazonaws.com/dev.assets.neo4j.com/wp-content/uploads/20160816215537/cypher-query-dfw-food-drink-real-time-recommendations-768x364.png) 这将提取出目录中用户所请求的所有地点，终点和出入口。然后我们可以计算出用户所在位置到出入口的准确距离，并以升序返回结果。再次说明，一个非常简单的 Cypher 推荐仅仅依据用户在机场中的位置。 - ### 社会推荐 让我们来看一下社会推荐。在我们的假想应用程序中，用户可以登录并且可以用和 Facebook 类似的方式标记自己“喜爱”的地点，也可以查询登记地点。