关于mysql:使用MySQL实现一个简单的推荐算法

举荐算法是会常常遇到的技术。次要解决的是问题是：如果你喜爱书 A，那么你可能会喜爱书 B。

本文咱们应用 MySQL，基于数据统计，拆解实现了一个简略的举荐算法。

首先，创立一个 用户喜爱的书数据表，所示意的是 user\_id 喜爱 book\_id。

CREATE TABLE user_likes (
    user_id INT NOT NULL,
    book_id VARCHAR(10) NOT NULL,
    PRIMARY KEY (user_id,book_id),
    UNIQUE KEY book_id (book_id, user_id)
);

CREATE TABLE user_likes_similar (
    user_id INT NOT NULL,
    liked_user_id INT NOT NULL,
    rank INT NOT NULL,
    KEY book_id (user_id, liked_user_id)
);

插入 4 条测试数据

INSERT INTO user_likes VALUES (1, 'A'), (1, 'B'), (1, 'C');
INSERT INTO user_likes VALUES (2, 'A'), (2, 'B'), (2, 'C'), (2,'D');
INSERT INTO user_likes VALUES (3, 'X'), (3, 'Y'), (3, 'C'), (3,'Z');
INSERT INTO user_likes VALUES (4, 'W'), (4, 'Q'), (4, 'C'), (4,'Z');

代表的含意为：用户 1 喜爱 A、B、C，用户 2 喜爱 A、B、C、D，用户 3 喜爱 X、Y、C、Z，用户 4 喜爱 W、Q、C、Z。

认为用户 1 计算举荐书籍为例，咱们须要计算用户 1 和其余用户的类似度，而后依据类似度排序。

清空类似度数据表

DELETE FROM user_likes_similar WHERE user_id = 1;

计算用户类似度数据表

INSERT INTO user_likes_similar
SELECT 1 AS user_id, similar.user_id AS liked_user_id, COUNT(*) AS rank
    FROM user_likes target
    JOIN user_likes similar ON target.book_id= similar.book_id AND target.user_id != similar.user_id
    WHERE target.user_id = 1
    GROUP BY similar.user_id ;

能够看到查找到的类似度后果为

user_id, liked_user_id, rank
1, 2, 2
1, 3, 1
1, 4, 1

而后依据类似度排序，取前 10 个，就是举荐的书籍了。

SELECT similar.book_id, SUM(user_likes_similar.rank) AS total_rank
    FROM user_likes_similar
    JOIN user_likes similar ON user_likes_similar.liked_user_id = similar.user_id
    LEFT JOIN user_likes target ON target.user_id = 1 AND target.book_id = similar.book_id
    WHERE user_likes_similar.user_id = 1 AND target.book_id IS NULL
    GROUP BY similar.book_id
    ORDER BY total_rank desc
    LIMIT 10;