mysql中如何检测文本的相似性的三种方法

mysql中如何检测文本的相似性，比如标题或文章的相似性

方法有三种

第一种，将文章的标题进行分词，存在一个单独的分词表中，结构如下

好了，接下来我们通过sql来计算每篇文章标题中相似词的个数

select count(*)
from  wordstring
where artcle_id = 2
and word in 
  (select word 
  from wordstring
  where article_id= 1);

第二种，单独写个存储过程

CREATE FUNCTION `wordsimilarity`( s1 text, s2 text) RETURNS int(11)
    DETERMINISTIC
BEGIN 
    DECLARE s1_len, s2_len, i, j, c, c_temp, cost INT; 
    DECLARE s1_char CHAR; 
    DECLARE cv0, cv1 text; 
    SET s1_len = CHAR_LENGTH(s1), s2_len = CHAR_LENGTH(s2), cv1 = 0x00, j = 1, i = 1, c = 0; 
    IF s1 = s2 THEN 
      RETURN 0; 
    ELSEIF s1_len = 0 THEN 
      RETURN s2_len; 
    ELSEIF s2_len = 0 THEN 
      RETURN s1_len; 
    ELSE 
      WHILE j <= s2_len DO 
        SET cv1 = CONCAT(cv1, UNHEX(HEX(j))), j = j + 1; 
      END WHILE; 
      WHILE i <= s1_len DO 
        SET s1_char = SUBSTRING(s1, i, 1), c = i, cv0 = UNHEX(HEX(i)), j = 1; 
        WHILE j <= s2_len DO 
          SET c = c + 1; 
          IF s1_char = SUBSTRING(s2, j, 1) THEN  
            SET cost = 0; ELSE SET cost = 1; 
          END IF; 
          SET c_temp = CONV(HEX(SUBSTRING(cv1, j, 1)), 16, 10) + cost; 
          IF c > c_temp THEN SET c = c_temp; END IF; 
            SET c_temp = CONV(HEX(SUBSTRING(cv1, j+1, 1)), 16, 10) + 1; 
            IF c > c_temp THEN  
              SET c = c_temp;  
            END IF; 
            SET cv0 = CONCAT(cv0, UNHEX(HEX(c))), j = j + 1; 
        END WHILE; 
        SET cv1 = cv0, i = i + 1; 
      END WHILE; 
    END IF; 
    RETURN c; 
  END

CREATE FUNCTION `wordsimilarity_ratio`( s1 text, s2 text ) RETURNS int(11)
    DETERMINISTIC
BEGIN 
    DECLARE s1_len, s2_len, max_len INT; 
    SET s1_len = LENGTH(s1), s2_len = LENGTH(s2); 
    IF s1_len > s2_len THEN  
      SET max_len = s1_len;  
    ELSE  
      SET max_len = s2_len;  
    END IF; 
    RETURN ROUND((1 - wordsimilarity(s1, s2) / max_len) * 100); 
  END

第三种，souddex()

soundex是一个将任何文本串转换为描述其语音表示的字母数字模式的算法。soundex考虑了类似的发音字符和音节，使得对字符串进行发音比较而不是字母比较。虽然，soundex不是SQL概念，但是多数DBMS都提供对soundex的支持。

SELECT *
FROM article
WHERE  soundex(title) = soundex('hello world');