请教字符串相似度的算法

[yinhongyan]

请问哪位有成熟的字符串相似度的算法和代码

[treeroot]

public class Distance {

//****************************
// Get minimum of three values
//****************************

private int Minimum (int a, int b, int c) {
int mi;

mi = a;
if (b < mi) {
mi = b;
}
if (c < mi) {
mi = c;
}
return mi;

}

//*****************************
// Compute Levenshtein distance
//*****************************

public int LD (String s, String t) {
int d[][]; // matrix
int n; // length of s
int m; // length of t
int i; // iterates through s
int j; // iterates through t
char s_i; // ith character of s
char t_j; // jth character of t
int cost; // cost

// Step 1

n = s.length ();
m = t.length ();
if (n == 0) {
return m;
}
if (m == 0) {
return n;
}
d = new int[n+1][m+1];

// Step 2

for (i = 0; i <= n; i++) {
d[i][0] = i;
}

for (j = 0; j <= m; j++) {
d[0][j] = j;
}

// Step 3

for (i = 1; i <= n; i++) {

s_i = s.charAt (i - 1);

// Step 4

for (j = 1; j <= m; j++) {

t_j = t.charAt (j - 1);

// Step 5

if (s_i == t_j) {
cost = 0;
}
else {
cost = 1;
}

// Step 6

d[i][j] = Minimum (d[i-1][j]+1, d[i][j-1]+1, d[i-1][j-1] + cost);

}

}

// Step 7

return d[n][m];

}

}

[boylez]

hash

[超级大笨狼]

--CSDN超级大笨狼。





CREATE function get_semblance_By_2words
(
@word1 varchar(50),
@word2 varchar(50)
)
returns nvarchar(4000)
as
begin
declare @re int
declare @maxLenth int
declare @i int,@l int
declare @tb1 table(child varchar(50))
declare @tb2 table(child varchar(50))
set @i=1
set @l=2
set @maxLenth=len(@word1)
if len(@word1)<len(@word2)
begin
set @maxLenth=len(@word2)
end
while @l<=len(@word1)
begin
while @i<len(@word1)-1
begin
insert @tb1 (child) values( SUBSTRING(@word1,@i,@l) )
set @i=@i+1
end
set @i=1
set @l=@l+1
end


set @i=1
set @l=2


while @l<=len(@word2)
begin
while @i<len(@word2)-1
begin
insert @tb2 (child) values( SUBSTRING(@word2,@i,@l) )
set @i=@i+1
end
set @i=1
set @l=@l+1
end

select @re=isnull(max( len(a.child)*100/ @maxLenth ) ,0) from @tb1 a, @tb2 b where a.child=b.child
return @re
end








GO

--测试
--select dbo.get_semblance_By_2words('我是谁','我是谁啊')
--75
--相似度