计算字符串相似度及寻找最相似字符串的代码

最新推荐文章于 2021-09-03 17:39:37 发布

转载最新推荐文章于 2021-09-03 17:39:37 发布 · 83 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/phcis/archive/2011/06/30/2094111.html

本文介绍了计算两个字符串差异距离及相似度的方法，并通过实例演示了应用过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

计算两个字符串的差异距离函数

/// <summary>
/// 计算两个字符串的差异距离
/// </summary>
/// <param name="source">来源字符串</param>
/// <param name="target">目标字符串</param>
/// <returns>字符串差距</returns>
public int CalcDistance(string source, string target)
{
int n = source.Length;
int m = target.Length;
if (m == 0) return n;
if (n == 0) return m;
var matrix = new int[n + 1, m + 1];
for (int i = 1; i <= n; i++)
{
matrix[i, 0] = i;
}
for (int i = 1; i <= m; i++)
{
matrix[0, i] = i;
}

for (int i = 1; i <= n; i++)
{
var si = source[i - 1];
for (int j = 1; j <= m; j++)
{
var tj = target[j - 1];

int cost;
if (si == tj)
cost = 0;
else
cost = 1;

int above = matrix[i - 1, j] + 1;
int left = matrix[i, j - 1] + 1;
int diag = matrix[i - 1, j - 1] + cost;
matrix[i, j] = Math.Min(above, Math.Min(left, diag));
}
}
return matrix[n, m];
}

计算两个字符串的相似度

/// <summary>
/// 计算两个字符串的相似度
/// </summary>
/// <param name="source">来源字符串</param>
/// <param name="target">目标字符串</param>
/// <returns>相似度</returns>
public double CalcSimilarity(string source, string target)
{
int n = source.Length;
int m = target.Length;
if (n == 0 || m == 0)
return 0;
int distance = CalcDistance(source, target);
int max = Math.Max(n, m);
return 1.0 * (max - distance) / max;
}

demo:

List<string> lvArea = new List<string>();
lvArea.Add("北京电信一区");
lvArea.Add("广东一区");
lvArea.Add("北京网通二区");
lvArea.Add("北京网通一区");

decimal lvSmall = 100;
string lvRes = "";
foreach (string item in lvArea)
{
decimal lvTemp = CalcDistance("北京网通二区", item);
if (lvTemp < lvSmall)
{
lvSmall = lvTemp;
lvRes = item;
}

}
MessageBox.Show(lvRes);

转载于:https://www.cnblogs.com/phcis/archive/2011/06/30/2094111.html