C#中文文本匹配,字符串匹配,中文词语匹配,计算2个句子相似度

C#中文文本匹配,字符串匹配,中文词语匹配,计算2个句子相似度

 向量在数学上余弦定义如下:
  (https://img-blog.csdnimg.cn/67190e6263ad4acab813496d6de2be18.webp?x-oss-process=image/watermark,type_d3F5LXplbmhlaQ,shadow_50,text_Q1NETiBA5p2O55qT6ZyG,size_20,color_FFFFFF,t_70,g_se,x_16#pic_center)
  因此我们可以将句子向量话计算句子的余弦相似度。
Public static void Main()
{
   
   
var segmenter = new  JiebaSegmenter();
var douba = ClassSim.MatchKeywordSim("123", "145");
Console.WriteLine("【相似度1】:{0}", douba);
var douba1 = ClassSim.MatchKeywordSim("包皮手术治疗费用怎么治疗?", "包皮手术费用");
Console.WriteLine("【相似度1】:{0}", douba1)
namespace ServiceRanking { /// <summary> /// Summary description for TF_IDFLib. /// </summary> public class TFIDFMeasure { private string[] _docs; private string[][] _ngramDoc; private int _numDocs=0; private int _numTerms=0; private ArrayList _terms; private int[][] _termFreq; private float[][] _termWeight; private int[] _maxTermFreq; private int[] _docFreq; public class TermVector { public static float ComputeCosineSimilarity(float[] vector1, float[] vector2) { if (vector1.Length != vector2.Length) throw new Exception("DIFER LENGTH"); float denom=(VectorLength(vector1) * VectorLength(vector2)); if (denom == 0F) return 0F; else return (InnerProduct(vector1, vector2) / denom); } public static float InnerProduct(float[] vector1, float[] vector2) { if (vector1.Length != vector2.Length) throw new Exception("DIFFER LENGTH ARE NOT ALLOWED"); float result=0F; for (int i=0; i < vector1.Length; i++) result += vector1[i] * vector2[i]; return result; } public static float VectorLength(float[] vector) { float sum=0.0F; for (int i=0; i < vector.Length; i++) sum=sum + (vector[i] * vector[i]); return (float)Math.Sqrt(sum); } } private IDictionary _wordsIndex=new Hashtable() ; public TFIDFMeasure(string[] documents) { _docs=documents; _numDocs=documents.Length ; MyInit(); } private void GeneratNgramText() { } private ArrayList GenerateTerms(string[] docs) { ArrayList uniques=new ArrayList() ; _ngramDoc=new string[_numDocs][] ; for (int i=0; i < docs.Length ; i++) { Tokeniser tokenizer=new Tokeniser() ; string[] words=tokenizer.Partition(docs[i]); for (int j=0; j < words.Length ; j++) if (!uniques.Contains(words[j]) ) uniques.Add(words[j]) ; } return uniques; } private static object
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值