增加参数实现准确率识别，对应修改处理流程

model/TestResult.txt

@@ -13,13 +13,13 @@
 1.0
 2.0
 2.0
-1.0
 2.0
 2.0
+1.0
 2.0
 2.0
+1.0
 2.0
 2.0
-1.0
 2.0
 2.0

model/model.txt

@@ -2,30 +2,33 @@ svm_type c_svc
 kernel_type rbf
 gamma 0.07142857142857142
 nr_class 2
-total_sv 22
-rho 0.3544510261690456
+total_sv 23
+rho 0.4090245608696046
 label 1 2
-nr_sv 10 12
+probA -1.6128218314376728
+probB 0.14720533163949925
+nr_sv 11 12
 SV
-1.0 9:3.0588936890535687 
-1.0 8:1.5294468445267844 3:0.6609640474436812 
-0.9903141391672972 3:1.3219280948873624 
-1.0 3:1.3219280948873624 
-1.0 3:1.3219280948873624 
-1.0 3:1.3219280948873624 
-1.0 10:3.6438561897747253 
-1.0 8:1.019631229684523 7:1.019631229684523 3:0.44064269829578745 
-1.0 13:1.8219280948873626 9:1.5294468445267844 
-1.0 5:3.6438561897747253 
--0.6700922884685501 14:2.643856189774725 
--0.2563835238113437 11:3.0588936890535687 
+1.0 8:0.979533151778619 7:0.979533151778619 3:0.4005446203898835 
+1.0 13:1.7617809780285065 9:1.4692997276679285 
+0.3704443587292751 3:1.2016338611696504 
+1.0 5:3.523561956057013 
+1.0 3:1.2016338611696504 
+1.0 10:3.523561956057013 
+1.0 3:1.2016338611696504 
+1.0 8:1.4692997276679285 3:0.6008169305848252 
+1.0 3:1.2016338611696504 
+1.0 3:1.2016338611696504 
+1.0 9:2.938599455335857 
+-0.34763255797023584 11:2.938599455335857 
+-1.0 14:1.2617809780285065 12:1.7617809780285065 
+-0.27060537603115437 4:2.523561956057013 
+-0.9876261200717943 11:2.938599455335857 
 -1.0 
--1.0 2:3.6438561897747253 
--0.07237134131172171 4:2.643856189774725 
--1.0 4:1.3219280948873624 7:1.5294468445267844 
--1.0 1:1.8219280948873626 14:1.3219280948873624 
--0.9914669855756817 11:3.0588936890535687 
--1.0 14:1.3219280948873624 12:1.8219280948873626 
+-1.0 1:1.7617809780285065 14:1.2617809780285065 
+-1.0 2:3.523561956057013 
 -1.0 
--1.0 4:2.643856189774725 
--1.0 6:3.6438561897747253 
+-1.0 4:1.2617809780285065 7:1.4692997276679285 
+-0.8144378826386051 14:2.523561956057013 
+-1.0 6:3.523561956057013 
+-0.9501424220174856 4:2.523561956057013 

model/train.txt

-1 9:3.0588936890535687
-1 8:1.5294468445267844 3:0.6609640474436812
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 3:1.3219280948873624
-1 10:3.6438561897747253
-1 8:1.019631229684523 7:1.019631229684523 3:0.44064269829578745
-1 13:1.8219280948873626 9:1.5294468445267844
-1 5:3.6438561897747253
-2 14:2.643856189774725
-2 11:3.0588936890535687
+1 8:0.979533151778619 7:0.979533151778619 3:0.4005446203898835
+1 3:1.2016338611696504
+1 13:1.7617809780285065 9:1.4692997276679285
+1 3:1.2016338611696504
+1 3:1.2016338611696504
+1 5:3.523561956057013
+1 3:1.2016338611696504
+1 10:3.523561956057013
+1 3:1.2016338611696504
+1 8:1.4692997276679285 3:0.6008169305848252
+1 3:1.2016338611696504
+1 3:1.2016338611696504
+1 9:2.938599455335857
+2 11:2.938599455335857
+2 14:1.2617809780285065 12:1.7617809780285065
+2 4:2.523561956057013
+2 11:2.938599455335857
 2
-2 2:3.6438561897747253
-2 4:2.643856189774725
-2 4:1.3219280948873624 7:1.5294468445267844
-2 1:1.8219280948873626 14:1.3219280948873624
-2 11:3.0588936890535687
-2 14:1.3219280948873624 12:1.8219280948873626
+2 1:1.7617809780285065 14:1.2617809780285065
+2 2:3.523561956057013
 2
-2 4:2.643856189774725
-2 6:3.6438561897747253
+2 4:1.2617809780285065 7:1.4692997276679285
+2 14:2.523561956057013
+2 6:3.523561956057013
+2 4:2.523561956057013

src/main/java/com/xoado/domain/service/IdentifyService.java

@@ -105,21 +105,21 @@ public class IdentifyService {
         if(matchedSkills.size()==0){
             matchedSkills = matchSkillByRegex(formattext,matchedSkills);
         }
-        Skill matchedSkill = null;
-        List wordList = WordUtil.getNlpSeg(text);
-        //TODO 匹配到一个的话直接确定意图，否则用模型进行二次识别。识别模型目前必定识别出结果，无概率计算。
-        if((matchedSkills.size()==1)){
-            matchedSkill = matchedSkills.get(0);
-            FakeLog.log("match only one skill:"+matchedSkill.getName() );
-        }else if(matchedSkills.size()>1){
-            String identifyBySVMResult = SVMService.predict(wordList);
-            matchedSkill = StringUtils.isEmpty(identifyBySVMResult)?null:skillList.getSkillByName(identifyBySVMResult);
-        }
-        //直接进行模型测试
 //        Skill matchedSkill = null;
 //        List wordList = WordUtil.getNlpSeg(text);
-//        String identifyBySVMResult = SVMService.predict(wordList);
-//        matchedSkill = StringUtils.isEmpty(identifyBySVMResult)?null:skillList.getSkillByName(identifyBySVMResult);
+//        //TODO 匹配到一个的话直接确定意图，否则用模型进行二次识别。识别模型目前必定识别出结果，无概率计算。
+//        if((matchedSkills.size()==1)){
+//            matchedSkill = matchedSkills.get(0);
+//            FakeLog.log("match only one skill:"+matchedSkill.getName() );
+//        }else if(matchedSkills.size()>1){
+//            String identifyBySVMResult = SVMService.predict(wordList);
+//            matchedSkill = StringUtils.isEmpty(identifyBySVMResult)?null:skillList.getSkillByName(identifyBySVMResult);
+//        }
+        //直接进行模型测试
+        Skill matchedSkill = null;
+        List wordList = WordUtil.getNlpSeg(text);
+        String identifyBySVMResult = SVMService.predict(wordList);
+        matchedSkill = StringUtils.isEmpty(identifyBySVMResult)?null:skillList.getSkillByName(identifyBySVMResult);
 
         if(matchedSkill == null){
             FakeLog.log("无法识别:"+text);

src/main/java/com/xoado/domain/svm/comMain.java

@@ -16,7 +16,7 @@ public class comMain {
 
 // TODO Auto-generated method stub
 
-        String[] arg = { "model\\train.txt", // 存放SVM训练模型用的数据的路径
+        String[] arg = { "-b","1", "model\\train.txt", // 存放SVM训练模型用的数据的路径
 
                 "model\\model.txt" }; // 存放SVM通过训练数据训/ //练出来的模型的路径
 

src/main/java/com/xoado/domain/svm/svm_train.java

@@ -116,13 +116,6 @@ class svm_train {
 
 	public static void main(String argv[]) throws IOException
 	{
-
-		String model_file = argv[0];
-		String output_file = argv[1];
-		argv = new String[4];
-		argv[0] = model_file;
-		argv[1] = output_file;
-
 		svm_train t = new svm_train();
 		t.run(argv);
 	}

src/main/java/org/shirdrn/document/processor/component/DocumentWordsCollector.java

@@ -59,7 +59,7 @@ public class DocumentWordsCollector extends AbstractComponent {
 			int n = 1;
 			for(File file : files) {
 				String doc = file.getAbsolutePath();
-				//遍历文件里的每一行内容
+				//遍历文件里的每一行内容
 				BufferedReader br = null;
 				try {
 					br = new BufferedReader(

src/main/resources/skill.json

@@ -13,8 +13,7 @@
     "keyList": ["吃饭","外卖","科","吃"],
     "regexeList": [
       "^.*(叫|点|吃).*$",
-      "^.*来.*碗.*$",
-      "^.*(科技).*$"
+      "^.*来.*碗.*$"
     ]
   }
 ]
\ No newline at end of file