private void makeNewTerm() {
Term term = new Term(sb.toString(), offe, tempNature.natureStr, 1);
term.selfScore = score;
term.setNature(tempNature);
if (sb.length() > 3) {
term.setSubTerm(TermUtil.getSubTerm(from, to));
}
TermUtil.termLink(from, term);
TermUtil.termLink(term, to);
TermUtil.insertTerm(terms, term);
TermUtil.parseNature(term);
}
private List<Term> recogntion_() {
Term term = null;
Term tempTerm = null;
List<Term> termList = new ArrayList<Term>();
int beginFreq = 10;
for (int i = 0; i < terms.length; i++) {
term = terms[i];
if (term == null || !term.getTermNatures().personAttr.flag) {
continue;
}
term.score = 0;
term.selfScore = 0;
int freq = 0;
for (int j = 2; j > -1; j--) {
freq = term.getTermNatures().personAttr.getFreq(j, 0);
if ((freq > 10) || (term.getName().length() == 2 && freq > 10)) {
tempTerm = nameFind(i, beginFreq, j);
if (tempTerm != null) {
termList.add(tempTerm);
// 如果是无争议性识别
if (skip) {
for (int j2 = i; j2 < tempTerm.getToValue(); j2++) {
if (terms[j2] != null) {
terms[j2].score = 0;
terms[j2].selfScore = 0;
}
}
i = tempTerm.getToValue() - 1;
break;
}
}
}
}
beginFreq = term.getTermNatures().personAttr.begin + 1;
}
return termList;
}
public void recognition() {
if (branch == null) {
return;
}
int length = terms.length - 1;
Term term = null;
for (int i = 0; i < length; i++) {
if (terms[i] == null) {
continue;
} else {
from = terms[i].getFrom();
terms[i].score = 0;
terms[i].selfScore = 0;
}
branch = branch.getBranch(terms[i].getName());
if (branch == null || branch.getStatus() == 3) {
reset();
continue;
}
offe = i;
// 循环查找添加
term = terms[i];
sb.append(term.getName());
if (branch.getStatus() == 2) {
term.selfScore = branch.getParam().getScore();
}
boolean flag = true;
while (flag) {
term = term.getTo();
branch = branch.getBranch(term.getName());
// 如果没有找到跳出
if (branch == null) {
break;
}
switch (branch.getStatus()) {
case 1:
sb.append(term.getName());
continue;
case 2:
sb.append(term.getName());
score = branch.getParam().getScore();
tempNature = branch.getParam().getNature();
to = term.getTo();
makeNewTerm();
continue;
case 3:
sb.append(term.getName());
score = branch.getParam().getScore();
tempNature = branch.getParam().getNature();
to = term.getTo();
makeNewTerm();
flag = false;
break;
default:
System.out.println("怎么能出现0呢?");
break;
}
}
reset();
}
}
/**
* 人名识别
*
* @param term
* @param offe
* @param freq
*/
private Term nameFind(int offe, int beginFreq, int size) {
// TODO Auto-generated method stub
StringBuilder sb = new StringBuilder();
int undefinite = 0;
skip = false;
PersonNatureAttr pna = null;
int index = 0;
int freq = 0;
double allFreq = 0;
Term term = null;
int i = offe;
for (; i < terms.length; i++) {
// 走到结尾处识别出来一个名字.
if (terms[i] == null) {
continue;
}
term = terms[i];
pna = term.getTermNatures().personAttr;
// 在这个长度的这个位置的词频,如果没有可能就干掉,跳出循环
if ((freq = pna.getFreq(size, index)) == 0) {
return null;
}
if (pna.allFreq > 0) {
undefinite++;
}
sb.append(term.getName());
allFreq += Math.log(term.getTermNatures().allFreq + 1);
allFreq += -Math.log((freq));
index++;
if (index == size + 2) {
break;
}
}
double score = -Math.log(FACTORY[size]);
score += allFreq;
double endFreq = 0;
// 开始寻找结尾词
boolean flag = true;
while (flag) {
i++;
if (i >= terms.length) {
endFreq = 10;
flag = false;
} else if (terms[i] != null) {
int twoWordFreq = NgramLibrary.getTwoWordFreq(term, terms[i]);
if (twoWordFreq > 3) {
return null;
}
endFreq = terms[i].getTermNatures().personAttr.end + 1;
flag = false;
}
}
score -= Math.log(endFreq);
score -= Math.log(beginFreq);
if (score > -3) {
return null;
}
if (allFreq > 0 && undefinite > 0) {
return null;
}
skip = undefinite == 0;
term = new Term(sb.toString(), offe, TermNatures.NR);
term.selfScore = score;
return term;
}
