nlp实现备注name提取

如何进行name提取？

name提取即为在一段短文本中进行name，即词性为nr的提取，我们采用hanlp进行的nlp分词，如果短文本中没有nr词性即利用n词性进行填充
import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.seg.NShort.NShortSegment;
import com.hankcs.hanlp.seg.Segment;
import com.hankcs.hanlp.seg.Viterbi.ViterbiSegment;
import com.hankcs.hanlp.seg.common.Term;

public static String nameextract(String str) {
List list1 = new ArrayList<>();
List list2 = new ArrayList<>();
// HanLP.Config.IOAdapter = new HadoopFileIoAdapter();

    Segment segment = HanLP.newSegment()
            .enableNameRecognize(true).
                    enableCustomDictionary(true);
    Segment nShortSegment = new NShortSegment().
            enableCustomDictionary(true)
            .enablePlaceRecognize(true)
            .enableOrganizationRecognize(true);
    Segment shortestSegment = new ViterbiSegment()
            .enableCustomDictionary(true)
            .enablePlaceRecognize(true)
            .enableOrganizationRecognize(true);
    String[] strlist = str.split(",");
    for (String str1 : strlist) {
        if (str1.length() < 3) {
            list1.add(str1);
        } else {
            List<Term> termList =
                    segment.seg(str1);
            List<Term> termList1 =
                    nShortSegment.seg(str1);
            List<Term> termList2 =
                    shortestSegment.seg(str1);
            /**
             * 设定返回字段，如果常规分词检测不到人名字段，转到n-最短路径分词，再转到Viterbi分词
             * 如果三个分词均为检测到，分词标准降为名词，依次进行上述三种分词
             */
            for (Term aTermList : termList)
                if (aTermList.nature.toString().contains("nr")) {
                    list1.add(aTermList.word);
                    list2.add(aTermList.word);
                }
            if (list2.size() == 0) for (Term aTermList : termList1)
                if (aTermList.nature.toString().contains("nr")) {
                    list1.add(aTermList.word);
                    list2.add(aTermList.word);

                }
            if (list2.size() == 0) {
                for (Term aTermList : termList2)
                    if (aTermList.nature.toString().contains("nr")) {
                        list1.add(aTermList.word);
                        list2.add(aTermList.word);
                    }
            }
            if (list2.size() == 0) {
                for (Term aTermList : termList)
                    if (aTermList.nature.toString().contains("n")) {
                        list1.add(aTermList.word);
                        list2.add(aTermList.word);
                        break;
                    }
                if (list2.size() == 0)
                    for (Term aTermList : termList1)
                        if (aTermList.nature.toString().contains("n")) {
                            list1.add(aTermList.word);
                            list2.add(aTermList.word);
                            break;
                        }

                if (list2.size() == 0) {
                    for (Term aTermList : termList2)
                        if (aTermList.nature.toString().contains("n")) {
                            list1.add(aTermList.word);
                            list2.add(aTermList.word);
                            break;
                        }
                }
            }
            list2.clear();
        }
    }
    return list1.toString().replace("[", "").replace("]", "");
}
public static void main(String[] args){
Sysout.print.out(nameextract("小红第一次写文章"))
}