ChatGPT Java: 기사에서 주요 정보를 자동으로 요약하고 추출하는 방법

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;

public class Summarizer {
    public static String summarize(String text, int numSentences) throws Exception {
        // 创建索引
        Directory directory = new RAMDirectory();
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        IndexWriter writer = new IndexWriter(directory, config);
        
        // 创建文档
        Document doc = new Document();
        doc.add(new TextField("text", text, Field.Store.YES));
        writer.addDocument(doc);
        writer.close();
        
        // 搜索并获取摘要
        IndexSearcher searcher = new IndexSearcher(directory);
        TopDocs topDocs = searcher.search(query, numSentences);
        StringBuilder summary = new StringBuilder();
        for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
            Document summaryDoc = searcher.doc(scoreDoc.doc);
            summary.append(summaryDoc.get("text")).append(" ");
        }
        
        searcher.getIndexReader().close();
        directory.close();
        
        return summary.toString();
    }
}

import edu.stanford.nlp.simple.*;

public class KeywordExtractor {
    public static List<String> extractKeywords(String text, int numKeywords) {
        List<String> keywords = new ArrayList<>();
        Document document = new Document(text);
        
        // 提取名词关键词
        for (Sentence sentence : document.sentences()) {
            for (String word : sentence.words()) {
                if (sentence.posTag(word).startsWith("NN")) {
                    keywords.add(word);
                }
            }
        }
        
        // 统计关键词频率
        Map<String, Integer> freqMap = new HashMap<>();
        for (String keyword : keywords) {
            freqMap.put(keyword, freqMap.getOrDefault(keyword, 0) + 1);
        }
        
        // 按照频率排序
        List<Map.Entry<String, Integer>> sortedList = new ArrayList<>(freqMap.entrySet());
        sortedList.sort(Map.Entry.comparingByValue(Comparator.reverseOrder()));
        
        // 返回前 numKeywords 个关键词
        List<String> topKeywords = new ArrayList<>();
        for (int i = 0; i < Math.min(numKeywords, sortedList.size()); i++) {
            topKeywords.add(sortedList.get(i).getKey());
        }
        
        return topKeywords;
    }
}