2017年只剩下10天了。 小帅丶 7叔再来一篇NLP的示例代码

示例代码地址:https://gitee.com/xshuai/ai/tree/master/AIDemo/src/main/java/com/xs/nlp

• 官网接口文档:http://ai.baidu.com/docs#/NLP-API/top
• 准备工作 已经创建了语言处理基础技术应用并且拿到apikey sercetkey得到AccessToken
• 接口地址:https://aip.baidubce.com/rpc/2.0/nlp/v1/lexer

***************************提供分词、词性标注、专名识别***************************

• 词法分析接口-Java-API示例代码

参数格式是JSON格式的字符串哦。

package com.xs.nlp;

import java.util.List;
import com.alibaba.fastjson.JSON;
import com.xs.common.APIContants;
import com.xs.pojo.nlp.LexerAnalysisBean;
import com.xs.pojo.nlp.LexerAnalysisBean.Items;
import com.xs.util.baidu.HttpUtil;
/**
 * 自然语言处理-词法分析
 * @author 小帅丶
 *
 */
public class LexerAnalysis {
	/**
	 * 词法分析接口地址
	 */
	public static String LEXERANALYSIS_URL = "https://aip.baidubce.com/rpc/2.0/nlp/v1/lexer";
	public static void main(String[] args) throws Exception {
		//输出字符串内容
//		String result = getLexerAnalysisResult("百度是一家互联网公司", "自己的token");
//		System.out.println(result);
		LexerAnalysisBean lexerAnalysisBean = getLexerAnalysisBean("百度是一家互联网公司","自己的token");
		List items = lexerAnalysisBean.getItems();
		for (int i = 0; i < items.size(); i++) {
			//输出Items对象中basic_words内容
			System.out.println(items.get(i).getBasic_words());
		}
	}
	/**
	 * 词法分析接口
	 * @param text
	 * @param accessToken
	 * @return data
	 * @throws Exception
	 */
	public static String getLexerAnalysisResult(String text,String accessToken) throws Exception {
		String url_param = "?access_token="+accessToken;
		String url = LEXERANALYSIS_URL+url_param;	
		String param = "{\"text\":\""+text+"\"}";
		String data = HttpUtil.postNLP(url, param);
		return data;
	}
	/**
	 * 词法分析接口
	 * @param text
	 * @param accessToken
	 * @return data
	 * @throws Exception
	 */
	public static LexerAnalysisBean getLexerAnalysisBean(String text,String accessToken) throws Exception {
		String url_param = "?access_token="+accessToken;
		String url = LEXERANALYSIS_URL+url_param;	
		String param = "{\"text\":\""+text+"\"}";
		String data = HttpUtil.postNLP(url, param);
		LexerAnalysisBean lexerAnalysisBean = JSON.parseObject(data,LexerAnalysisBean.class);
		return lexerAnalysisBean;
	}
}

• 返回结果内容:

{
    "log_id": 2621974962532031000, 
    "text": "百度是一家互联网公司", 
    "items": [
        {
            "loc_details": [ ], 
            "byte_offset": 0, 
            "uri": "", 
            "pos": "", 
            "ne": "ORG", 
            "item": "百度", 
            "basic_words": [
                "百度"
            ], 
            "byte_length": 4, 
            "formal": ""
        }, 
        {
            "loc_details": [ ], 
            "byte_offset": 4, 
            "uri": "", 
            "pos": "v", 
            "ne": "", 
            "item": "是", 
            "basic_words": [
                "是"
            ], 
            "byte_length": 2, 
            "formal": ""
        }, 
        {
            "loc_details": [ ], 
            "byte_offset": 6, 
            "uri": "", 
            "pos": "m", 
            "ne": "", 
            "item": "一家", 
            "basic_words": [
                "一", 
                "家"
            ], 
            "byte_length": 4, 
            "formal": ""
        }, 
        {
            "loc_details": [ ], 
            "byte_offset": 10, 
            "uri": "", 
            "pos": "n", 
            "ne": "", 
            "item": "互联网", 
            "basic_words": [
                "互联", 
                "网"
            ], 
            "byte_length": 6, 
            "formal": ""
        }, 
        {
            "loc_details": [ ], 
            "byte_offset": 16, 
            "uri": "", 
            "pos": "n", 
            "ne": "", 
            "item": "公司", 
            "basic_words": [
                "公司"
            ], 
            "byte_length": 4, 
            "formal": ""
        }
    ]
}

• 所用到的postNLP方法

需要注意GBK编码。文档要求是GBK哦。不过也支持UTF-8 只需要在接口地址增加charset=UTF-8 注意大小写敏感

/**
     * NLP接口HTTP请求方法
     * @param requestUrl
     * @param params
     * @return
     * @throws Exception
     */
    public static String postNLP(String requestUrl,String params) throws Exception {
    	String encoding = "";
    	if(requestUrl.contains("nlp")){
    		encoding = "GBK";
    	}else{
    		encoding = "UTF-8";
    	}
        String generalUrl = requestUrl;
        URL url = new URL(generalUrl);
        // 打开和URL之间的连接
        HttpURLConnection connection = (HttpURLConnection) url.openConnection();
        connection.setRequestMethod("POST");
        // 设置通用的请求属性
        connection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
        connection.setRequestProperty("Connection", "Keep-Alive");
        connection.setUseCaches(false);
        connection.setDoOutput(true);
        connection.setDoInput(true);
        // 得到请求的输出流对象
        DataOutputStream out = new DataOutputStream(connection.getOutputStream());
        out.write(params.getBytes(encoding));
        out.flush();
        out.close();
        // 建立实际的连接
        connection.connect();
        // 获取所有响应头字段
        Map> headers = connection.getHeaderFields();
        // 遍历所有的响应头字段
        for (String key : headers.keySet()) {
            System.out.println(key + "--->" + headers.get(key));
        }
        // 定义 BufferedReader输入流来读取URL的响应
        BufferedReader in = null;
        if (requestUrl.contains("nlp"))
            in = new BufferedReader(new InputStreamReader(connection.getInputStream(), "GBK"));
        else
            in = new BufferedReader(new InputStreamReader(connection.getInputStream(), "UTF-8"));
        String result = "";
        String getLine;
        while ((getLine = in.readLine()) != null) {
            result += getLine;
        }
        in.close();
        System.out.println("result:" + result);
        return result;
    }

• 所用到的JavaBean对象

package com.xs.pojo.nlp;

import java.util.List;
/**
 * NLP对象
 * @author 小帅丶
 * 2017年12月20日
 */
public class LexerAnalysisBean {
	    private long log_id;
	    private String text;
	    private List items;
	    
	    public long getLog_id() {
			return log_id;
		}
		public void setLog_id(long log_id) {
			this.log_id = log_id;
		}
		public String getText() {
			return text;
		}
		public void setText(String text) {
			this.text = text;
		}
		public List getItems() {
			return items;
		}
		public void setItems(List items) {
			this.items = items;
		}

		public static class Items{
	    	private List loc_details;
    	    private int byte_offset;
    	    private String uri;
    	    private String pos;
    	    private String ne;
    	    private String item;
    	    private List basic_words;
    	    private int byte_length;
    	    private String formal;
			public List getLoc_details() {
				return loc_details;
			}
			public void setLoc_details(List loc_details) {
				this.loc_details = loc_details;
			}
			public int getByte_offset() {
				return byte_offset;
			}
			public void setByte_offset(int byte_offset) {
				this.byte_offset = byte_offset;
			}
			public String getUri() {
				return uri;
			}
			public void setUri(String uri) {
				this.uri = uri;
			}
			public String getPos() {
				return pos;
			}
			public void setPos(String pos) {
				this.pos = pos;
			}
			public String getNe() {
				return ne;
			}
			public void setNe(String ne) {
				this.ne = ne;
			}
			public String getItem() {
				return item;
			}
			public void setItem(String item) {
				this.item = item;
			}
			public List getBasic_words() {
				return basic_words;
			}
			public void setBasic_words(List basic_words) {
				this.basic_words = basic_words;
			}
			public int getByte_length() {
				return byte_length;
			}
			public void setByte_length(int byte_length) {
				this.byte_length = byte_length;
			}
			public String getFormal() {
				return formal;
			}
			public void setFormal(String formal) {
				this.formal = formal;
			}
	    }
}

以上就是示例代码所有内容。

小程序增加了食材识别的功能。您体验了吗？