使用前提：服务开通与资源包购买
- 自然语言处理：开通地址
- NLP自学习平台：开通地址
- 自学习平台资源包：购买地址
- 获取阿里云账号的AccessKey ID 和AccessKey Secret
- 授权子账号（无需子账号，可以忽略此步骤）：RAM鉴权
操作步骤：
1.添加pom依赖
<dependency>
<groupId>com.aliyun</groupId>
<artifactId>aliyun-java-sdk-core</artifactId>
<version>4.5.25</version>
</dependency>
<dependency>
<groupId>com.aliyun</groupId>
<artifactId>aliyun-java-sdk-nlp-automl</artifactId>
<version>0.0.5</version>
</dependency>
<dependency>
<groupId>com.aliyun</groupId>
<artifactId>aliyun-java-sdk-alinlp</artifactId>
<version>1.0.16</version>
</dependency>
2.Code Sample
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.exceptions.ClientException;
import com.aliyuncs.nlp_automl.model.v20191111.RunPreTrainServiceRequest;
import com.aliyuncs.nlp_automl.model.v20191111.RunPreTrainServiceResponse;
import com.aliyuncs.profile.DefaultProfile;
import com.google.gson.Gson;
import java.util.HashMap;
import java.util.Map;
//预训练模型 在线客服场景客户咨询解析使用示例
public class Demo3 {
public static void main(String[] args) throws ClientException{
DefaultProfile defaultProfile = DefaultProfile.getProfile("cn-hangzhou","XXXXXXXXXX","XXXXXXXXXX");
IAcsClient client = new DefaultAcsClient(defaultProfile);
Map<String, Object> map = new HashMap<>();
map.put("input", "服务态度不好，你们就是这种服务态度的？");
RunPreTrainServiceRequest request = new RunPreTrainServiceRequest();
request.setServiceName("Dialog-Analysis");
//request.setPredictContent(JSON.toJSONString(map));
request.setPredictContent(new Gson().toJson(map));
RunPreTrainServiceResponse response = client.getAcsResponse(request);
System.out.println(response.getPredictResult());
}
}
3.测试结果
{"sentiment":{"score":1.0,"key":"负"},"emotion":{"score":0.4929790198802948,"key":"抱怨"},"aspectItem":[{"aspectPolarity":"负","terms":[{"aspectTerm":"服务态度","opinionTerm":"不好"}],"positiveProb":0.0,"aspectCategory":"客服-服务","negativeProb":1.0}],"category":{"score":0.45799994468688965,"key":"其他类-其他"},"intent":{"score":0.7565186023712158,"key":"无"}}
更多参考
快速入门-模型服务调用流程
预训练模型使用教程
在线客服场景客户咨询解析
阿里云自然语言处理PHP Core SDK使用Quick Start
