在线客服场景客户咨询解析

在线客服场景客户咨询解析服务适用于针对电商等行业的客服-消费者在线聊天场景，解析消费者说话内容，得到消费者意图、情感、情绪、关注点、细粒度情感等结果。使用示例如下。

服务开通与资源包购买

预训练模型使用前，请确认是否已经开通了NLP自学习平台服务，开通后可购买优惠资源包。

NLP自学习平台：开通地址

自学习平台资源包：购买地址

Java代码示例

DefaultProfile defaultProfile = DefaultProfile.getProfile("cn-hangzhou","your-access-id-key","your-access-id-secret");
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));
RunPreTrainServiceResponse response = client.getAcsResponse(request);
System.out.println(response.getPredictResult());

Python代码示例

# 安装依赖
pip install aliyun-python-sdk-core
pip install aliyun-python-sdk-nlp-automl

# -*- coding: utf8 -*-
import json
from aliyunsdkcore.client import AcsClient
from aliyunsdkcore.acs_exception.exceptions import ClientException
from aliyunsdkcore.acs_exception.exceptions import ServerException
from aliyunsdknlp_automl.request.v20191111 import RunPreTrainServiceRequest
# Initialize AcsClient instance
client = AcsClient(
  "<your-access-key-id>",
  "<your-access-key-secret>",
  "cn-hangzhou"
);
# 输入还可以包括上文context_above和下文context_below信息，有助于提升算法效果，但也可以省略不写，参考输入示例。
content = {
  "input": "服务态度不好，你们就是这种服务态度的？",
}
# Initialize a request and set parameters
request = RunPreTrainServiceRequest.RunPreTrainServiceRequest()
request.set_ServiceName('Dialog-Analysis')
request.set_PredictContent(json.dumps(content))
# Print response
response = client.do_action_with_exception(request)
resp_obj = json.loads(response)
predict_result = json.loads(resp_obj['PredictResult'])
print(predict_result['result'])

PredictContent内容示例

#包含上文context_above和下文context_below数据的完整示例，有助于提升算法效果，上下文也可以省略不写
{
  "context_above": [
    {
      "role": "⽤户",
      "context": "叫你改价格直接取消我订单？"
    },
    {
      "role": "客服",
      "context": "订单下单后不⽀持修改"
    }
  ],
  "input": "服务态度不好，你们就是这种服务态度的？",
  "context_below": [
    {
      "role": "客服",
      "context": "不好意思呢，确实是这样的"
    },
    {
      "role": "⽤户",
      "context": "拜拜，再也不来了"
    }
  ]
}

PredictResult内容示例

{
  "emotion": {
    "key": "抱怨",
    "score": 0.4929790496826172
  },
  "intent": {
    "key": "⽆",
    "score": 0.756518542766571
  },
  "category": {
    "key": "其他类-其他",
    "score": 0.4580000042915344
  },
  "sentiment": {
    "key": "负",
    "score": 1.0
  },
  "aspectItem": [
    {
      "aspectCategory": "客服-服务",
      "aspectPolarity": "负",
      "negativeProb": 1.0,
      "positiveProb": 0.0,
      "terms": [
        {
          "aspectTerm": "服务态度",
          "opinionTerm": "不好"
        }
      ]
    }
  ]
}

入参说明

出参说明