本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 启用生成式通话摘要
<a name="tca-enable-summarization"></a>

**注意**  
 **由 Amazon Bedrock 提供支持：** AWS 实现[自动滥用检测](https://docs.aws.amazon.com//bedrock/latest/userguide/abuse-detection.html)。由于生成式人工智能支持的通话后摘要是基于 Amazon Bedrock 构建的，因此，用户可以充分利用 Amazon Bedrock 中实施的控制措施以安全且负责任地使用人工智能 (AI)。

要在通话后分析作业中使用生成式通话摘要，请参阅以下示例：

## AWS 管理控制台
<a name="analytics-summarization-console"></a>

在“摘要”面板中，启用生成式通话摘要以在输出中收到摘要。

![\[Amazon Transcribe 控制台屏幕截图：“呼叫分析作业” 页面。\]](http://docs.aws.amazon.com/zh_cn/transcribe/latest/dg/images/analytics-summarization.png)


## AWS CLI
<a name="analytics-summarization-cli"></a>

此示例使用带有`Summarization`子`Settings`参数的[start-call-analytics-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-call-analytics-job.html)命令和参数。有关更多信息，请参阅 [https://docs.aws.amazon.com//transcribe/latest/APIReference/API_StartCallAnalyticsJob.html](https://docs.aws.amazon.com//transcribe/latest/APIReference/API_StartCallAnalyticsJob.html)。

```
aws transcribe start-call-analytics-job \
--region us-west-2 \
--call-analytics-job-name my-first-call-analytics-job \
--media MediaFileUri=s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac \
--output-location s3://amzn-s3-demo-bucket/my-output-files/ \
--data-access-role-arn arn:aws:iam::111122223333:role/ExampleRole \
--channel-definitions ChannelId=0,ParticipantRole=AGENT ChannelId=1,ParticipantRole=CUSTOMER
--settings '{"Summarization":{"GenerateAbstractiveSummary":true}}'
```

以下是另一个使用[start-call-analytics-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-call-analytics-job.html)命令的示例，以及支持该任务汇总的请求正文。

```
aws transcribe start-call-analytics-job \
--region us-west-2 \
--cli-input-json file://filepath/my-call-analytics-job.json
```

*my-call-analytics-job.json* 文件包含以下请求正文。

```
{
  "CallAnalyticsJobName": "my-first-call-analytics-job",
  "DataAccessRoleArn": "arn:aws:iam::111122223333:role/ExampleRole",
  "Media": {
    "MediaFileUri": "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac"
  },
  "OutputLocation": "s3://amzn-s3-demo-bucket/my-output-files/",
  "ChannelDefinitions": [
    {
      "ChannelId": 0,
      "ParticipantRole": "AGENT"
    },
    {
      "ChannelId": 1,
      "ParticipantRole": "CUSTOMER"
    }
  ],
  "Settings": {
    "Summarization":{
      "GenerateAbstractiveSummary": true
    }
  }
}
```

## 适用于 Python (Boto3) 的 AWS SDK
<a name="analytics-summarization-python"></a>

此示例使用 start\$1call\$1analytics [\$1job 方法启动](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/transcribe.html#TranscribeService.Client.start_call_analytics_job)启用汇总功能的呼叫分析。 适用于 Python (Boto3) 的 AWS SDK 有关更多信息，请参阅 [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartCallAnalyticsJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartCallAnalyticsJob.html)。

有关使用的其他示例 AWS SDKs，包括特定功能、场景和跨服务示例，请参阅本章。[使用 Amazon Transcribe 的代码示例 AWS SDKs](service_code_examples.md)

```
from __future__ import print_function
from __future__ import print_function
import time
import boto3
transcribe = boto3.client('transcribe', 'us-west-2')
job_name = "my-first-call-analytics-job"
job_uri = "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac"
output_location = "s3://amzn-s3-demo-bucket/my-output-files/"
data_access_role = "arn:aws:iam::111122223333:role/ExampleRole"
transcribe.start_call_analytics_job(
  CallAnalyticsJobName = job_name,
  Media = {
    'MediaFileUri': job_uri
  },
  DataAccessRoleArn = data_access_role,
  OutputLocation = output_location,
  ChannelDefinitions = [
    {
      'ChannelId': 0, 
      'ParticipantRole': 'AGENT'
    },
    {
      'ChannelId': 1, 
      'ParticipantRole': 'CUSTOMER'
    }
  ],
  Settings = {
    "Summarization":
      {
        "GenerateAbstractiveSummary": true
      }
  }
)
    
while True:
  status = transcribe.get_call_analytics_job(CallAnalyticsJobName = job_name)
  if status['CallAnalyticsJob']['CallAnalyticsJobStatus'] in ['COMPLETED', 'FAILED']:
    break
  print("Not ready yet...")
  time.sleep(5)
print(status)
```