Q35 — AWS SAA-C03 第3章

第 35/65 题 | ← 返回第3章

Q165.一家支付处理公司记录与其客户的所有语音通信，并将音频文件存储在 Amazon S3 存储桶中.公司需要从音频文件中捕获文本.公司必须从文本中删除属于客户的任何个人身份信息 (PII).解决方案架构师应该怎么做才能满足这些要求?

正确答案: C. 配置 Amazon Transcribe 转录作业并启用 PII 编辑.当音频文件上传到 S3 存储桶时，调用 AWS Lambda 函数启动转录作业.将输出存储在单独的 S3 存储桶中

解析

o meet the requirement of capturing text from audio files stored in an Amazon S3 bucket by a payment processing company and removing any personally identifiable information (PII) belonging to customers, a solutions architect should configure an Amazon Transcribe transcription job with PII redaction turned on. An AWS Lambda function should be invoked to start the transcription job when an audio file is uploaded to the S3 bucket, and the output should be stored in a separate S3 bucket. Therefore, option C is the correct answer.Option A suggests using Amazon Kinesis Video Streams to process the audio files, which may not be the most appropriate solution for this use case.Option B suggests invoking an AWS Lambda function to start an Amazon Textract task to analyze the call recordings, which may work but would require more manual configuration and would not provide the same level of integration and automation as using Amazon Transcribe.Option D suggests creating an Amazon Connect contact flow that ingests the audio files with transcription turned on and embedding an AWS Lambda function to scan for known PII patterns. While this could work, it requires more manual configuration and does not provide the same level of integration and automation as using Amazon Transcribe.By using Amazon Transcribe with PII redaction turned on, the transcription job automatically removes any PII from the text output, ensuring compliance with privacy regulations. Using an AWS Lambda function to trigger the transcription job when an audio file is uploaded to the S3 bucket minimizes operational overhead. The output can be stored in a separate S3 bucket for further analysis or processing. This approach provides a secure, scalable, and reliable solution for capturing text from audio files while protecting customer privacy.为了满足支付处理公司从存储在Amazon S3存储桶中的音频文件中捕获文本并删除属于客户的任何个人身份信息(PII)的需求，解决方案架构师应该配置一个开启PII编印的Amazon transcript转录作业。当将音频文件上传到S3桶时，应该调用AWS Lambda函数来启动转录作业，并且输出应该存储在单独的S3桶中。因此，选项C是正确答案。选项A建议使用Amazon Kinesis视频流来处理音频文件，这可能不是最适合此用例的解决方案。选项B建议调用AWS Lambda函数来启动Amazon text任务来分析呼叫记录，这可能可行，但需要更多的手动配置，并且不能提供与使用Amazon transcript相同级别的集成和自动化。选项D建议创建一个Amazon Connect联系流，该流摄取打开转录的音频文件，并嵌入一个AWS Lambda函数来扫描已知的PII模式。虽然这可以工作，但它需要更多的手动配置，并且不能提供与使用Amazon transcript相同级别的集成和自动化。通过使用打开PII编辑的Amazon translate，转录作业将自动从文本输出中删除任何PII，从而确保符合隐私法规。当将音频文件上传到S3桶时，使用AWS Lambda函数触发转录作业可以最大限度地减少操作开销。输出可以存储在单独的S3桶中，以便进一步分析或处理。这种方法提供了一种安全、可扩展且可靠的解决方案，可以在保护客户隐私的同时从音频文件中捕获文本。