Content Moderation and Compliance Using AWS AI Services
Publication date: October 28, 2022 (Diagram history)
This architecture shows how to build customizable serverless workflows for reliable and scalable AI-based content moderation. With AWS AI services, you can automate content analysis across multiple media types.
Content Moderation and Compliance Using AWS AI Services
The following steps describe the architecture:
-
End users upload their content into the AWS Cloud.
-
Amazon Transcribe and Amazon Rekognition process the audio streams within video streams. They extract content moderation categories by using simple APIs.
-
Workflows, publisher/subscription patterns, and custom code moderate the content.
-
Content securely persists into an Amazon Simple Storage Service bucket or another data store.
-
Amazon Transcribe converts audio into text. Amazon Comprehend provides natural language processing (NLP) for analysis.
-
Amazon Textract extracts content from documents. Amazon Comprehend NLP moderates the extracted content.
-
Amazon SageMaker AI Ground Truth integrates human workforces to customize model vocabularies and image labels.
-
Amazon Augmented AI (Amazon A2I) brings humans into the loop for scenarios that are not fully automatable.
Further reading
For additional information, refer to the following resources:
Diagram history
To be notified about updates to this reference architecture diagram, subscribe to the RSS feed.
| Change | Description | Date |
|---|---|---|
Initial publication | Reference architecture diagram first published. | October 28, 2022 |
Note
To subscribe to RSS updates, you must have an RSS plugin enabled for the browser you are using.
