Amazon Comprehend launches real time custom classification

Posted on: Nov 25, 2019

Amazon Comprehend now supports real time Custom Classification. You can use the real time Custom Classification to understand, label and route information based on your own business rules in real time. For example, you can instantly categorize the content of support requests and route them to the proper support team. Or you can automatically moderate website comments as they’re flowing in. Prior to this launch, customers used Custom Classification with their business-specific labels to categorize documents asynchronously. Now, customers can choose real time or asynchronous Custom Classification depending on their use case. 

Creating a custom model is simple. You provide examples of text for each of the labels you want to use, and Comprehend trains on those to create your custom model. No machine learning experience required. For real time classification, you can provision an endpoint with capacity that fits your need. You can also use Application Auto Scaling and dynamically scale the capacity to minimize costs and meet your user demand with low latency. Application Auto Scaling supports scheduled scaling and target tracking. Scheduled scaling allows you to scale based on a schedule and target tracking allows you to maintain your capacity utilization at the level you set.

With custom classification, you can build your custom model without using a single line of code. An SDK is available for you to integrate your customer classifier into your current applications. With your custom model, it is easy to moderate website comments, triage customer feedback, and organize workgroup documents. 

Amazon Comprehend real time Custom Classification is now available in all AWS regions where Amazon Comprehend is available. To try the new feature, log in to the Amazon Comprehend console for a code-free experience, or download the AWS SDK. You can also learn more about this new feature in the documentation.