Alexa equipped devices are about to get even smarter. A new feature, already available to US-based English speakers, will give follow up suggestions to certain questions.

It uses artificial intelligence (AI) to infer latent goals: The thing you actually want, not what you exactly asked.

Alexa Will Now Make Better Suggestions

The changes were announced on the Amazon Science blog. Alexa will follow up on certain questions with suggestions based on what it thinks you really want. Amazon uses how long you should steep tea as an example:

With the new capability, Alexa might answer that question, "Five minutes is a good place to start", then follow up by asking, "Would you like me to set a timer for five minutes?"

The new feature uses a mixture of past behavior and current dialogue to determine what suggestions work best for the user. The announcement goes on to highlight the multi-step process required to get behavior like this right.

A Complex New AI Model

The machine learning-based trigger model determines whether there should be a suggestion based on a perceived latent goal. Each suggestion is decided by a deep learning-based sub module responsible for analyzing the likelihood of a follow-up interaction or whether the user's initial question was meant to be a request.

This is paired with a model responsible for semantic role labeling—the process of assigning meaningful labels to words in a sentence. All of this information feeds into an optimized system for tracking which recommendations are helpful and which should be suppressed in the future.

Another Step Towards Natural Alexa Interactions

This addition is the latest in a long line of improvements to Alexa's conversational skillset. Natural turn-taking was introduced in September 2020. This improves Alexa's ability to determine when a user has finished speaking and whether the user is talking to the device or not.

Amazon also introduced the Alexa Conversations beta in July 2020, a system making it easier for developers to integrate complex conversational experiences into Alexa skills.

All of these capabilities are already available to US-based English speaking Alexa users. Amazon also claims these features will work with existing Alexa skills, too. However, developers can use the name-free interaction (NFI) toolkit to add further integration, as outlined in the the Alexa Skills Kit blog.

If you want the interaction to feel more natural, you can also change Alexa's name.

Convenience Beamed From the Cloud to Your Home

Given Alexa's always-on cloud-based operation it makes sense for Amazon to add the ability to inference and train AI remotely. The new tech will make Amazon smart devices easier to use, and as long as you are comfortable with the ways Alexa can pose a privacy risk, you'll find these changes welcome.