Amazon Alexa can now predict a task – even when a user hasn't directly expressed it

Amazon Alexa can now predict a task – even when a user hasn't directly expressed it
Amazon has launched a new Alexa skill that will help predict customers latent goals -- goals that are implicit in customer requests but not directly expressed -- when they talk to Alexa about tasks.

For instance, if a customer asks, "How long does it take to steep tea?", the latent goal could be setting a timer for steeping a cup of tea.

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?"

Complimentary Tech Event
Transform talent with learning that works
Capability development is critical for businesses who want to push the envelope of innovation.Discover how business leaders are strategizing around building talent capabilities and empowering employee transformation.Know More
"We're taking another step toward natural interaction with a capability that lets Alexa infer customers' latent goals," the company said in a statement on Wednesday.

The first step for Alexa is to decide whether to anticipate a latent goal at all.


To determine whether to suggest a latent goal, "we use a deep-learning-based trigger model that factors in several aspects of the dialogue context, such as the text of the customer's current session with Alexa and whether the customer has engaged with Alexa's multi-skill suggestions in the past".

If the trigger model finds the context suitable, the system suggests a skill to service the latent goal.

Those suggestions are based on relationships learned by the latent-goal discovery model.

For instance, the model may have discovered that customers who ask how long tea should steep frequently follow up by asking Alexa to set a timer for that amount of time.

The latent-goal discovery model analyzes multiple features of customer utterances, including pointwise mutual information, which measures the likelihood of an interaction pattern in a given context relative to its likelihood across all Alexa traffic.

Over time, the discovery model improves its predictions through active learning, which identifies sample interactions that would be particularly informative during future fine-tuning.

This capability is already available to Alexa customers in English in the United States.