Amazon says, “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.”
In September, Amazon launched natural turn-taking which allows the user to converse with the digital assistant without having to speak the wake word. Now, with Alexa’s improved machine learning technology, Alexa could be one step ahead of its rivals. The key, of course, is to somehow figure out what the intent of the user is; once that is accomplished, Alexa might be able to complete a subsequent request without being asked to do so.
