Expediting interaction with a digital assistant by predicting user responses

Abstract

A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.

Description

Background technique

[0001] A digital assistant refers to a virtual agent that is used to answer a user's queries, usually via multiple rounds of dialogue. In a typical case, the user starts by entering an initial command, such as "book a hotel in New York." The digital assistant then goes through a series of system prompts to identify the time, location, and other details of the reservation. To perform this task, digital assistants typically rely on one or more skill components. Each skill component is configured to handle a specific task, such as booking a restaurant, controlling a media system, retrieving news, and so on.

[0002] Although digital assistants have become ubiquitous in our lives, these agents sometimes exhibit suboptimal performance. For example, users may be increasingly frustrated with the amount of time it takes digital assistants to understand and perform tasks. Users can be especially frustrated whenever the digital assistant misinterprets the user's...

Images