Automated Multi-Persona Response Generation

Multi-persona AI response generation with robotics/speech-synthesis CPC signal.

A system for performing automated multi-persona response generation includes processing hardware, a display, and a memory storing a software code. The processing hardware executes the software code to receive input data describing an action and identifying a multiple interaction profiles corresponding respectively to multiple participants in the action, obtain the interaction profiles, and simulate execution of the action with respect to each of the participants. The processing hardware is further configured to execute the software code to generate, using the interaction profiles, a respective response to the action for each of the participants to provide multiple responses. In various implementations, one or more of those multiple responses may be used to train additional artificial intelligence (AI) systems, or may be rendered to an output device in the form of one or more of a display, an audio output device, or a robot, for example.

BACKGROUND

Advances in artificial intelligence have led to the development of a variety of systems providing interfaces that simulate social agents. However, composing dialogue or choreographing actions for execution by a social agent requires an understanding of not only what the social agent should say or do, but also anticipating how a user or interaction participant (hereinafter “participant”) will respond during a particular interaction with the social agent. Given the variability of human language, personality types or “personas,” demographics, and the context in which an interaction takes place, it is infeasible for a human system designer to predict all of the possible responses a participant might make for all but the simplest interactive prompts.

In the existing art, responses to dialogue content for example, are typically tested by directing samples of dialogue to different human subjects, and collecting and analyzing the responses by those subjects. However, such an approach imposes a high resource and time overhead. For example, these existing techniques may require several weeks or more to generate the variety of responses needed by dialogue authors to accurately associate anticipated participant responses with the variety of personas and interaction contexts that are likely to be encountered.