Method and system for automatic back-channel generation in interactive agent system

An automatic back-channel generation system comprising:

• one or more processors comprising:
• an input unit configured to receive an utterance of a user;
• a prediction unit configured to predict a back-channel and predict a utterance sentiment feature by analyzing the received utterance of the user in a back-channel prediction model;
• a generator configured to generate the predicted back-channel;
• and
• an output unit configured to output the generated back-channel,
• wherein the back-channel prediction model is an AI model that is trained to predict a back-channel to express from the utterance of the user, and
• wherein a training of the back-channel prediction model to predict the back-channel is performed at the same as a training of the back-channel prediction model to predict the utterance sentiment feature is performed.

An automatic back-channel generation method comprising:

• predicting a back-channel and predicting a utterance sentiment feature by analyzing an utterance of a user in a back-channel prediction model;
• and
• generating the predicted back-channel,
• wherein the back-channel prediction model is an AI model that is trained to predict a back-channel to express from the utterance of the user, and
• wherein a training of the back-channel prediction model to predict the back-channel is performed at the same as a training of the back-channel prediction model to predict the utterance sentiment feature is performed.