A study of emotional interaction decision making in human-computer interaction based on the concept of emotional cognitive evaluation

Abstract

As science and technology continue to advance, there is a growing desire for computers to gradually begin to replace humans in some complex tasks, as well as for them to have more human-like functions. As a result, the modern field of artificial intelligence research has begun to focus on the new research direction of artificial emotions, and the study of emotional robots relies on the ever-improving theories of cognitive psychology, cognitive psychiatry, and cognitive evaluation of emotions. Most machine learning algorithms ignore the high-level regulatory role of cognition and emotion, and as a result, robots do not have the ability to provide emotional feedback during human-robot interaction. In this regard, based on the theory of emotional cognitive evaluation, the author proposes an emotional cognitive decision algorithm based on emotional cognitive evaluation and Q-learning by establishing an emotional cognitive evaluation model, and simulates the emotional intelligence experiment through the improved Q-learning algorithm.