Emotion modeling method and apparatus thereof

An emotion modeling apparatus, comprising:

• a detector configured to detect a sound uttered by a user comprising an emotional adjective;
• and
• a processor configured to:
• determine an emotional attribute based on the sound using an emotion analysis algorithm comprising a conversational memory network (CMN) by analyzing the emotional adjective to derive an emotional state, a disposition and a preferred sound of the user,
• derive an instrumental value of a sound concept by:
• classifying vehicle environment development needs using at least one of logistic regression (LR), a support vector machine (SVM), or a K-nearest neighbor (KNN) algorithm;
• reflecting psychosocial consequences in the classified vehicle environment development needs;
• and
• predicting a vehicle environment function using at least one of multiple linear regression (MLR) or support vector regression (SVR) to derive the instrumental value by analyzing psychosocial consequences of the emotional attribute using an artificial neural network,
• generate a plurality of emotional models based on the instrumental value of the sound concept, wherein the plurality of emotional models comprise a cultured sound model, an entertaining sound model, and an adaptable sound model;
• select one of the plurality of emotional models based on a drive mode, wherein the drive mode is one of an eco mode, a comfort mode, a sports mode, and a smart mode and wherein:
• when the drive mode is set to the comfort mode, the cultured sound model is selected;
• when the drive mode is set to the sports mode, the entertaining sound model is selected;
• and
• when the drive mode is set to the smart mode, the adaptable sound model is selected;
• generate a vehicle sound corresponding to the selected emotional model using the selected emotional model;
• and
• output the generated vehicle sound through a speaker, wherein, when the drive mode is set to the eco mode, the vehicle sound is turned off;
• wherein the processor is further configured to:
• establish a criterion of determining borderline data by performing position calculation of conservative and progress and stability and fun by receiving personalized data as input data using the derived instrumental value of the sound concept, and
• determine an emotion modeling methodology based on the criterion;
• wherein establishing the criterion of determining borderline data comprises determining three methodologies of the emotion modeling using position calculation for conservative and progress on an X-axis and stability and fun on a Y-axis to be used in generating the plurality of emotional models.