AI digital human sentiment analysis method based on multiple modes

• Main Authors: ZHU XIAOQIU, FAN WEIDONG, ZHANG XINGXING, CHEN ZAIDIE
• Format: Patent
• Language: Chinese; English
• Published: 08.07.2022
• Subjects: ACOUSTICS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention discloses an AI digital human sentiment analysis method based on multiple modes, which comprises the following steps: S1, facial expression recognition and sentiment judgment are carried out, and a result a is output and input into a multi-mode sentiment analysis module; s2, voice emotion recognition and judgment are carried out, and a result e is output to a multi-mode emotion analysis module; s3, text emotion recognition and judgment are carried out, and a result f is output to a multi-mode emotion analysis module; and S4, in a multi-mode sentiment analysis module, performing sentiment random combination judgment on the results a, e and f, taking an average probability value of a random sentiment combination condition as a final sentiment judgment result g, and outputting the final sentiment judgment result g to the AI digital human. According to the method, the emotional state of the user is judged through multiple modes, the emotional state of the user can be grasped most comprehensively and