Speech-based anxiety prediction model generation method and anxiety prediction system

Abstract

The invention provides a speech-based anxiety prediction model generation method and an anxiety prediction system, and the method comprises the steps: 1, collecting speech of a text read by the user and the SAS scale score of the user, and marking the speech with the score; and 2, extracting voice features of the voice, and constructing an anxiety prediction model by using a neural network. According to the invention, automatic recognition of the tested anxiety state is realized through machine learning by using the voice of the reading text, the system is convenient to operate and deploy, andthe anxiety recognition and prediction convenience is improved.

Description

technical field

[0001] The invention relates to the fields of psychology and artificial intelligence, and more particularly relates to a method for generating a voice-based anxiety prediction model and an anxiety prediction system. Background technique

[0002] Anxiety disorder is a chronic disease characterized by uncontrollable, excessive, extensive, and persistent anxiety, also known as anxiety neurosis, with anxiety emotional experience as the main feature. The main manifestations are: nervousness and worry without a clear objective object, restlessness, and symptoms of autonomic dysfunction, such as palpitations, hand tremors, sweating, frequent urination, etc., and restlessness in movement. Anxiety disorders are not caused by actual threats, or the level of anxiety and panic is very disproportionate to the actual situation. Drug therapy such as anti-anxiety drugs and psychotherapy are the main treatment methods for anxiety disorders.

[0003] Anxiety disorder can be ...

Images