近年来，在人工智能的迅速发展推动下，机器自动的情绪检测逐渐成为一个热门的领域。面部表情在传递信息中占据十分重要的作用。所以，此文采用基于面部表情识别的情绪检测。不同于专注于静态图片和文本等的情绪检测，此文提出了基于隐性马尔科夫模型的动态情绪检测。 此文论述了情绪和表情之间的关系，简要概括了情绪检测的发展历史和现状，解释了隐性马尔科夫模型的定义和主要算法，基于Baum-Welch算法对HMM模型进行训练并成功建立模型，并基于不同性别的HMM模型对男女的情绪表达差异化进行分析。 最后通过Viterbi算法对HMM模型进行测试，验证了此模型的有效性和可行性。

In recent years, with the development of artificial intelligence, machine automatic emotional detection has gradually become a hot area. Facial expressions in the transmission of information occupies a very important role. Therefore, this article uses facial expression recognition based on emotional detection. Different from the emotional detection of static pictures and text, this paper proposes dynamic emotion detection based on the hidden Markov model. This paper expounds the relationship between emotion and expression, briefly summarizes the development history and present situation of emotion detection, explains the definition and main algorithm of the hidden Markov model, and exercises the HMM model based on Baum-Welch algorithm and successfully established Model, and based on different gender HMM model of men and women to analyze the differences in emotional expression. Finally, the HMM model is tested by Viterbi algorithm, and the feasibility and validity of the model are verified.