Fetal heart state detection method based on multi-modal data, electronic equipment and storage medium

The invention provides a fetal heart state detection method based on multi-modal data, electronic equipment and a storage medium. The fetal heart state detection method comprises the steps that the multi-modal data is acquired; for each mode, preprocessing the data in the mode to obtain data features of the mode; inputting the multi-modal data features into corresponding recurrent neural networks respectively to obtain feature vectors output by the multiple recurrent neural networks respectively; and fusing the plurality of feature vectors into a to-be-detected feature, and inputting the to-be-detected feature into a trained classifier to obtain fetal heart state category information. According to the scheme, related information from different modes is effectively extracted and integrated, and the accuracy and robustness of fetal heart state detection are effectively improved. 本申请提供一种基于多模态数据的胎心状态检测方法、电子设备、存储介质，包括：获取多模态数据；针对每一模态，分别对所述模态下数据进行预处理，得到所述模态的数据特征；将多模态的数据特征分别输入至对应的循环神经网络，得到多个循环神经网络分别输出的特征向量；将多个特征向量融合为