Stock market risk prediction method and apparatus, computer device and storage medium

The embodiment of the invention discloses a stock market risk prediction method and apparatus, a computer device and a storage medium. The method comprises the following steps: crawling text data of aspecified time period of a current day; performing word segmentation on the text data of the specified time period of the current day to obtain a word segmentation result of the text of the current day; and inputting the word segmentation result of the text of the current day into a pre-trained recurrent neural network for predicting stock market risks to obtain a stock rise and fall prediction result of the current day. According to the method, the massive information on the Internet is fully utilized as the basic data of stock market risk prediction, and rapid and intelligent prediction ismade on the stock market risks according to a recurrent neural network model. 本申请实施例公开了种股市风险预测方法、装置、计算机设备及存储介质。该方法包括：爬取当日指定时间段的文本数据；将所述当日指定时间段的文本数据进行分词，得到当日文本的分词结果；将所述当日文本的分词结果输入至预先训练得到的用于预测股市风险的循环神经网络，得到当日股票涨跌预测结果。该方法实现充分利用互联