User learning behavior-based recommendation method and device

The invention provides a user learning behavior-based recommendation method, which can be applied to the technical field of artificial intelligence. The method comprises the steps of: obtaining database topics and user historical data, wherein the user historical data comprise article reading records and keyword searching records; determining a user feature portrait according to the user historical data and a preset feature tag; determining a question feature vector according to the database question and the preset feature tag; calculating the similarity between the user feature portrait and the question feature vector; and recommending questions to the user according to the similarity. The invention further provides a recommendation device and equipment based on the user learning behaviors, a storage medium and a program product. 本公开提供了一种基于用户学习行为的推荐方法，可以应用于人工智能技术领域。该方法包括：获取数据库题目和用户历史数据，其中，所述用户历史数据包括阅读文章记录和关键字搜索记录；根据所述用户历史数据和预设特征标签确定用户特征画像；根据所述数据库题目和所述预设特征标签确定题目特征向量；计算所述用户特征画像和所述题目特征向量的相似度；根据所述相似度向用户推荐题目。本公开还