Core entity prediction model training method and device, equipment and storage medium

The invention provides a core entity prediction model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence such as knowledge maps and natural language processing, and can be applied to scenes such as intelligent industry and intelligent government affairs. According to the specific implementation scheme, a plurality of words and position information of the words are mined based on a training document; constructing a training sample based on the plurality of words and the position information of each word; and training a core entity prediction model based on the training document and the training sample. In addition, the invention further provides a core entity mining method. According to the technology disclosed by the invention, the training efficiency of the core entity prediction model and the core entity mining efficiency can be effectively improved. 本公开提供了一种核心实体预测模型的训练方法、装置、设备及存储介质，涉及知识图谱、自然语言处理等人工智能技术领域，可应用于智能工业、智慧政务等场景。具体实现方案为：基于训练文档，挖掘多个