Text classification method fusing optimization pre-training model and graph convolutional network model

The invention discloses a text classification method fusing an optimization pre-training model and a graph convolutional network model, and relates to the technical field of natural language processing. According to the method, text features are extracted through an optimized pre-training model for feature interpolation and a graph convolutional network model for designing a scale fusion mechanism, classification prediction is carried out, and then weighted fusion is carried out on two prediction results, so that efficient text classification is realized. By utilizing a more comprehensive text classification technology provided by the invention, the accuracy of text classification can be effectively improved, and the method can be widely applied to multiple fields. 本发明公布了一种融合优化预训练模型与图卷积网络模型的文本分类方法，涉及自然语言处理技术领域；分别通过进行特征插值的优化的预训练模型和通过设计尺度融合机制的图卷积网络模型提取文本特征并进行分类预测，再将两种预测结果进行加权融合，实现高效的文本分类。利用本发明提供的更为全面的文本分类技术，能够有效地提升文本分类的准确度，可广泛应用于多个领域。