Research on Chinese Patent Text Classification in the Field of New Energy Vehicles Based on the XGBoost Model

To improve the efficiency of automatic patent text classification and further elevate the level of patent management, this paper proposes a Chinese patent text classification model in the field of new energy vehicles based on the XGBoost model. The research employs jieba word segmentation and word vectors generated by word2vec to represent the patent text. It then combines five machine learning algorithm models to train on the patent text corpus, achieving automatic classification of the patent text. Comparative experimental results demonstrate that the XGBoost model outperforms other models in terms of precision, recall, and f1_score, with classification accuracy reaching up to 95% for some categories. The model has guiding significance for automatic patent text classification.