Patent value prediction in biomedical textiles: A method based on a fusion of machine learning models

Abstract

Patent value prediction is essential for technology innovation management. This study aims to enhance technology innovation management in the field of biomedical textiles by processing complex biomedical patent information to improve the accuracy of predicting patent values. A patent value grading prediction method based on a fusion of machine learning models is proposed, utilizing 113,428 biomedical textile patents as the research sample. The method combines BERT (Bidirectional Encoder Representations from Transformers) and a stacking strategy to classify and predict the value class of biomedical textile patents using both textual information and structured patent features. We implemented this method for patent value prediction in biomedical textiles, leading to the development of BioTexVal—the first dedicated patent value prediction model for this domain. BioTexVal’s innovation lies in employing a stacking strategy that integrates multiple machine learning models to enhance predictive accuracy while leveraging unstructured data during training. Results have shown that this approach significantly outperforms previous predictive methods. Validated on 113,428 biomedical textile patents spanning from 2003 to 2023, BioTexVal achieved an accuracy of 88.38%. This study uses average annual forward citations as an indicator for distinguishing patent value grades. The method may require adjustments based on data characteristics when applied to other research fields to ensure its effectiveness.