期刊论文

Detecting Inventors of Breakthrough Innovation Based on Dynamic Learning of Patent Knowledge Graph

中文

数据分析与知识发现

2096-3467

2023

7

12

40-51

10.11925/infotech.2096-3467.2023.0219

本校为第一机构

[目的]利用发明人的合作和引用关系特征,提前发现突破式创新发明人.[方法]首先定义突破式创新发明人的度量指标,然后通过分析挖掘发明人合作和引用关系特征,基于专利知识图动态学习建立预测发明人未来创新类型的统计学习模型,实现突破式创新发明人的提前发现,最后对突破式创新发明人的关键特征进行分析.[结果]基于真实专利数据的实验结果表明,使用随机森林模型预测的准确率达到83.51％,对突破式创新发明人和延续式创新发明人预测的准确率分别为85.99％和81.40％.模型在预测突破式创新发明人时,发明人的合作和引用相关特征的重要性评分排名均靠前.[局限]未完全解决专利的技术创新度量在零值附近的...

[Objective]This paper aims to identify breakthrough innovation inventors through their collaboration and citation features.[Methods]First,we defined the metrics of breakthrough innovation inventors.Then,we examined the features of cooperation and citation relationship of inventors.Third,we established a statistical learning model to predict their future innovations based on the dynamic learning of the patent knowledge graph.Finally,we analyzed the characteristics of breakthrough innovation inventors.[Results]We examined our model with patent da...