突破式创新发明人的提前发现:基于专利知识图动态学习的预测  

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

作　　者：余博文 刘向[1] Yu Bowen;Liu Xiang(School of Information Management,Central China Normal University,Wuhan 430079,China)

机构地区：[1]华中师范大学信息管理学院,武汉430079

出　　处：《数据分析与知识发现》2023年第12期40-51,共12页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:71673106)的研究成果之一。

摘　　要：[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歧义问题,本文对因该问题导致无法识别创新类型的发明人进行过滤。[结论]本文模型可以通过多维度特征对突破式创新发明人进行提前发现,并且在预测发明人未来创新类型时,发现发明人的合作和引用相关特征均很重要。[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 data and found its overall prediction accuracy reached 83.51%.The model’s accuracy for predicting breakthrough and continuation innovation inventors reached 85.99%and 81.40%,respectively.While predicting the inventors,their collaboration and citation-related features were ranked high.[Limitations]The ambiguity of the technological innovation metric of patents around the value of 0 was not fully resolved.We filtered inventors with unidentified categories due to this problem.[Conclusions]The proposed model could discover breakthrough innovation inventors earlier.

关 键 词：专利分析 引用网络 合作网络 突破式创新 统计学习 

分 类 号：G305[文化科学] TP181[自动化与计算机技术—控制理论与控制工程]