基于多元关系融合的专利技术演化路径识别方法研究  

Patented Technology Evolution Path Identification Based on Multi-relation Data Fusion

作　　者：张娴[1,2] 曾荣强 李姝影 李嘉晖[1,2] Zhang Xian;Zeng Rongqiang;Li Shuying;Li Jiahui(Chengdu Library and Information Center,Chinese Academy of Sciences,Chengdu 610299;Department of Information Resource Management,School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190;School of Computer Science,Chengdu University of Information Technology,Chengdu 610225)

机构地区：[1]中国科学院成都文献情报中心,成都610299 [2]中国科学院大学经济与管理学院信息资源管理系,北京100190 [3]成都信息工程大学计算机学院,成都610225

出　　处：《图书情报工作》2024年第3期71-84,共14页Library and Information Service

基　　金：国家社会科学基金项目“技术创新路径识别与预测的多元关系融合方法研究”(项目编号:18BTQ067)研究成果之一。

摘　　要：[目的/意义]有效融合专利引用网络中的多元关系,消除引用主观动机对技术关联真实性的影响,提高技术演化路径识别的客观性与准确性。[方法/过程]将专利引用网络中的引用连接关系、主题关联关系、引用动机关系分别作为基础关系、增强关系和调节关系,提出一种多元关系融合的主路径识别方法,在此基础上构建基于多元关系融合的技术演化路径搜索模型,采用迭代局部搜索算法实现该模型的求解,并以石墨烯传感技术领域为例开展实证研究。[结果/结论 ]对比实验证明本方法可以有效提高实证领域的技术演化路径识别效果。未来多元关系融合主路径研究深化方向是:发掘应用更多具有融合价值的主题关联类型;加强数据融合算法与模型的研究与验证。[Purpose/Significance] The effective integration of the multiple relations in the patent citation network is conducive to eliminating the influence of subjective motivation on the authenticity of technical relation and improving the objectivity and accuracy of technology evolution path identification results.[Method/Process]Taking the link connectivities,subject similarities and citing intentions in the patent citation network as the basic relations,strengthened relations and regulation relations,it proposed a main path analysis method based on multi-relation data fusion.On this basis,it constructed a technical evolution path searching model based on multi-relation data fusion,and solved the model by using an iterated local search algorithm.Then,it carried out an empirical research t in the field of graphene sensing technology as an example.[Result/Conclusion] The experimental results show that the proposed method can effectively improve the effect of technology evolution path identification in the empirical field.In the future,much work in main path of multi-relation fusion needs to be done in discovering and applying more types of theme associations with integration value,and strengthening the research and verification of data fusion algorithms and models.

关 键 词：主路径 技术演化 多元关系融合 专利引用网络 引用动机 局部搜索算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] G306[自动化与计算机技术—计算机科学与技术]