基于多模态特征融合的相似专利识别方法研究  

Research on Similar Patent Identification Based on Multimodal Feature Fusion

作　　者：谢小东 吴洁[1] 盛永祥[1] 王建刚[1] 周潇[1] Xie Xiaodong;Wu Jie;Sheng Yongxiang;Wang Jiangang;Zhou Xiao(School of Economics and Management,Jiangsu University of Science and Technology,Zhenjiang 212003)

机构地区：[1]江苏科技大学经济管理学院,镇江212003

出　　处：《图书情报工作》2024年第18期112-122,共11页Library and Information Service

基　　金：国家自然科学基金面上项目“面向产业安全的产业创新生态系统韧性内涵、评价与优化策略研究”(项目编号:72171122);江苏省研究生科研与实践创新计划项目“创新联合体潜在合作伙伴选择及合作方向研究”(项目编号:KYCX23_3817)研究成果之一。

摘　　要：[目的/意义]专利数量攀升的同时给专利检索工作带来了巨大的挑战,如何利用先进的计算机技术进行相似专利识别成为亟待解决的问题。[方法/过程]提出一种基于多模态特征融合的相似专利识别方法,通过BERTwwm模型和ResNet-50模型提取专利文本模态特征和图像模态特征,结合自注意力机制和交叉注意力机制有效利用两种模态内部特征信息以及模态间的交互信息,在此基础上通过模型训练与优化进行相似专利识别。[结果/结论]采用IPC为“C08F10/00”领域数据进行实证,本文模型准确率达到80.03%,召回率达到82.01%,优于基线模型效果。进行相似专利识别模拟实验,本文模型召回率达到88.89%,实际应用效果较为优异。文本模态特征和图像模态特征结合可以有效提高相似专利识别准确率和效率,本文方法有助于提高专利检索效率,加快专利审查过程,辅助专利预警分析,加强知识产权的保护。[Purpose/Significance]The burgeoning number of patents poses significant challenges to patent retrieval,highlighting the urgent need for advanced computational techniques to identify similar patents.[Method/Process]This paper proposed a multimodal feature fusion method for similar patent identification.It utilized the BERT-wwm model and the ResNet-50 model to extract textual and image features of patents,respectively.By integrating self-attention and cross-attention mechanisms,the method effectively harnessed intra-modal feature information and inter-modal interaction information.Based on these,the model was trained and optimized for the similar patent identification.[Result/Conclusion]Empirical tests using IPC category“C08F10/00”data demonstrate that the model achieves an accuracy of 80.03%and a recall rate of 82.01%,outperforming baseline models.In simulations of similar patent identification,the model reaches a recall rate of 88.89%,indicating superior practical performance.The fusion of textual and image modal features significantly enhances the accuracy and efficiency of similar patent identification.This approach facilitates improved patent retrieval efficiency,accelerates the patent examination process,aids in patent alert analysis,and strengthens intellectual property protection.

关 键 词：多模态 文本特征 图像特征 自注意力 交叉注意力 特征融合 相似专利识别 

分 类 号：G306[文化科学]