基于图神经网络链接预测与回归的新兴技术预测研究--以人工智能技术为例  

Research on Emerging Technology Prediction Based on Graph Neural Network Link Prediction and Regression——Taking Artificial Intelligence Technology as an Example

作　　者：肖君超 钟福利 张金玲[1] XIAO Junchao;ZHONG Fuli;ZHANG Jinling(Guangdong University of Technology Library,Guangzhou 510006,China;School of Systems Science and Engineering,Sun Yat-Sen University,Guangzhou 510275,China)

机构地区：[1]广东工业大学图书馆,广州510006 [2]中山大学系统科学与工程学院,广州510275

出　　处：《竞争情报》2024年第5期46-56,共11页Competitive Intelligence

基　　金：国家自然科学基金青年项目“面向服务韧性提升的空间网络系统评估及群智能优化方法研究”(编号:62102466)的研究成果之一。

摘　　要：面向专利文本数据的新兴技术预测对于协助管理者挖掘并聚焦技术发展方向、调整技术研发路线和占据技术竞赛主动具有重要意义。以人工智能技术为例,首先利用语法分析技术识别英文句子的名词短语,通过网络词语共现方法构造名词短语共现图。其次,构造图神经网络模型,并进行共现图链接预测和链接回归分析。最后,结合链接预测和链接回归结果,对人工智能技术进行技术预测。基于收集的专利数据进行预测实验,结果表明图神经网络融合名词短语共现图方法更适合复杂语义情形下的新兴技术预测,可获得更小预测识别粒度;此外,实验结果显示人工智能技术朝着电子会议、计算机视觉、医疗健康、交互界面、测量与监控、机器学习算法、传感器、数据通道和智能制造等方向应用发展。The prediction of emerging technologies based on patent text data is of great significance for managers,who must focus on the direction of technology development,adjust technology research and development routes,and take the initiative in technology competitions.Taking the AI technology as an example,firstly,use grammatical analysis technology to identify noun phrases in English sentences and construct a noun phrase co-occurrence graph through the network word co-occurrence method.Secondly,a graph neural network model is built to implement co-occurrence graph link prediction and regression.Finally,link prediction and link regression results are combined to make technical predictions for artificial intelligence technology.The experimental results show that using the graph neural network to fuse the noun phrase co-occurrence graph method is more suitable for the prediction of emerging technologies in complex semantic situations and can obtain smaller prediction recognition granularity;in addition,the prediction results show that artificial intelligence technology is forward to application development in electronic meetings,computer vision,medical health,interactive interfaces,measurement and monitoring,machine learning algorithms,sensors,data channels,and intelligent manufacturing.

关 键 词：新兴技术预测 图神经网络 链接预测 链接回归 名词短语 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程] G353.1[文化科学—情报学]