自动化学报2025，Vol.51Issue(12)：2621-2632,12.DOI:10.16383/j.aas.c250094
"结构-内容"框架下融合时空特征的技术预测模型
A Technology Forecasting Model Integrating Spatiotemporal Features Under the"Structure-Content"Framework
摘要
Abstract
The development of science and technology is a dynamic,nonlinear,and complex evolutionary process.To enhance the precision of technological development predictions,this paper proposes a novel"structure-content"spatiotemporal technological forecasting model based on large language models,graph convolutional neural net-works,bidirectional long short-term memory neural networks,and robust stochastic configuration networks(RSCN).Firstly,by integrating graph convolutional neural networks and bidirectional long short-term memory neural networks,the model captures the spatial dependencies and temporal evolution patterns within technological networks,thereby overcoming the limitations of traditional forecasting models in terms of dynamic behavior and structural representation,and addressing the"pseudo-dynamic"and"static"constraints of conventional technolo-gical forecasting models.Secondly,the introduction of large language models enables dual semantic representation of node and edge features within the technological network,expanding the predictive framework from a single struc-tural dimension to a dual-dimensional"structure-content"analysis.This significantly enhances the model's ability to understand and represent information related to technological development.Finally,by incorporating RSCN,the model effectively addresses the challenges posed by extremely imbalanced data distributions,further improving the robustness and accuracy of predictions.The proposed forecasting framework outperforms various current technolo-gical forecasting methods across multiple metrics,providing strong support for advancing technological forecasting modeling and evaluating future technological development trajectories.关键词
科学技术发展/图卷积神经网络/大语言模型/双向长短期记忆神经网络/鲁棒随机配置网络Key words
Science and technology development/graph convolutional neural networks/large language models/bid-irectional long short-term memory neural networks/robust stochastic configuration networks引用本文复制引用
XI Xi,XU Wei,LIU Chuan-Bin,LIU Wei-Qian,SU Xin-Jie.."结构-内容"框架下融合时空特征的技术预测模型[J].自动化学报,2025,51(12):2621-2632,12.基金项目
国家自然科学基金面上项目(72473142,72374089)资助 Supported by National Natural Science Foundation of China(General Program)(72473142,72374089) （72473142,72374089）
