智能生成式设计——一种新的机械设计理念

doi:10.3901/JME.2025.24.267

摘要/Abstract

摘要： 随着生成式人工智能的快速发展，机械设计领域迎来新的变革。设计理念正逐渐由传统的“计算机辅助+人工经验”发展为具备高级智能化的“历史设计数据与知识+生成式模型”，具体设计行为由“人工建模”发展为“生成式建模”，机械产品设计驱动由人工经验发展为数据知识。针对这一种发展趋势，提出了新的机械设计理念：智能生成式设计，阐述了智能生成式设计的内容组成、核心运行机制、设计特点、关键技术等。在此基础上，探讨了智能生成式设计在机械产品设计上的应用价值，为机械产品的设计指明新趋势和发展方向。

关键词: 机械设计, 人工智能, 自主学习, 知识推理, 计算机辅助设计

Abstract: With the rapid development of generative artificial intelligence, the field of mechanical design has ushered in new changes. The design concept is gradually developed from the traditional “computer-aided + artificial experience” to “historical design data and knowledge + generative modeling” with advanced intelligence, and specific design behavior is developed from “manual modeling” to “generative modeling”, and the mechanical product design driver is developed from manual experience to data knowledge. In response to this development trend, a new mechanical design concept is proposed: Intelligent generative design (IGD). The content composition, core operation mechanism, design features, and key technologies of IGD are described in this article. On this basis, this study explores the application value of IGD in mechanical product design, and points out the new trend and development direction for the design of mechanical products.

Key words: mechanical design, artificial intelligence, independent learning, knowledge reasoning, computer-aided design

中图分类号:

TH122

宁方伟, 鲁嘉星, 王一轩, 马玉山, 黎磊, 李赫然, 石岩. 智能生成式设计——一种新的机械设计理念[J]. 机械工程学报, 2025, 61(24): 267-284.

NING Fangwei, LU Jiaxing, WANG Yixuan, MA Yushan, LI Lei, LI Heran, SHI Yan. Intelligent Generative Design—A New Mechanical Design Concept[J]. Journal of Mechanical Engineering, 2025, 61(24): 267-284.

参考文献

[1] CAMBA J D,COMPANY P,NAYA F. Sketch-based modeling in mechanical engineering design:Current status and opportunities[J]. Computer-Aided Design,2022,150:103283.
[2] CHALAMALASETTI G S. A novel application of computer vision and deep learning for assessing mechanical engineering drawings[M]. Regina:The University of Regina,2021.
[3] MA W,CHEN S,LOU Y,et al. Draw step by step:reconstructing cad construction sequences from point clouds via multimodal diffusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,16-22 June,2024,Seattle,WA,USA. NewYork:IEEE, 2024:27154-27163.
[4] 程锦,叶虎强,冯劲松,等. 三维CAD软件性能自动化测试与变粒度可视评价[J]. 西安交通大学学报,2023,57(8):92-104. CHENG Jin,YE Huqiang,FENG Jinsong. Automatic testing and variable-granularity visual evaluation of the performance of 3D CAD software[J]. Journal of Xi'an Jiaotong University. 2023,57(8):92-104.
[5] HUNDE B R,WOLDEYOHANNES A D. Future prospects of computer-aided design (CAD)-A review from the perspective of artificial intelligence (AI),extended reality,and 3D printing[J]. Results in Engineering,2022,14:100478.
[6] 龙辉,郝佳,牛红伟,等. 基于情境的CAD模型手势操控技术[J]. 机械工程学报,2022,58(10):374-382. LONG Hui,HAO Jia,NIU Hongwei,et al. Gesture control technology of CAD model based on situation model[J]. Journal of Mechanical Engineering,2022,58(10):374-382.
[7] 程锦,吕昊,刘振宇,等. 考虑多源不确定性的三维CAD软件质量综合评价[J]. 机械工程学报,2024,60(13):235-246. CHENG Jin,LÜ Hao,LIU Zhenyu,et al. Comprehensive quality evaluation of 3D CAD software considering multi-source uncertainties[J]. Journal of Mechanical Engineering,2024,60(13):235-246.
[8] 程锦,叶虎强,谭建荣,等. 三维CAD技术研究进展及其发展趋势综述[J]. 机械工程学报,2023,59(23):158-185. CHENG Jin,YE Huqiang,TAN Jianrong,et al. Review of research progress and development trends of 3D CAD technology[J]. Journal of Mechanical Engineering,2023,59(23):158-185.
[9] MA L,SHARMA A. Research on 3D CAD design of manufacturing domain integration system based on cloud computing[J]. Computer-Aided Design & Applications,2022.
[10] 华顺刚,谢守广,刘斌,等. 基于CAD模型参数和MHD度量的装配体检索研究[J]. 机械工程学报,2022,58(16):384-390. HUA Shungang,XIE Shouguang,LIU Bin,et al. Study on assembly retrieval based on CAD model parameters and MHD metric[J]. Journal of Mechanical Engineering,2022,58(16):384-390.
[11] NING F,SHI Y,CAI M,et al. Manufacturing cost estimation based on a deep-learning method[J]. Journal of Manufacturing Systems,2020,54:186-195.
[12] NING F,SHI Y,CAI M,et al. Part machining feature recognition based on a deep learning method[J]. Journal of Intelligent Manufacturing,2023,34(2):809-821.
[13] HOU J,LUO C,QIN F,et al. FuS-GCN:Efficient B-rep based graph convolutional networks for 3D-CAD model classification and retrieval[J]. Advanced Engineering Informatics,2023,56:102008.
[14] ALZUBAIDI L,ZHANG J,HUMAIDI A J,et al. Review of deep learning:Concepts,cnn architectures,challenges,applications,future directions[J]. Journal of big Data,2021,8:1-74.
[15] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[J]. Advances in Neural Information Processing Systems,2017,30:1706.
[16] 白辰甲,许华哲,李学龙. 大模型驱动的具身智能:发展与挑战[J]. 中国科学:信息科学,2024,54(9):1-48. BAI Chenjia,XU Huazhe,LI Xuelong. Embodied-AI with large models:Research and challenges[J]. Scientia Sinica(Informationis),2024,54(9):1-48.
[17] CAMBA J D,CONTERO M,COMPANY P. Parametric CAD modeling:An analysis of strategies for design reusability[J]. Computer-Aided Design,2016,74:18-31.
[18] GAI Z,YANG T. The application of CAD combined deep learning algorithms in advertising creative design[J]. Computer-Aided Design & Applications, 2024,21(S18):290-305.
[19] XU P,ZHU X,CLIFTON D A. Multimodal learning with transformers:A survey[J]. IEEE Transactions on Pattern Analysis Machine Intelligence,2023,45(10):12113-12132.
[20] 车万翔,窦志成,冯岩松,等. 大模型时代的自然语言处理:挑战、机遇与发展[J]. 中国科学:信息科学,2023,53(9):1645-1687. CHE Wanxiang,DOU Zhicheng,FENG Yansong,et al. Towards a comprehensive understanding of the impact of large language models on natural language processing:Challenges,opportunities and future directions[J]. Scientia Sinica(Informationis),2023,53(9):1645-1687.
[21] 周涛,李鑫,周俊临,等. 大模型智能体:概念、前沿和产业实践[J]. 电子科技大学学报,2024,26(4):57-62. ZHOU Tao,LI Xin,ZHOU Junlin,et al. AI large model ai-agents large-model-based agents[J]. Journal of University of Electronic Science and Technology of China,2024,26(4):57-62.
[22] DING Y,YU J,LIU B,et al. Mukea:Multimodal knowledge extraction and accumulation for knowledge-based visual question answering[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,June 18-24,2022,New Orleans,LA,USA. NewYork:IEEE,2022:5089-5098.
[23] 何俊,张彩庆,李小珍,等. 面向深度学习的多模态融合技术研究综述[J]. 计算机工程与科学,2020,46(5):11. HE Jun,ZHANG Caiqing,LI Xiaozhen,et al. Survey of research on multimodal fusion technology for deep learning[J]. Computer Engineering,2020,46(5):11.
[24] 张正,徐勇,卢光明. 数据分析的结构化表征学习[M]. 北京:人民邮电出版社,2022. ZHANG Zheng,XU Yong,LU Guangming. Structured reprentation learning for data analys[M]. Beijing:Posts & Telecom Press,2022.
[25] 胡志强,刘鸣飞,李琦,等. 基于多源异构数据的风机多模态装配工艺知识图谱建模[J]. 上海交通大学学报,2024,58(8):1249-1263. HU Zhiqiang,LIU Mingfei,LI Qi,et al. Modeling of multi-modal knowledge graph for assembly process of wind turbines with multi-source heterogeneous data[J]. Journal of Shanghai Jiao Tong University,2024,58(8):1249-1263.
[26] 杜鹏飞,李小勇,高雅丽. 多模态视觉语言表征学习研究综述[J]. 软件学报,2021,32(2):327-348. DU Pengfei,LI Xiaoyong,GAO Yali. Survey on multimodal visual language representation learning[J]Journal of Software,2021,32(2):327-348.
[27] 杨宏宇,马建辉,侯旻,等. 基于多模态对比学习的代码表征增强预训练方法[J]. 软件学报,2024,35(4):1601-1617. YANG Hongyu,MA Jianhui,HOU Min,et al. Hou minpre-training method for enhanced code representation based on multimodal contrastive learning[J]. Journal of Software,2024,35(4):1601-1617.
[28] 刘静,郭龙腾. GPT-4对多模态大模型在多模态理解,生成,交互上的启发[J]. 中国科学基金,2023,5:793-802. LIU Jing,GUO Longteng. Inspiration of GPT-4on multimodal foundation models in multimodal understanding,generation,and interaction[J]. Fundamental Research,2023,5:793-802.
[29] 汪美玲,邵伟,张道强. 基于标签对齐的多模态一致性表型关联方法[J]. 软件学报,2022,33(12):4545-4558. WANG Meiling,SHAO Wei,ZHANG Daoqiang. Label-aligned multi-modality consistent phenotype association method[J]. Journal of Software,2022,33(12):4545-4558.
[30] HU R,SINGH A. Unit:Multimodal multitask learning with a unified transformer[C]//Proceedings of the IEEE/CVF international conference on computer vision,October 10-17,2021,Montreal,QC,Canada. NewYork:IEEE,2021:1439-1449.
[31] 曹建军,聂子博,郑奇斌,等. 跨模态数据实体分辨研究综述[J]. 软件学报,2023,34(12):5822-5847. CAO Jianjun,NIE Zibo,ZHENG Qibin,et al. Survey on cross-modal data entity resolution[J]. Journal of Software,2023,34(12):5822-5847.
[32] CHEN H,JIANG D,SAHLI H. Transformer encoder with multi-modal multi-head attention for continuous affect recognition[J]. IEEE Transactions on Multimedia,2020,23:4171-4183.
[33] 赵鹏,马泰宇,李毅,等. 融合全模态自编码器和生成对抗机制的跨模态检索[J]. 计算机辅助设计与图形学学报,2021,33(10):1486-1494. ZHAO Peng,MA Taiyu,LI Yi,et al. Cross-modal retrieval based on full-modal autoencoder with generative adversarial mechanism[J]. Journal of Computer-Aided Design & Computer Graphics,2021,33(10):1486-1494.
[34] RICHARDSON E,ALALUF Y,PATASHNIK O,et al. Encoding in style:a stylegan encoder for image-to-image translation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,June 19-25,2021,Nashville,USA. NewYork:IEEE Computer Society Press,2021:2287-2296.
[35] 王德文,魏波涛. 基于孪生变分自编码器的小样本图像分类方法[J]. 智能系统学报,2021,16(2):254-262. WANG Dewen,WEI Botao. A small-sample image classification method based on a Siamese variational auto-encoder[J]. CAAI Transactions on Intelligent Systems,2021,16(2):254-262.
[36] XIA M,ZHAO X,HU X. Machining feature and topological relationship recognition based on a multi-task graph neural network[J]. Advanced Engineering Informatics,2024,62:102721.
[37] QIAO Z,ZHOU Y,YANG D,et al. Seed:Semantics enhanced encoder-decoder framework for scene text recognition[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. June 13-19,2020,Seattle,USA. NewYork:IEEE Computer Society Press,2020:13528-13537.
[38] 吴福祥,程俊. 基于自编码器生成对抗网络的可配置文本图像编辑[J]. 软件学报,2022,33(9):3139-3151. WU Fuxiang,CHENG Jun. Configurable text-based image editing by autoencoder-based generative adversarial networks[J]. Journal of Software,2022,33(9):3139-3151.
[39] 兰猛,张乐飞,杜博,等. 基于时空层级查询的指代视频目标分割[J]. 中国科学:信息科学,2024,54(3):674-91. LAN Meng,ZHANG Lefei,DU Bo,et al. Spatio-temporal hierarchical query for referring video object segmentation[J]. Scientia Sinica (Informationis),2024,54(3):674-691.
[40] CHEN X,JIA S,XIANG Y. A review:Knowledge reasoning over knowledge graph[J]. Expert Systems with Applications,2020,141:112948.
[41] 黄勃,吴申奥,王文广,等. 图模互补:知识图谱与大模型融合综述[J]. 武汉大学学报,2024,70(4):397-412. HUANG Bo,WU Shenao,WANG Wenguang,et al. KG-LLM-MCom:A survey on integration of knowledge graph and large language model[J]. Journal of Wuhan University,2024,70(4):397-412.
[42] WANG Y,TANG S,ZHU F,et al. Revisiting the transferability of supervised pretraining:an MLP perspective[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-24,2022,New Orleans,LA,USA. NewYork:IEEE,2022:9183-9193.
[43] LIN H,CHENG X,WU X,et al. Cat:Cross attention in vision transformer[C]//2022 IEEE International Conference on Multimedia and Expo (ICME),July 18-22,2022,Taipei,China. NewYork:IEEE,2022:1-6.
[44] FENG J,LIN M,SHANG L,et al. Autonomous aspect-image instruction a2II:Q-Former guided multimodal sentiment classification[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics,Language Resources and Evaluation (2024),May 20-25,2024,Torino,Italy. Torino:LREC-COLING. 2024:1996-2005.
[45] LIU C,SUN K,ZHOU Q,et al. Cpmi-chatglm:Parameter-efficient fine-tuning chatglm with chinese patent medicine instructions[J]. Scientific Reports,2024,14(1):6403.
[46] SANDMANN S,RIEPENHAUSEN S,PLAGWITZ L,et al. Systematic analysis of ChatGPT,Google search and Llama 2 for clinical decision support tasks[J]. Nature Communications,2024,15(1):1-8.
[47] ZHANG L,LIU Y,LUO Y,et al. Qwen-ig:A qwen-based instruction generation model for llm fine-tuning[C]//Proceedings of the 202413th International Conference on Computing and Pattern Recognition. Association for Computing Machinery,October 25-272024,Tianjin,China. NewYork:ACM,2025:295-302
[48] BARBIERI L,BRAMBILLA M,STEFANUTTI M,et al. A tiny transformer-based anomaly detection framework for IoT solutions[J]. IEEE Open Journal of Signal Processing,2023,4:462-478.
[49] ALMEIDA L B. Multilayer perceptrons[M]. Handbook of Neural Computation. Carabas:CRC Press,2020.
[50] HEDLIN E,SHARMA G,MAHAJAN S,et al. Unsupervised semantic correspondence using stable diffusion[J]. Advances in Neural Information Processing Systems,2023,36:8266-8279.
[51] LIU H,YUAN Y,LIU X,et al. Audioldm 2:Learning holistic audio generation with self-supervised pretraining[J]. IEEE/ACM Transactions on Audio,2024,32:2871-2883.
[52] JI S,PAN S,CAMBRIA E,et al. A survey on knowledge graphs:representation,acquisition,and applications[J]. IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514.
[53] 缪青海,王兴霞,杨静,等. 从基础智能到通用智能:基于大模型的GenAI和AGI之现状与展望[J]. 自动化学报,2024,50(4):674-687. MIAO Qinghai,WANG Xingxia,YANG Jing,et al. From foundation intelligence to general intelligence:The state-of-art and perspectives of genai and agi based on foundation models[J]. Acta Automatica Sinica,2024,50(4):674-687.
[54] TOMCZAK J M. Why deep generative modeling?[M]. NewYork:Springe,2021.
[55] 宋雪萌,聂礼强,申恒涛,等. 融合预训练技术的多模态学习研究专题前言[J]. 软件学报,2023,34(5):1997-1999. SONG Xuemeng,NIE Liqiang,SHEN Hengtao,et al. Introduction to the research on multimodal learning with fusion of pre-training techniques[J]. Journal of Software,2023,34(5):1997-1999.
[56] WANG P,LIU W,YOU Y. A hybrid framework for manufacturing feature recognition from CAD models of 3-axis milling parts[J]. Advanced Engineering Informatics,2023,57:102073.
[57] 姚鑫骅,于涛,封森文,等. 基于图神经网络的零件机加工特征识别方法[J]. 浙江大学学报,2024,58(2):349-359. YAO Xinhua, YU Tao, FENG Senwen,et al. Recognition method of parts machining features based on graph neural network[J]. Journal of Zhejiang University,2024,58(2):349-359.
[58] LEE H,LEE J,KWON S,et al. Simplification of 3d cad model in voxel form for mechanical parts using generative adversarial networks[J]. Computer-Aided Design,2023,163:103577.
[59] 龚靖渝,楼雨京,柳奉奇,等. 三维场景点云理解与重建技术[J]. 中国图象图形学报,2023,28(6):1741-1766. GONG Jingyu,LOU Yujing,LIU Fengqi,et al. Scene point cloud understanding and reconstruction technologies in 3D space[J]. Journal of Image and Graphics,28(6):1741-1766.
[60] 张虎成,李雷孝,刘东江. 多模态数据融合研究综述[J]. 计算机科学与探索,2024,18(10):2501-2520. ZHANG Hucheng,LI Leixiao,LIU Dongjiang. Survey of multimodal data fusion research[J]. Journal of Frontiers of Computer Science and Technology,2024,18(10):2501-2520.
[61] 田枫,宗内丽,刘芳,等. 多模态融合的三维目标检测方法研究[J]. 计算机工程与应用,2024,60(13):113-123. TIAN Feng,ZONG Neili,LIU Fang,et al. Research on 3D object detection method based on multi-modal fusion[J]. Computer Engineering and Applications,2024,60(13):113-123.
[62] 叶志鸿,吴运兵,戴思翀,等. 多级融合知识图谱补全模型[J]. 计算机科学与探索,2025,19(3):1-15. YE Zhihong,WU Yunbing,DAI Sichong,et al. Multi-level fusion knowledge graph completion model[J]. Journal of Frontiers of Computer Science and Technology,2025,19(3):1-15.
[63] 吕友豪,贾袁骏,庄圆,等. 基于多模态信息融合的四足机器人避障方法[J]. 工程科学学报,2024,46(8):1426-1433. LÜ Youhao,JIA Yuanjun,ZHUANG Yuan,et al. Obstacle avoidance approach for quadruped robot based on multi-modal information fusion[J]. Chinese Journal of Engineering,2024,46(8):1426-1433.
[64] 李雄,苏建宁,张志鹏,等. 特征迁移的细粒度产品形态智能决策方法[J]. 计算机辅助设计与图形学学报,2024,36(1):47-62. LI Xiong,SU Jianning,ZHANG Zhipeng,et al. Intelligent decision-making of fine-grained product form with feature transfer[J].Journal of Computer-Aided Design & Computer Graphics,2024,36(1):47-62.
[65] 刘学博,户保田,陈科海,等. 大模型关键技术与未来发展方向——从ChatGPT谈起[J]. 中国科学基金,2023,37(5):758-766. LIU Xuebo,HU Baotian,CHEN Kehai,et al. Key technologies and future development directions of largelanguage models:Insights from chatgpt[J]. Fundamental Research,2023,37(5):758-766.
[66] 李国杰. 智能化科研(AI4R):第五科研范式[J]. 中国科学院院刊,2024,39(1):1-9. LI Guojie. AI4R:The fifth scientific research paradigm[J]. Bulletin of Chinese Academy of Sciences,2024,39(1):1-9.
[67] 袁小锋,王雅琳,阳春华,等. 深度学习在流程工业过程数据建模中的应用[J]. 智能科学与技术学报,2020,2(2):107-115. YUAN Xiaofeng,WANG Yalin,YANG Chunhua,et al. The application of deep learning in data-driven modeling of process industries[J]. Chinese Journal of Intelligent Science and Technology,2020,2(2):107-115.
[68] CHAI C P. The importance of data cleaning:Three visualization examples[J]. Chance,2020,33(1):4-9.
[69] FALLAHIAN M,DORODCHI M,KRETH K. Gan-based tabular data generator for constructing synopsis in approximate query processing:Challenges and solutions[J]. Machine Learning and Knowledge Extraction,2024,6(1):171-198.
[70] 刘冬,袁利恒,丛明. 齿轮机器人复杂装配过程在线建模与参数优化[J]. 机械工程学报,2021,57(13):124-131. LIU Dong,YUAN Liheng,CONG Ming. Online modeling and parameter optimization method for robotic complex assembly process of gear[J]. Journal of Mechanical Engineering,2021,57(13):124-131.
[71] DEWI C,CHEN R C,LIU Y T,et al. Synthetic data generation using dcgan for improved traffic sign recognition[J]. Neural Computing and Applications,2022,34(24):21465-21480.
[72] 葛轶洲,许翔,杨锁荣,等. 序列数据的数据增强方法综述[J]. 计算机科学与探索,2021,15(7):1207-1219. GE Yizhou,XU Xiang,YANG Suorong,et al. Survey on sequence data augmentation[J]. Journal of Frontiers of Computer Science and Technology,2021,15(7):1207-1219.
[73] HUANG J,CUI K,GUAN D,et al. Masked generative adversarial networks are data-efficient generation learners[J]. Advances in Neural Information Processing Systems,2022,35:2154-2167.
[74] ZEBARI R,ABDULAZEEZ A,ZEEBAREE D,et al. A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction[J]. Journal of Applied Science Technology Trends,2020,1(1):56-70.
[75] 吕天根,洪日昌,何军,等. 多模态引导的局部特征选择小样本学习方法[J]. 软件学报,2022,34(5):2068-2082. LÜ Tiangen,HONG Richang,HE Jun,et al. Multimodal-guided local feature selection for few-shot learning[J]. Journal of Software,2022,34(5):2068-2082.
[76] DUAN H,SUN Y,CHENG W,et al. Gesture recognition based on multi-modal feature weight[J]. Concurrency and Computation:Practice and Experience,2021,33(5):e5991.
[77] HOU Z,LIU Y,ZHANG L. POS-GIFT:A geometric and intensity-invariant feature transformation for multimodal images[J]. Information Fusion,2024,102:102027.
[78] ZHENG Y,HUANG D,LIU S,et al. Cross-domain object detection through coarse-to-fine feature adaptation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. June 13-19,2020,Seattle,USA. NewYork:IEEE Computer Society Press,2020:13766-13775.
[79] ZHONG L,WU J,LI Q,et al. A comprehensive survey on automatic knowledge graph construction[J]. ACM Computing Surveys,2023,56(4):1-62.
[80] 陈强,张栋,李寿山,等. 融合任务知识的多模态知识图谱补全[J]. 软件学报,2024(4):1590-1603. CHEN Qiang,ZHANG Dong,LI Shoushan,et al. Task knowledge fusion for multimodal knowledge graph completion[J]. Journal of Software,2024(4):1590-1603.
[81] 韩铖山,李红辉,闫佳和,等. 基于知识图谱的多源异构信息通道耦合技术研究[J]. 集成技术,2023,12(3):48-60. HAN Chengshan,LI Honghui,YAN Jiahe,et al. Research on coupling technology of multi-source heterogeneous information channels based on knowledge graph[J]. Journal of Integration Technology,2023,12(3):48-60.
[82] 毕忠勤,张锴,单美静,等. 基于图神经网络的多源异构知识增强对话模型[J]. 科学技术与工程,2024,24(17):7196-7204. BI Zhongqin,ZHANG Kai,SHAN Meijing,et al. Multi-source heterogeneous knowledge enhanced dialogue model based on graph neural network[J]. Science Technology and Engineering,2024,24(17):7196-7204.
[83] 郝小芳,张超群,李晓翔,等. 融合交互注意力网络的实体和关系联合抽取模型[J]. 计算机工程与应用,2024,60(8):156-164. HAO Xiaofang,ZHANG Chaoqun,LI Xiaoxiang,et al. Joint entity relation extraction model based on interactive attention[J]. Computer Engineering and Applications,2024,60(8):156-164.
[84] DAI G,WANG X,ZOU X,et al. Mrgat:Multi-relational graph attention network for knowledge graph completion[J]. Neural Networks,2022,154:234-245.
[85] WANG M,QI G,WANG H,et al. Richpedia:A comprehensive multi-modal knowledge graph[C]//Semantic Technology:9th Joint International Conference,November 25-27,2019,Hangzhou,China. NewYork:Springer,2020:130-145.
[86] 孔德明,李晓伟,杨庆鑫. 基于伪点云特征增强的多模态三维目标检测方法[J]. 计算机学报,2024,47(4):759-775. KONG Deming,LI Xiaowei,YANG Qingxin. Multimodal 3d obiect detection method based on pseudopoint cloud feature enhancement[J]. Chinese Journal of Computers,2024,47(4):759-775.
[87] YANG Z,XU B,LUO W,et al. Autoencoder-based representation learning and its application in intelligent fault diagnosis:A review[J]. Measurement,2022,189:110460.
[88] 管浩良,张广滨,王岩. 融合特征金字塔和自注意力机制的SAR三维点云目标识别方法[J]. 信号处理,2025,41(1):70-83. GUAN Haoliang,ZHANG Guangbin,WANG Yan. Fusing feature pyramid and self-attention mechanism for sar 3d point cloud target recognition[J]. Journal of Signal Processing,2025,41(1):70-83.
[89] 吴萌,严瑞祺,孙增国,等. 三维点云双重补全网络[J]. 计算机工程与应用,2025,61(7):297-305. WU Meng,YAN Ruiqi,SUN Zengguo,et al. 3D point cloud dual completion network[J]. Computer Engineering and Applications,2025,61(7):297-305.
[90] 杨军,张琛. 融合双注意力机制和动态图卷积神经网络的三维点云语义分割[J]. 北京航空航天大学学报,2023,50(10):2984-2994. YANG Jun,ZHANG Chen. Semantic segmentation of 3D point cloud by fusing dual attention mechanism and dynamic graph convolution neural network[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,50(10):2984-2994.
[91] 吴亦奇,韩放,张德军,等. 基于特征通道和空间位置注意力的三维点云特征学习网络[J]. 计算机工程与科学,2022,44(7):1239. WU Yiqi,HAN Fang,ZHANG Dejun,et al. A 3D point cloud feature learning network based on feature channel and spatial position attentions[J]. Computer Engineering & Science,2022,44(7):1239.
[92] NIU Z,ZHONG G,YU H. A review on the attention mechanism of deep learning[J]. Neurocomputing,2021,452:48-62.
[93] 宫丽娜,周易人,乔羽,等. 预训练模型在软件工程领域应用研究进展[J]. 软件学报,2025,36(1):1-26. GONG Lina,ZHOU Yiren,QIAO Yu,et al. Research progress of pre-trained model in software engineering[J],Journal of Software,2025,36(1):1-26.
[94] 曾焕强,胡浩麟,林向伟,等. 深度神经网络压缩与加速综述[J]. 信号处理,2022,38(1):183-194. ZENG Huanqiang,HU Haolin,LIN Xiangwei,et al. Deep neural network compression and acceleration:an overview[J]. Journal of Signal Processing,2022,38(1):183-194.
[95] GANDHI A,ADHVARYU K,PORIA S,et al. Multimodal sentiment analysis:A systematic review of history,datasets,multimodal fusion methods,applications,challenges and future directions[J]. Information Fusion,2023,91:424-444.
[96] ZHU Y,WU L,GUO Q,et al. Collaborative large language model for recommender systems[C]//Proceedings of the ACM Web Conference 2024,May 13-17,2024,Singapore:ICPS,2024:3162-3172.
[97] WANG Y,REDDY R G,MUJAHID Z M,et al. Factcheck-bench:Fine-grained evaluation benchmark for automatic fact-checkers[C]//In Findings of the Association for Computational Linguistics,November,2024,Miami,Florida,USA. Miami:Association for Computational Linguistics, 2023:14199-14230.
[98] 张明悦,金芝,刘坤. 合作-竞争混合型多智能体系统的虚拟遗憾优势自博弈方法[J]. 软件学报,2024,35(2):739-757. ZHANG Mingyue,JIN Zhi,LIU Kun. Counterfactual regret advantage-based self-play approach for mixed cooperative-competitive multi-agent systems[J]. Journal of Software,2024,35(2):739-757.
[99] ZHOU L,DENG X,WANG Z,et al. Semantic information extraction and multi-agent communication optimization based on generative pre-trained transformer[J]. IEEE Transactions on Cognitive Communications and Networking,2025,11(2):725-737.
[100] KANNAN S S,VENKATESH V L N,MIN B C. Smart-llm:smart multi-agent robot task planning using large language models[C]//2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),14-18,October,2024,Abu Dhabi:IEEE. 2024:12140-12147.
[101] YAO S,ZHAO J,YU D,et al. React:Synergizing reasoning and acting in language models[C]//International Conference on Learning Representations (ICLR),May 1-5,2023,Kigali,Rwanda. Kigali:OpenReview,2023:1-33.
[102] WEI J,WANG X,SCHUURMANS D,et al. Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in Neural Information Processing Systems,2022,35:24824-24837.
[103] 黄峻,林飞,杨静,等. 生成式AI的大模型提示工程:方法,现状与展望[J]. 智能科学与技术学报,2024,6(2):115-133. HUANG Jun,LIN Fei,YANG Jing,et al. From prompt engineering to generative artificial intelligence for large models:The state of the art and perspective[J]. Chinese Journal of Intelligent Science and Technology,2024,6(2):115-133.
[104] YIN X,NI C,WANG S. Multitask-based evaluation of open-source llm on software vulnerability[J]. IEEE Transactions on Software Engineering,2024,50(11):3071-3087.
[105] 赵睿卓,曲紫畅,陈国英,等. 大语言模型评估技术研究进展[J]. 数据采集与处理,2024,39(3):502-523. ZHAO Ruizhuo,QU Zichang,CHEN Guoying,et al. Research progress in evaluation techniques for large language models[J]. Journal of Data Acquisition & Processing,2024,39(3):502-523.
[106] ZHANG W,ALJUNIED M,GAO C,et al. M3exam:A multilingual,multimodal,multilevel benchmark for examining large language models[J]. Advances in Neural Information Processing Systems,2023,36:5484-5505.
[107] STRUBELL E,GANESH A,MCCALLUM A. Energy and policy considerations for deep learning in NLP[C]//In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,July 28th to August 2nd,2019,Florence,Italy. Florence:Association for Computational Linguistics,2019:3645-3650.
[108] WANG J,HUANG Y,CHEN C,et al. Software testing with large language models:Survey,landscape,and vision[J]. IEEE Transactions on Software Engineering,2024,50(4):911-936.
[109] DULNY A,HOTHO A,KRAUSE A. DynaBench:A benchmark dataset for learning dynamical systems from low-resolution data[C]//Machine Learning and Knowledge Discovery in Databases:Research Track,September 18-22,2023,Turin,Italy. NewYork:Springer,2023:438-555.