李文璋1* 郭海辰2,3* 李学恩3+
1.解放军63891部队;2.北京工商大学计算机与人工智能学院;3.中国科学院自动化研究所
摘要(Abstract):
针对传统人工设计实验方案的模式难以适应智能设备快速迭代需求的现状,提出了一种基于知识图谱与反馈的实验方案智能生成方法。该方法通过构建“知识建模-需求解析-方案生成-反馈优化”的闭环系统,可提升实验方案设计效率。该方法具体实现包含四个关键环节:首先基于实验领域的语料构建实验领域知识图谱,实现知识的结构化表征;接着,通过提取模型获取需求文档的关键要素,并激活图谱中相关知识形成动态背景知识空间;随后在知识约束下生成候选实验方案;最终引入人机协同反馈机制,通过优化策略实现背景知识的动态更新与方案持续优化。通过构建的实验领域数据集进行相关实验,实验结果证明了融合知识与反馈信息有助于提升实验方案的质量。为验证方法可应用性,研发了原型系统平台并开展案例验证,结果表明该方法可有效地提升实验方案设计的智能化水平和迭代效率。
关键词(KeyWords):
实验领域知识图谱;知识图谱增强生成;反馈信息收集;优化实验方案生成;原型系统平台
参考文献(References):
[1]韦正现.智能装备试验与测试的挑战与对策思考[J].测控技术,2021,40(02):1-5+12 .
[2]赵蕊蕊,于海跃,游雅倩,等.无人集群试验评估现状及技术方法综述[J].系统工程与电子技术,2024,46(02):570-585 .
[3]钟昊,郭永贞,宗孝鹏.基于知识图谱的智能决策辅助系统研究[C]//第九届中国指挥控制大会论文集.2021.
[4]Lewis M,Liu Y,Goyal N, et al.BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation,Translation,and Comprehension.[J].CoRR,2019, abs/1910 .13461
[5]YE LIU,YAO WAN,LIFANG HE,et al. KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning[C]//35th AAAI Conference on Artificial Intelligence: AAAI-21,Online,2-9 February 2021,v.7. AAAI Technical Tracks: Human-Computation and Crowd Sourcing; Humans and AI; Intelligent Robots; Knowledge Representation and Reasoning.:Association for the Advancement of Artificial Intelligence,2021:6418-6425.
[6]Ma Ningchen,Wang Dong,Bao Hongyun,et al. KEPL: Knowledge Enhanced Prompt Learning for Chinese Hypernym-Hyponym Extraction[C]//Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.2023: 5858-5867.
[7]顾滨兵,李军锋,王鑫.***智能装备试验鉴定的几点思考[J].火力与指挥控制,2024,49(07):162-168.
[8]李伟泽.基于C#的断路器产品型式试验方案自动生成系统的研究[J].市场监管与质量技术研究,2023,(01):41-44.
[9]Yu W, Zhu C, Li Z,et al.A Survey of Knowledge-enhanced Text Generation[J].ACM Computing Surveys,2022,54(11-Sup):38.
[10]Liang Y,He J,Li G,et al.Rich Human Feedback for Text-to-Image Generation[J].IEEE,2023.
[11]薛孟武,吴晓芳,黄振铭.面向电子对抗领域装备知识图谱的本体构建[J].空天预警研究学报,2024,38(05):331-335+341 .
[12]任秀丽,孔鑫,赵向东,等.装备运用领域的知识图谱构建与应用[J].装备制造技术,2024,(05):121-124.
[13]栾瑞鹏,张静,刘立坤.面向装备试验鉴定领域数据治理的知识图谱本体构建[J].系统工程与电子技术,2024,46(03):1013-1020.
[14]HYUNJOONG KANG,SANGHYUN HONG,KOOKJIN LEE, et al. On Integrating Knowledge Graph Embedding into SPARQL Query Processing[C]//2018 IEEE International Conference on Web Services: IEEE International Conference on Web Services(ICWS),2-7 July 2018,San Francisco,CA,USA.:Institute of Electrical and Electronics Engineers,2018:371-374.
[15]Shen W,Wang J,0001 H J .Entity Linking with a Knowledge Base: Issues,Techniques,and Solutions.[J].IEEE Trans. Knowl. Data Eng.,2015,27(2):443-460.
[16]张玥,李韧,杨建喜,等.基于深度神经网络的实体链接研究综述[J].中文信息学报,2024,38(08):1-14.
[17]SUNCONG ZHENG,FENG WANG,HONGYUN BAO, et al. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme[C]//55th annual meeting of the Association for Computational Linguistics: long papers,vol. 2: 55th annual meeting of the Association for Computational Linguistics(ACL 2017), 30 July-4 August 2017, Vancouver, Canada.:Association for Computational Linguistics,2017:1227-1236.
[18]ANTOINE BORDES,NICOLAS USUNIER,ALBERTO GARCIA-DURAN, et al. Translating Embeddings for Modeling Multi-relational Data[C]//Advances in Neural Information Processing Systems 26, vol. 4: 27th annual conference on Neural Information Processing Systems 2013,December 5-10,2013,Lake Tahoe, Nevada, USA.:Neural Information Processing Systems,2013:2799-2807.
[19]ZHEN WANG,JIANWEN ZHANG,JIANLIN FENG, et al. Knowledge Graph Embedding by Translating on Hyperplanes[C]//Proceedings of the twenty-eighth AAAI conference on artificial intelligence and the twenty-sixth innovative applications of artificial intelligence conference: 27-31 July 2014,Quebec Ciry,Quebec, Canada,v.2.:AAAI Press,2014:1112-1119.