[目的/意义] 在用户层面增强知识融合，使知识服务中用户需求嵌入的实现更为合理与可行。[方法/过程] 从作者知识元与语义知识元间的主题关系、合作关系和混合关系出发，设计神经网络下基于内容推荐、协同过滤推荐、混合推荐三类推荐思路的4种推荐算法及流程，并将数据集以“7+2+1”的形式划分训练集、测试集、校准集，进而构建用户需求挖掘型知识融合模式实现方案，并选用WoS数据库中的人工智能领域数据进行实现对比与结果验证。[结果/结论] 提出的基于内容推荐(C)、协同过滤推荐(CF)、内容推荐—协同推荐(CCF)、协同推荐—内容推荐(CFC)4种知识推荐模型及实现流程，输出结果可作为用户需求的辅助表征，支撑知识融合模式的实现，验证了“语义补充—语义推荐”路径的可行性。此外，CFC推荐在内容评估和量化评估中均有着显著高于其他模型的准确度。
[Purpose/Significance] This study aims to enhance knowledge fusion at the user level, enabling a more systematic and feasible approach to embedding user needs into knowledge services. [Method/Process] Based on the thematic, collaborative, and hybrid relationships between author knowledge elements and semantic knowledge elements, this paper designs four recommendation algorithms within a neural network framework. These algorithms are categorized into three types: content-based, collaborative filtering, and hybrid recommendation. The dataset is divided into training set, test set, and calibration set in a 7:2:1 ratio. An implementation framework for a knowledge fusion model to mine user needs is constructed. The artificial intelligence domain data in WoS database is selected for implementation comparison and result validation. [Result/Conclusion] This paper proposes four knowledge recommendation models: content-based(C), collaborative filtering(CF), content-based collaborative filtering(CCF), and collaborative filtering content-based recommendation(CFC). The outputs from these models can serve as an auxiliary representation for user needs, support the implementation of the knowledge fusion model, and validate the feasibility of the “semantic supplementation-semantic recommendation” path. In addition, the CFC recommendation model achieves significantly higher accuracy than other models in both content evaluation and quantitative evaluation.
[1] 赵蓉英,张心源.大数据环境对知识融合的影响研究[J].情报学报, 2017, 36(9):878-885.(ZHAO R Y, ZHANG X Y. Review of impact study of big data on knowledge fusion[J]. Journal of the China Society for scientific and Technical Information, 2017,36(9):878-885.)
[2] 尹丽英,赵捧未,秦春秀,等.科技管理数据服务模式创新:从多层用户需求分析[J].情报理论与实践, 2020, 43(4):82-88, 65.(YIN L Y, ZHAO P W, QIN C X, et al. Service patterns innovation of sci-tech management data:analysis of multi-level user demands[J]. Information studies:theory&application,2020, 43(4):82-88, 65.)
[3] 朱红涛,朱梦真,王思源,等.面向用户需求的高校未来学习中心服务优化研究[J].图书情报工作, 2024, 68(14):25-33.(ZHU H T, ZHU M Z, WANG S Y, et al. Research on service optimization in university future learning centers on user needs[J]. Library and information service, 2024, 68(14):25-33.)
[4] 臧振春,崔春生.基于Vague集理论一维属性--需求匹配的知识推荐算法研究[J].运筹与管理, 2020, 29(8):112-119.(ZANG Z C, CUI C S. Research on knowledgebased recommendation by one-dimensional of properties and requirement matching based on vague sets[J]. Operations research and management science, 2020, 29(8):112-119.)
[5] ROZANEC J, FORTUNA B, MLADENIC D. Knowledge graphbased rich and confidentiality preserving explainable artificial intelligence (XAI)[J]. Information fusion, 2022, 81:91-102.
[6] HUANG X, ZHU S, REN Y. A semantic matching method of e-government information resources knowledge fusion service driven by user decisions[J]. Journal of organizational and end user computing, 2023, 35(1):1-17.
[7] 黄新平,黄萃,张韫麒,等.面向决策的政府网站信息资源领域知识融合服务模型研究[J].图书情报工作, 2018,62(23):6-13.(HUANG X P, HUANG C, ZHANG Y Q, et al.Research on knowledge fusion service model of government website information resources in policy-making[J]. Library and information service, 2018, 62(23):6-13.)
[8] TARUS J K, NIU Z, MUSTAFA G. Knowledge-based recommendation:a review of ontology-based recommender systems for e-learning[J]. Artificial intelligence review, 2018,50(1):21-48.
[9] ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems:a survey of the state-of-the-art and possible extensions[J]. IEEE transactions on knowledge and data engineering, 2005, 17(6):734-749.
[10] LINDEN G, SMITH B, YORK J. Amazon.com recommendation:item-to-item collaborative filtering[J]. IEEE Internet computing,2003, 7(1):76-80.
[11] BERKE R. Hybrid recommender systems:survey and experiments[J]. User modeling and user-adapted interaction,2002, 12(4):331-370.
[12] ANTHIMOPOULOS M, CHRISTODOULIDIS S, EBNER L, et al. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network[J]. IEEE transactions on medical imaging, 2016, 35(5):1207-1216.
[13] 张岚泽,赵晓亮,刘津彤,等.基于空间-邻域自适应的图卷积神经网络信贷欺诈检测模型[J].数据分析与知识发现,2024, 8(4):137-151.(ZHANG L Z, ZHAO X L, LIU J T, et al.A graph convolutional credit fraud detection model with spatialneighborhood adaptability[J]. Data analysis and knowledge discovery, 2024, 8(4):137-151.)
[14] WANG S, PAN L, WU Y. Meta-information fusion of hierarchical semantics dependency and graph structure for structured text classification[J]. ACM transactions on knowledge discovery from data, 2023, 17(2):1-18.
[15] 石湘,刘萍.基于知识元语义描述模型的领域知识抽取与表示研究--以信息检索领域为例[J].数据分析与知识发现,2021, 5(4):123-133.(SHI X, LIU P. Extraction and representation of domain knowledge with semantic description model and knowledge elements:case study of information retrieval[J]. Data analysis and knowledge discovery, 2021, 5(4):123-133.)
[16] 李剑锋,陈海龙,翟军,等.完全冷启动下的个性化推荐算法[J].计算机工程与设计, 2024, 45(8):2329-2335.(LI J F, CHEN H L, ZHAI J, et al. Personalized recommendation algorithm under completely cold start[J]. Computer engineering and design, 2024, 45(8):2329-2335.)
