[1]黄慧玲,郭荣新,施一帆.面向可信推理与语义补全的区块链知识图谱共享框架[J].华侨大学学报(自然科学版),2025,46(5):539-550.[doi:10.11830/ISSN.1000-5013.202508020]
　HUANG Huiling,GUO Rongxin,SHI Yifan.Knowledge Graph Sharing Framework With Blockchain for Trustworthy Inference and Semantic Completion[J].Journal of Huaqiao University(Natural Science),2025,46(5):539-550.[doi:10.11830/ISSN.1000-5013.202508020]
点击复制

面向可信推理与语义补全的区块链知识图谱共享框架()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第5期
页码:
539-550
栏目:
出版日期:
2025-09-20

文章信息/Info

Title:
Knowledge Graph Sharing Framework With Blockchain for Trustworthy Inference and Semantic Completion
文章编号:
1000-5013(2025)05-0539-12
作者:
黄慧玲;  郭荣新;  施一帆
华侨大学 工学院, 福建 泉州 362021
Author(s):
HUANG Huiling;  GUO Rongxin;  SHI Yifan
College of Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
区块链;  门限签名算法;  大语言模型;  知识图谱推理;  协同优化
Keywords:
blockchain;  threshold signature algorithm;  large language model;  knowledge graph reasoning;  collaborative optimization
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.202508020
文献标志码:
A
摘要:
针对当前区块链驱动的知识共享架构在异构知识图谱整合、可信交互与系统效率方面面临的挑战,提出一种基于区块链的知识图谱可信推理框架(BKTRF)。首先,通过去中心化预言机实现链上与链下推理结果的可信传输,并采用基于门限机制的BLS签名算法提升多节点协同签名的效率与容错性,降低链上计算与存储开销。然后,引入基于大语言模型的知识图谱补全方法,自动生成高质量逻辑规则,以支持语义补全与推理优化。结果表明:相较于BLS签名算法,门限BLS签名算法的签名效率最高可提升53.5%;在3个数据集上,BKTRF表现出更优的补全效果与泛化能力。
Abstract:
To address challenges faced by current blockchain-driven knowledge sharing architectures in heterogeneous knowledge graph integration, trusted interaction, and system efficiency, a blockchain-based knowledge graph trusted reasoning framework(BKTRF)is proposed. First, the trusted transmission of on-chain and off-chain reasoning results are achieved through decentralized oracles, and the BLS signature algorithm based on a threshold mechanism is employed to enhance the efficiency and fault tolerance of multi-node collaborative signatures while reducing on-chain computational and storage overhead. Then, a large language model-based knowledge graph completion method is introduced to automatically generate high-quality logic rules for semantic completion and reasoning optimization. The results show that compared to the standard BLS signature algorithm, the threshold BLS signature algorithm can improve signing efficiency by up to 53.5%. In addition, BKTRF demonstrates superior completion performance and generalization capability across three datasets.

参考文献/References:

[1] RAZZAQ A.Blockchain-based secure data transmission for internet of underwater things[J].Cluster Computing,2022,25(6):4495-4514.
[2] ROTMENSCH M,HALPERN Y,TLIMAT A,et al.Learning a health knowledge graph from electronic medical records[J].Scientific Reports,2017,7(1):5994.
[3] JI Shengwei,LIU Longfei,XI Jizhong,et al.KLR-KGC: Knowledge-guided LLM reasoning for knowledge graph completion[J].Electronics,2024,13(24):5037.
[4] SHAMIR A.How to share a secret[J].Communications of the ACM,1979,22(11):612-613.DOI:10.1145/359168.359176.
[5] CHEN Huajun,HU Ning,QI Guilin,et al.OpenKG Chain: A blockchain infrastructure for open knowledge graphs[J].Data Intelligence,2021,3(2):205-227.DOI:10.1162/dint_a_00095.
[6] JAYABALASAMY G,PUJOL C,BHASKARAN K L.Application of graph theory for blockchain technologies[J].Mathematics,2024,12:1133.DOI:10.3390/math12081133.
[7] TSOULIAS K,PALAIOKRASSAS G,FRAGKOS G,et al.A graph model based blockchain implementation for increasing performance and security in decentralized ledger systems[J].IEEE Access,2020,8:130952-130965.
[8] ZHANG Haibao,JIANG Wenbao,JIN Ding.A blockchain network admission control mechanism using anonymous identity-based cryptography[J].Applied Sciences,2025,15:130.DOI:10.3390/app15010130.
[9] CALDARELLI G.Understanding the blockchain oracle problem: A call for action[J].Information,2020,11:509.DOI:10.3390/info11110509.
[10] CHANDAK P,HUANG Kexin,ZITNIK M.Building a knowledge graph to enable precision medicine[J].Scientific Data,2023,10:67.DOI:10.1038/s41597-023-01960-3.
[11] LIU Yushan,MA Yunpu,HILDEBRANDT M,et al.TLogic: Temporal logical rules for explainable link forecasting on temporal knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Washington D C: AAAI Press,2022:4120-4127.
[12] 朱龙.利润约束的关联规则挖掘算法[J].华侨大学学报(自然科学版),2015,36(5):522-526.DOI:10.11830/ISSN.1000-5013.2015.05.0522.
[13] LUO Linhao,JU Jiaxin,XIONG Bo,et al.ChatRule: Mining logical rules with large language models for knowledge graph reasoning[C]//Advances in Knowledge Discovery and Data Mining.Singapore: Springer,2025:341-356.DOI:10.1007/978-981-96-8173-0_25.
[14] MILUTINOVIC M,BAYDIN G A,ZINKOV R,et al.End-to-end training of differentiable pipelines across machine learning frameworks[EB/OL].(2019-01-01)[2025-08-22] .https://openreview.net/forum?id=ryh7qqGRZ.
[15] QU Meng,CHEN Junkun,XHONNEUX L P,et al.RNNLogic: Learning logic rules for reasoning on knowledge graphs[EB/OL].(2020-10-08)[2025-08-22] .https://arxiv.org/abs/2010.04029.
[16] CHENG Kewei,AHMED N K,SUN Yizhou.Neural compositional rule learning for knowledge graph reasoning[EB/OL].(2023-03-07)[2025-08-22] .https://arxiv.org/abs/2303.03581.
[17] XU Zezhong,YE Peng,CHEN Hui,et al.Ruleformer: Context-aware rule mining over knowledge graph[C]//Proceedings of the 29th International Conference on Computational Linguistics.Gyeongju: Association for Computational Linguistics,2022:2551-2560.
[18] PAN Shitui,LUO Linhao,WANG Yufei,et al.Unifying large language models and knowledge graphs: A roadmap[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(7):3580-3599.
[19] WANG Shihao,DU Xuehui,WU Xiangyu,et al.A trusted distributed oracle scheme based on share recovery threshold signature[J].Computers, Materials&Continua,2025,82(2):3355-3379.DOI:10.32604/cmc.2024.059722.
[20] 程小刚,郭韧,周长利,等.层次匿名群签名的概念与构建[J].华侨大学学报(自然科学版),2022,43(6):819-824.DOI:10.11830/ISSN.1000-5013.202202009.
[21] KRAUSE S,STOLZENBURG F.Commonsense reasoning and explainable artificial intelligence using large language models[C]//ECAI 2023 International Workshops.Cham: Springer,2024:221-235.DOI:10.1007/978-3-031-50396-2_17.
[22] HINTON G E.Learning distributed representations of concepts[C]//Proceedings of the Annual Meeting of the Cognitive Science Society.Hillsdale: Cognitive Science Society,1986:1-12.
[23] KOK S,DOMINGOS P.Statistical predicate invention[C]//Proceedings of the 24th International Conference on Machine Learning.New York: Association for Computing Machinery,2007:433-440.DOI:10.1145/1273496.1273556.
[24] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[J].Advances in Neural Information Processing Systems,2013,26:2787-2795.
[25] YANG Bishan,YIH W,HE Xiaodong,et al.Embedding entities and relations for learning and inference in knowledge bases[EB/OL].(2014-12-20)[2025-08-22] .https://arxiv.org/abs/1412.6575.
[26] TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//Proceedings of the International Conference on Machine Learning.New York: Association for Computing Machinery,2016:2071-2080.
[27] SUN Zhiqing,DENG Zhihong,NIE Jianyun,et al.RotatE: Knowledge graph embedding by relational rotation in complex space[EB/OL].(2019-02-26)[2025-08-22] .https://arxiv.org/abs/1902.10197.
[28] TANG Xiaojuan,ZHU Songchun,LIANG Yitao,et al.RulE: Knowledge graph reasoning with rule embedding[EB/OL].(2022-10-27)[2025-08-22] .https://arxiv.org/abs/2210.14905.
[29] XU Zezhong,YE Peng,CHEN Hui,et al.Ruleformer: Context-aware rule mining over knowledge graph[C]//Proceedings of the 29th International Conference on Computational Linguistics.Gyeongju: Association for Computational Linguistics,2022:2551-2560.
[30] WEI J,BOSMA M,ZHAO V Y,et al.Finetuned language models are zero-shot learners[C]//The Tenth International Conference on Learning Representations.Vancouver: [s.n.],2021:5-9.
[31] CHENG Kewei,LIU Jiahao,WANG Wei,et al.RLogic: Recursive logical rule learning from knowledge graphs[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.New York: Association for Computing Machinery,2022:179-189.

相似文献/References:

[1]傅文龙,李国刚,解童.采用区块链的物联网数据共享方案[J].华侨大学学报(自然科学版),2023,44(2):257.[doi:10.11830/ISSN.1000-5013.202204028]
　FU Wenlong,LI Guogang,XIE Tong.Data Sharing Scheme for Internet of Things Using Blockchain[J].Journal of Huaqiao University(Natural Science),2023,44(5):257.[doi:10.11830/ISSN.1000-5013.202204028]

备注/Memo

备注/Memo:
收稿日期: 2025-08-25
通信作者: 郭荣新(1980-),男,副教授,主要从事区块链技术、人工智能、物联网技术的研究。E-mail:grxeee@hqu.edu.cn。
基金项目: 国家自然科学青年基金资助项目(62306122); 福建省科技项目引导性项目(2023H0012)
更新日期/Last Update: 2025-09-20