垂直领域知识图谱构建及应用平台的设计与实现

doi:10.11871/jfdc.issn.2096-742X.2023.03.008

数据与计算发展前沿 ›› 2023, Vol. 5 ›› Issue (3): 111-122.

CSTR: 32002.14.jfdc.CN10-1649/TP.2023.03.008

doi: 10.11871/jfdc.issn.2096-742X.2023.03.008

垂直领域知识图谱构建及应用平台的设计与实现

张博尧^1,^2,^*(),曹荣强^1,²,万萌¹,孙境棋¹,王彦棡^1,²,王珏^1,²,赵永华^1,²

1.中国科学院计算机网络信息中心，人工智能技术与应用发展部，北京 100083
2.中国科学院大学，北京 100049

收稿日期:2022-03-17 出版日期:2023-06-20 发布日期:2023-06-21
通讯作者: *张博尧（E-mail: zhangby@sccas.cn）
作者简介:张博尧，中国科学院计算机网络信息中心，中国科学院大学，工程师，硕士，主要研究方向为人工智能应用。
本文承担工作为：平台的构建及应用。
ZHANG Boyao, Computer Network In-formation Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences, engi-neer, master. His main research interests include artificial inte-lligence applications.
In this paper, he undertakes the following tasks: the constr-uction and application of the platform.
E-mail: zhangby@sccas.cn
基金资助:
中国国家电网有限公司总部管理科技项目“自主可控电力人工智能开放平台关键技术研究”(5700-20215-8261A-0-0-00)

Design and Implementation of a Platform for Domain Knowledge Graph Construction and Applications

ZHANG Boyao^1,^2,^*(),CAO Rongqiang^1,²,WAN Meng¹,SUN Jingqi¹,WANG Yangang^1,²,WANG Jue^1,²,ZHAO Yonghua^1,²

1. Department of Artificial Intelligence Technology and Application Development, Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2022-03-17 Online:2023-06-20 Published:2023-06-21

摘要/Abstract

摘要：

【目的】 知识图谱可以将客观世界的实体、概念、关系等抽象成图数据结构，是垂直领域建模和应用的研究热点，本文研发和实现了从资源调度、知识图谱构建到应用场景全过程的自动化和一体化平台。【方法】 以微服务架构的方式部署了数据处理、算法仓库及知识图谱公共组件，采用了低耦合、高内聚和多层次的架构以提升平台处理知识抽取、存储与应用等不同任务时多模块间的协作能力，将计算资源虚拟化以提升初始化、生产与日常维护等平台的不同使用阶段的资源调度能力。【结果】 建成和部署了垂直领域知识图谱构建及应用平台，提供了数据处理、自动化知识抽取、图计算及扩展、图表示学习及应用等功能。以金融领域产业链知识图谱的构建及表示学习应用的过程为例，验证了平台的可用性。【结论】 该平台实现了垂直领域知识图谱从构建、图表示学习到领域应用的全流程覆盖，有效地降低了用户的使用难度，提高了资源的利用效率，也可以扩展到其它垂直领域。

关键词: 知识图谱, 资源虚拟化, 图表示学习, 微服务技术

Abstract:

[Objective] The entities, concepts, relationships, etc. of the objective world can be abstracted into a graph data structure by knowledge graph technology. It is a research hotspot of modeling and applications in the vertical domain. In this paper, an automated and integrated platform is developed and implemented, which can cover the whole process from resource scheduling and knowledge graph construction to applications. [Methods] The data processing module, algorithm warehouse, and knowledge graph common components are deployed in the form of microservice architecture. In order to improve the cooperation ability between multiple modules, the platform adopts a low-coupling, high-cohesion, and multi-layered architecture to handle different tasks such as knowledge extraction, storage, and applications. [Results] The knowledge graph construction and application platform in the vertical domain are built and deployed. It provides functions such as data processing, automatic knowledge extraction, graph computation and extension, graph representation learning and application. The usability of the platform is verified, with the construction of a knowledge graph and application of representation learning as a typical case in the financial domain. [Conclusions] The platform covers the whole process from graph construction, graph representation learning to domain applications for knowledge graphs in the vertical domain. It effectively reduces the difficulty of use, improves the efficiency of resource utilization, and can be extended to other vertical domains.

Key words: Knowledge graph, Resource virtualization, Graph representation learning, Microservices technology

张博尧, 曹荣强, 万萌, 孙境棋, 王彦棡, 王珏, 赵永华. 垂直领域知识图谱构建及应用平台的设计与实现[J]. 数据与计算发展前沿, 2023, 5(3): 111-122.

ZHANG Boyao, CAO Rongqiang, WAN Meng, SUN Jingqi, WANG Yangang, WANG Jue, ZHAO Yonghua. Design and Implementation of a Platform for Domain Knowledge Graph Construction and Applications[J]. Frontiers of Data and Computing, 2023, 5(3): 111-122, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.03.008.

图/表 8

图1

图2

图3

图4

图5

图6

图7

图8

参考文献 29

[1]	Dong X, Gabrilovich E, Heitz G, et al. Knowledge vault: A web-scale approach to probabilistic knowledge fusion[C]// Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014: 601-610.
[2]	Hogan A, Blomqvist E, Cochez M, et al. Knowledge gr-aphs[J]. Synthesis Lectures on Data, Semantics, and Kno-wledge, 2021, 12(2): 1-257.
[3]	Zhang F, Yuan N J, Lian D, et al. Collaborative know-ledge base embedding for recommender systems[C]// Proc-eedings of the 22nd ACM SIGKDD international confer-ence on knowledge discovery and data mining, 2016: 353-362.
[4]	Wang J, Guo Y, Wen X, et al. Improving graph-based label propagation algorithm with group partition for fraud detection[J]. Applied Intelligence, 2020, 50(10): 3291-3300. doi: 10.1007/s10489-020-01724-1
[5]	曹俊辉, 吴开超, 刘莹, 魏千程. 图结构特征挖掘在预测交易风险中的应用[J]. 科研信息化技术与应用, 2019, 10(01):59-65.
[6]	Xiao G, Ding L, Cogrel B, et al. Virtual knowledge gra-phs: An overview of systems and use cases[J]. Data Intel-ligence, 2019, 1(3): 201-223.
[7]	周园春, 常青玲, 杜一. SKS: 一种科技领域大数据知识图谱平台[J]. 数据与计算发展前沿, 2019, 1(1):82-93.
[8]	Cao Z, Ni L, Dai L. A Review of Knowledge Graphbas-ed Question and Answer System Research and Its Appli-cation in Chronic Disease Diagnosis[J]. Academic Journ-al of Computing & Information Science, 2021, 4 (4): 1-11.
[9]	Dhingra B, Zaheer M, Balachandran V, et al. Diffe-rentiable reasoning over a virtual knowledge base[J]. arXiv preprint arXiv:2002.10640, 2020.
[10]	Wang Q, Mao Z, Wang B, et al. Knowledge graph emb-edding: A survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724-2743. doi: 10.1109/TKDE.2017.2754499
[11]	Ji S, Pan S, Cambria E, et al. A survey on knowledge gr-aphs: Representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(2): 494-514. doi: 10.1109/TNNLS.2021.3070843
[12]	Ebisu T, Ichise R. TorusE: knowledge graph embedding on a lie group[C]// Proceedings of the Thirty-Second AA-AI Conference on Artificial Intelligence and Thirtieth Inn-ovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, 2018: 1819-1826.
[13]	Kim H. Building a K-Pop knowledge graph using an en-tertainment ontology[J]. Knowledge Management Res-earch & Practice, 2017, 15(2): 305-315.
[14]	Yu T, Li J, Yu Q, et al. Knowledge graph for TCM health preservation: Design, construction, and applications[J]. Artificial intelligence in medicine, 2017, 77: 48-52. doi: S0933-3657(17)30135-5 pmid: 28545611
[15]	Nadeau D, Sekine S. A survey of named entity recogni-tion and classification[J]. Lingvisti-cae Investigationes, 2007, 30(1): 3-26.
[16]	Aejas B, Bouras A, Belhi A, et al. A Review of Contract Entity Extraction[C]// Proceedings of Sixth International Congress on Information and Communication Technol-ogy, Singapore: Springer, 2022: 763-771.
[17]	Zhang T, Mao X, Li D, et al. Target-dependent Event Detection: A New Task to Event Extraction from News[C]// 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021: 571-580.
[18]	王彦棡, 王珏, 曹荣强. 人工智能计算与数据服务平台的研究与应用[J]. 数据与计算发展前沿, 2019, 1(2): 86-97.
[19]	Chen F, Wang Y C, Wang B, et al. Graph representation learning: a survey[J]. APSIPA Transactions on Signal and Information Processing, 2020, 9: e15.
[20]	Bordes A, Usunier N, Garcia-Durán A, et al. Translating embeddings for modeling multi-relational data[C]// Pro-ceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2, 2013: 2787-2795.
[21]	Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online lea-rning of social representa-tions[C]// Proceedings of the 20th ACM SIGKDD international conference on Know-ledge discovery and data mining, 2014: 701-710.
[22]	Grover A, Leskovec J. node2vec: Scalable feature lea-rning for networks[C]// Proceedings of the 22nd ACM SIGKDD international conference on Knowledge disc-overy and data mining, 2016: 855-864.
[23]	Scarselli F, Gori M, Tsoi A C, et al. The graph neural net-work model[J]. IEEE transactions on neural networks, 2008, 20(1): 61-80. doi: 10.1109/TNN.2008.2005605
[24]	Kivity A, Kamay Y, Laor D, et al. kvm: the Linux virtual machine monitor[C]// Proceedings of the Linux symp-osium, 2007, 1(8): 225-230.
[25]	Du R, Shi J, Zou J, et al. A Feasibility Study on workload integration between HT-Condor and Slurm Clusters[C]// EPJ Web of Conferences, EDP Sciences, 2019, 214: 080-04.
[26]	Bernstein D. Containers and cloud: From lxc to docker to kubernetes[J]. IEEE Cloud Computing, 2014, 1(3): 81-84. doi: 10.1109/MCC.2014.51
[27]	Medel V, Tolosana-Calasanz R, Bañares J Á, et al. Char-acterising resource management performance in Kuber-netes[J]. Computers & Electrical Engineering, 2018, 68: 286-297.
[28]	Curado M. Return random walks for link prediction[J]. Information Sciences, 2020, 510: 99-107. doi: 10.1016/j.ins.2019.09.017
[29]	Makarov I, Kiselev D, Nikitinsky N, et al. Survey on gra-ph embeddings and their applications to machine lear-ning problems on graphs[J]. PeerJ Computer Science, 2021, 7: e357-e357. doi: 10.7717/peerj-cs.357

垂直领域知识图谱构建及应用平台的设计与实现

Design and Implementation of a Platform for Domain Knowledge Graph Construction and Applications

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 29

相关文章 10

编辑推荐

Metrics

本文评价

[1]	张晓帆, 孙海春, 李欣. 融合多层注意力机制与BiLSTM的知识图谱补全算法研究[J]. 数据与计算发展前沿, 2023, 5(3): 123-137.
[2]	许淞源,李成赞,刘峰. 基于知识图谱和主题模型的短文本特征增强方法[J]. 数据与计算发展前沿, 2023, 5(2): 97-105.
[3]	罗婕溪,刘帅,张玉志,李正丹,孙羽菲,张圣林. 基于知识图谱技术的线上教学资源推荐系统设计与实现[J]. 数据与计算发展前沿, 2022, 4(3): 3-18.
[4]	兰格,王瑾瑜,孙羽菲,张玉志. 基于知识图谱的图匹配文本分类[J]. 数据与计算发展前沿, 2022, 4(2): 39-49.
[5]	陶磊,苏晨阳,李正丹,朱静雯,张玉志. 基于ElasticSearch和语义相似度匹配的教学资源搜索策略[J]. 数据与计算发展前沿, 2022, 4(2): 50-62.
[6]	胡正银,刘蕾蕾,陈文杰,刘春江,钱力,宋亦兵. 面向科学知识发现的造血干细胞知识图谱构建研究[J]. 数据与计算发展前沿, 2021, 3(6): 81-97.
[7]	李序,连一峰,张海霞,黄克振. 网络安全知识图谱关键技术[J]. 数据与计算发展前沿, 2021, 3(3): 9-18.
[8]	刘佳,夏晓蕾,王姝,王丽娟,郭志斌,胡良霖,周园春. 科技资源标识服务系统及创新应用[J]. 数据与计算发展前沿, 2020, 2(6): 62-73.
[9]	孙艳艳,毛卫南,毛宇斐,吴海博. 基于区域科技资源服务平台的虚拟创新生态系统构建研究[J]. 数据与计算发展前沿, 2020, 2(5): 30-40.
[10]	周园春,常青玲,杜一. SKS：一种科技领域大数据知识图谱平台 ^*[J]. 数据与计算发展前沿, 2019, 1(1): 82-93.