期刊文献+

融合知识图谱的智慧社区人机物三元交互模型

A ternary interaction model of human-machine-object in smart community based on knowledge graph
原文传递
导出
摘要 实现智慧社区需要更智能的方法来管理和优化处理人、机器和物品之间的复杂交互关系。知识图谱可以根据具体需求和应用场景灵活地设计和扩展数据模型,是行之有效的解决途径。该文通过对智慧社区人机物三元交互流程的研究,设计了一种融合强化学习的人机物三元协同智能调度方法,并使用社区数据对人机物本体进行建模,构建了融合知识图谱的社区人机物三元协同调度模型。本模型应用于首农东苑公寓智慧物业服务系统,涵盖了楼宇三维管理、智能设备检修等场景,解决了资源优化和管理问题,适应智慧社区不同服务场景人机物交互需求。 To achieve a smart community,there is a need for more intelligent approaches to manage and optimize the complex interaction relationships among humans,machines,and objects.knowledge graphs provide a flexible means to design and expand data models according to specific requirements and application scenarios,offering an effective solution pathway.This study,through an examination of the triadic interaction process among humans,machines,and objects in a smart community,devises a collaborative intelligent scheduling method that integrates reinforcement learning.Community data is employed to model the ontology of humans,machines,and objects,resulting in the construction of a collaborative scheduling model for the community,integrated with a knowledge graph.This model is applied to the intelligent property service system of Shounong Dongyuan apartments,encompassing scenarios such as three-dimensional building management and intelligent device maintenance.It resolves resource optimization and management issues and caters to diverse interaction requirements among humans,machines,and objects in different service scenarios within a smart community.
作者 周宇辰 何望君 石丽红 漆司翰 ZHOU Yuchen;HE Wangjun;SHI Lihong;QI Sihan(School of geomatics,Liaoning Technical University,Fuxing,Liaoning 123000,China;Chinese Academy of Surveying and Mapping,Beijing 100036,China)
出处 《测绘科学》 CSCD 北大核心 2024年第2期187-198,共12页 Science of Surveying and Mapping
基金 国家重点研发计划项目(2021YFF0900900)。
关键词 知识图谱 智慧社区 三元交互模型 强化学习 knowledge graph smart community ternary interaction model
  • 相关文献

参考文献12

二级参考文献71

  • 1Dnyanesh G R. An ontology based text mining system for knowledge discovery from the diagnosis data in the automotive domain[J]. Computers in Industry, 2013, 64(5): 565-580.
  • 2Cimiano P, Luker J, Nagel D, et al. Exploiting ontology lexica for generating naturallanguage texts from RDF data[EB/OL].[2014-07-30]. http)/www.aclweb.org/anthologyIW13-2102.
  • 3Huang X P, Du Y J, Ren Y Y. Research on automatic user on?tology construction[J]. Journal of Information and Computa- tional Science, 2012, 9(2): 285-292.
  • 4Subramaniyaswamy V. Automatic topic ontology construction using semantic relations from WordNet and Wikipedia[J]. International Journal of Intelligent Information Technologies, 2013,9(3):61-89.
  • 5Li J, Ding Y D, Shi Y Y, et al. Building a large annotation on?tology for movie video retrieval[EB/OL].[2014-08-01]. http)/www.aicit.orgljdctalpplI08.%20JDCTA2-390081pdj.
  • 6Xiao G Z, Wang X L. The text deduction and model realization of the lexical meanings in dictionaries based on "synset-lexeme anamorphosis" and "basic semantic elements and their struc?tures"[Cy/13th Chinese Lexical Semantics Workshop. Berlin: Springer-Verlag, 2013: 774-783.
  • 7Hu D. Primitive Structure of Mandarin in Natural Language Processing[M]. Guangzhou: World Publishing Corporation, 2014: 3-25(Ch).
  • 8Abbas J. Structures for Organizing Knowledge: Exploring Tax?Onomies, Ontologies, and Other Schemas[M]. New York: Neal-Schuman Publishers Inc, 2010: 5-20.
  • 9Noy N F, Hafner C D. The state of the art in ontology design: A survey and comparative review[J]. AI magazine, 1997, 18: 53-74.
  • 10Pazzaglia J R, Embury S M. Bottom-up integration of ontolo?gies in a database context[EB/OL].[2014-08-01]. http: / / sunsite. informatikrwth-aachen.delPublications/CEUR - WS/Vol -10/paper7ps.

共引文献332

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部