基于智能规划的工作流任务识别算法

doi:10.3969/j.issn.0372-2112.2018.04.015

摘要
图/表
参考文献(0)
相关文章 (4)

全文: PDF (722 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对传统算法将活动看成是彼此之间相互独立的事件，无法准确识别的问题，提出一种基于智能规划的工作流任务识别算法，利用工作流与智能规划在执行序列和操作规则方面存在的共性.通过高层次的抽象描述，自动推导出活动之间的内在逻辑联系，且能从外部信息充分挖掘潜在的知识，将工作流任务识别问题转变为对应的智能规划识别问题来进行求解，有效地解决了传统算法识别困难和对噪声数据敏感的问题.实验结果表明，本文提出的算法是可行的.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	曾霖
	卓汉逵
	李磊

关键词 ：工作流活动, 任务识别, 规划算法, 智能监控

Abstract：For traditional algorithms,activities are treated as events that are independent from each other and cannot be accurately identified,we propose a workflow task recognition algorithm based on intelligent programming,which utilizes the commonality of workflow and intelligent planning in the implementation of sequence and operation rules.Through the high-level abstract description,we can deduce the intrinsic logic relation between them automatically,and also explore potential knowledge from outside information,and transform the workflow task recognition problem into the corresponding planning recognition problem,and solve the problem that the traditional algorithm is difficult in recognition and sensitive to the noise data.Experimental results show that our algorithm is feasible.

Key words： workflow activity activity recognition planning intelligent monitoring

收稿日期: 2016-12-06

ZTFLH:

TP311

基金资助:国家自然科学基金（No.61309011，No.U1611262）；广州市珠江科技新星；广东省大数据分析与处理重点实验室

作者简介: 曾霖男,1981年生,中山大学数据科学与计算机学院博士研究生.研究方向为智能规划、机器学习、数据挖掘.E-mail:zsuzenglin@163.com;卓汉逵 男,1982年生,中山大学数据科学与计算学院副教授,博士.研究方向为智能规划、机器学习;李磊男,1951年生,中山大学数据科学与计算学院教授,博士生导师.研究方向为数据库、数据挖掘、人工智能

引用本文:

曾霖, 卓汉逵, 李磊. 基于智能规划的工作流任务识别算法[J]. 电子学报, 2018, 46(4): 871-877. ZENG Lin, ZHUO Han-kui, LI Lei. Workflow Task Recognition Algorithm Based on Intelligent Planning. Acta Electronica Sinica, 2018, 46(4): 871-877.

链接本文:

http://www.ejournal.org.cn/CN/10.3969/j.issn.0372-2112.2018.04.015 或 http://www.ejournal.org.cn/CN/Y2018/V46/I4/871

[1] Dumas,Marlon,et al.Process-Aware Information Systems:Bridging People and Software Through Process Technology[M].New Jersey:John Wiley & Sons,2005.
[2] Fan Shaokun,Lele Kang,Leon Zhao.Workflow-aware attention tracking to enhance collaboration management[J].Information Systems Frontiers,2015,17(6):1253-1264.
[3] Qanbari Soheil,Fei Li,Schahram Dustdar.Toward portable cloud manufacturing services[J].IEEE Internet Computing,2014,18(6):77-80.
[4] Völter Markus,et al.Model-Driven Software Development:Technology,Engineering,Management[M].New Jersey:John Wiley & Sons,2013.
[5] Eliceiri Kevin,et al.Biological imaging software tools[J].Nature methods,2012,9(7):697-710.
[6] Branco Moisés Castelo,et al.A case study on consistency management of business and IT process models in banking[J].Software & Systems Modeling,2014,13(3):913-940.
[7] 孙瑞志,史美林.一个支持动态变化的工作流元模型[J].电子学报,2002,30(S1):2052-2056. SUN Rui-zhi,SHI Mei-lin.A meta-model supporting dynamic changing workflow[J].Acta Electronica Sinica,2002,30(S1):2052-2056.(in Chinese)
[8] Costa Lauro Beltrão,et al.The case for workflow-aware storage:An opportunity study[J].Journal of Grid Computing,2015,13(1):95-113.
[9] Yan Yan,et al.Egocentric daily activity recognition via multitask clustering[J].IEEE Transactions on Image Processing,2015,24(10):2984-2995.
[10] Boiman Oren,Michal Irani.Detecting irregularities in images and in video[J].International Journal of Computer Vision,2007,74(1):17-31.
[11] Khalid Shehzad,Usman Akram,Shahid Razzaq.Behaviour recognition using multivariate m-mediod based modelling of motion trajectories[J].Multimedia Systems,2015,21(5):485-505.
[12] Geib Christopher,Robert P Goldman.A probabilistic plan recognition algorithm based on plan tree grammars[J].Artificial Intelligence,2009,173(11):1101-1132.
[13] Avrahami-Zilberbrand Kaminka.Fast and Complete Symbolic Plan Recognition[A].Proceedings of the 19th International Joint Conference on Artificial Intelligence[C].Burlington:Morgan Kaufmann,2005.653-658.
[14] Ramirez Geffner.Plan recognition as planning[A].Proceedings of the 21st International Joint Conference on Artificial Intelligence[C].Burlington:Morgan Kaufmann,2009.1778-1783.
[15] Yang Qiang,Kangheng Wu,Yunfei Jiang.Learning action models from plan examples using weighted MAX-SAT[J].Artificial Intelligence,2007,171(2-3):107-143.
[16] Hoffmann Jörg.FF:The fast-forward planning system[J].AI magazine,2001,22(3):57-62.
[17] Voulodimos Athanasios,et al.A dataset for workflow recognition in industrial scenes[A].Proceedings of the 18th IEEE International Conference on Image Processing[C].Piscataway:IEEE,2011.3249-3252.
[18] Han Wook-Shin,et al.iGraph:a framework for comparisons of disk-based graph indexing techniques[A].Proceedings of the VLDB Endowment[C].California:PVLDB,2010.449-459.
[19] Karpas Erez,Carmel Domshlak.Cost-optimal planning with landmarks[A].Proceedings of the 21st International Joint Conference on Artificial Intelligence[C].Burlington:Morgan Kaufmann,2009.1728-1733.