Time prediction on multi-perspective declarative business processes

作     者：Jimenez-Ramirez, Andres Barba, Irene Fernandez-Olivares, Juan Del Valle, Carmelo Weber, Barbara 

作者机构：Univ Seville Dept Lenguajes & Sistemas Informat Seville Spain Univ Granada Dept Ciencias Comp & Inteligencia Artificial Granada Spain Tech Univ Denmark Lyngby Denmark 

出 版 物：《KNOWLEDGE AND INFORMATION SYSTEMS》 (知识和信息系统季刊)

年 卷 期：2018年第57卷第3期

页      面：655-684页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 070105[理学-运筹学与控制论] 081101[工学-控制理论与控制工程] 0701[理学-数学] 071101[理学-系统理论] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：MINECO R&D Projects Pololas  (PLAN MINER TIN2015-71618-R  TIN2016-76956-C3-2-R) 

主　　题：Flexible process-aware information systems Time prediction Constraint programming Planning and scheduling Constraint-based process models Decision support systems 

摘      要：Process-aware information systems (PAISs) are increasingly used to provide flexible support for business processes. The support given through a PAIS is greatly enhanced when it is able to provide accurate time predictions which is typically a very challenging task. Predictions should be (1) multi-dimensional and (2) not based on a single process instance. Furthermore, the prediction system should be able to (3) adapt to changing circumstances and (4) deal with multi-perspective declarative languages (e.g., models which consider time, resource, data and control flow perspectives). In this work, a novel approach for generating time predictions considering the aforementioned characteristics is proposed. For this, first, a multi-perspective constraint-based language is used to model the scenario. Thereafter, an optimized enactment plan (representing a potential execution alternative) is generated from such a model considering the current execution state of the process instances. Finally, predictions are performed by evaluating a desired function over this enactment plan. To evaluate the applicability of our approach in practical settings we apply it to a real process scenario. Despite the high complexity of the considered problems, results indicate that our approach produces a satisfactory number of good predictions in a reasonable time.