Käitusaegse seire andmeteadlikud ärireeglid koos lineaarse planeerimisega
Files
Date
2016
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Käitusaegne seire (Runtime Compliance Monitoring) on oluline osa äriprotsesside halduse elutsüklis, mittevastavuse õigeaegses avastamises, samuti vastumeetmete korraldamises ja ennetamises. Täpsemalt on see seotud operatiivse otsuse toega, mille eesmärgiks on laiendada protsessikaeve tehnikat sidusrežiimis, käitada protsessi isendeid nii, et kõrvalekaldeid on võimalik avastada, ning on võimalik soovitada, mida võiks järgmiseks teha, ning samuti ennustada, mis hakkab juhtuma tulevaste juhtumite täitmisel. Antud magistritöö keskendub käitusaegse seire andmeteadlikele ärireeglitele. Töös kasutatakse varajaste rikkumiste tuvastamiseks lineaarset täisarvulist planeerimist (Integer Linear Programming (ILP)), mida rakendatakse kahe või enama kitsenduse koosmõjul. Töökorras toepakkujas on rakendatud protsessikaeve raamistikku ProM ja meetod on valideeritud kasutades sünteetilisi ja reaalseid logisid.
Runtime Compliance Monitoring is vital building block in the Business Process Management lifecycle, in timely detection of non-compliance as well as provision of responsive and proactive countermeasures. In particular, it is linked to operational decision support, which aims at extending the application of process mining techniques to on-line, running process instances, so that deviations can be detected and it is possible to recommend what to do next and predict what will happen in the future instance execution. \n\r\n\rIn this thesis, we focus on Runtime Compliance Monitoring of data-aware business rules. In particular, we use Integer Linear Programming (ILP) for early detection of violations that occur from interplay of two or more constraints. An operational support provider has been implemented as part of process mining framework ProM and the approach has been validated using synthetic and real life logs.
Runtime Compliance Monitoring is vital building block in the Business Process Management lifecycle, in timely detection of non-compliance as well as provision of responsive and proactive countermeasures. In particular, it is linked to operational decision support, which aims at extending the application of process mining techniques to on-line, running process instances, so that deviations can be detected and it is possible to recommend what to do next and predict what will happen in the future instance execution. \n\r\n\rIn this thesis, we focus on Runtime Compliance Monitoring of data-aware business rules. In particular, we use Integer Linear Programming (ILP) for early detection of violations that occur from interplay of two or more constraints. An operational support provider has been implemented as part of process mining framework ProM and the approach has been validated using synthetic and real life logs.