Automated discovery of business process simulation models from event logs: a hybrid process mining and deep learning approach
Kuupäev
2021-12-07
Autorid
Ajakirja pealkiri
Ajakirja ISSN
Köite pealkiri
Kirjastaja
Abstrakt
Protsessi muutmine võib ettevõtetele osutuda kulukaks ja riskantseks, kuid vajalikuks. Muutuste eiramine võib avaldada mõju ettevõtte resurssidele, selle keskkonnale või jätkusuutlikusele. Üks ettevõtete poolt enimkasutatumaid meetmeid disainimiseks ja hindamiseks protsessi on äriprotsessi simulatsioon. See tehnika võimaldab luua hüpoteetilisi stsenaariume ja hinnata teostuse tagajärgi virtuaalses keskkonnas võtmata riski ebaõnnestuda reaalsuses.
Modifitseerides protsessi üksikasju simulaatoris annab võimaluse analüütikutele teha oletusi nagu näiteks „kui sa eemaldad selle, juhtub see või kui sa lisad selle, siis võib juhtuda see.“ Selline võime on väga mugav abistamaks otsuse tegemise protsessi seoses potensiaalsete muutustega. Probleem antud meetodiga on, et simulatsioonimudeli loomine ja sobitamine on komplitseeritud ülesanne, mis vajab aega ja spetsialiseerunud tehnilisi teadmisi. Lisaks loovad analüütikud tavaliselt simulatsioonimudeleid, viies läbi intervjuusid, vaatlusi ja testimisi. Kõik need tehnikad on väga altid eelarvamustele, mis tähendab, et manuaalselt loodud mudelite täpsus on suhteliselt ekslik. Kõik see valmistab pettumust äriprotsessi simulatsiooni kasutusele võtmisel, mis teeb ettevõtetele antud tehnika kasutamise keeruliseks.
Käesolev doktoritöö pakub välja uusi tehnikaid loomaks äriprotsessi simulatsioonimudeleid, mis kasutavad andmeid ettevõtete infosüsteemidest samaaegselt neuronvõrkude ja protsessikaeve algoritmidega. Antud doktoritöö eesmärk on luua täpsemat automaatset simulatsioonitehnikat, mis vajab vähem inimese sekkumist, lahendamaks puuduseid hetkel kasutuselolevast protsessi simulatsioonimootori lähenemisest.
Me ühendame käesolevas doktoritöös välja toodud tehnikad kahes avatud lähtekoodiga tööriistas. Esimene tööriist, Simod, suudab täisautomaatselt avastada ja peenhäälestada simulatsioonimudeleid läbi kaeveprotsessi tehnikate. Välja toodud meetodil on siiski puudused, mis puudutavad iga tegevuse ajaennustust. Vastuseks on teine tööriist, DeepSimulator, mis ühildab avastamistehnikad, baseerudes kaeveprotsessile koos generatiivsete mudelitega, mis põhinevad süvaõppel. Hinnangu tulemused sellise hübriidlähenemise viisil viivad simulatsioonideni, mis peegeldavad lähemalt täheldatud protsessi dünaamikat kui meetodid, mis põhinevad paljalt kaeveprotsessil või süvaõppel.
For companies, changing a process can be costly and risky but necessary. And not doing it can affect its resources, its environment, or its continuity. One of the techniques most used by companies to design and evaluate their processes is business process simulation. This technique allows creating hypothetical scenarios and assessing the consequences of their implementation in a virtual environment without taking the risks of failure in real life. Modifying the process components in the simulator allows the analysts to make assumptions such as "if you remove this, this could happen, or if you add this, this could happen." This ability is very convenient to support the decision-making process concerning potential changes. The problem with this method is that creating and fitting a simulation model is a complex task that requires time and specialized technical knowledge. In addition, analysts usually create simulation models through interviews, observations, and sampling. All these techniques are highly prone to biases, which means that the precision of these manually created models is relatively inaccurate. All this makes disappointing the adoption of business process simulation, making it difficult for companies to use this technique. This thesis proposes new techniques for creating business process simulation models that use data extracted from enterprise information systems in conjunction with neural networks and process mining algorithms. This thesis aims to create a more precise automatic simulation technique that requires less human intervention solving the drawbacks of the current process simulation approach. We consolidate the techniques proposed in this thesis in two open-source tools. The first tool, called Simod, can fully automatically discover and fine-tune simulation models through process mining techniques. However, the proposed method often falls short when it comes to predicting the timing of each activity. In response, the second tool called DeepSimulator combines discovery techniques based on process mining with generative models based on deep learning. The evaluation results of this hybrid approach lead to simulations that more closely reflect the observed dynamics of the process than methods based purely on process mining or deep learning.
For companies, changing a process can be costly and risky but necessary. And not doing it can affect its resources, its environment, or its continuity. One of the techniques most used by companies to design and evaluate their processes is business process simulation. This technique allows creating hypothetical scenarios and assessing the consequences of their implementation in a virtual environment without taking the risks of failure in real life. Modifying the process components in the simulator allows the analysts to make assumptions such as "if you remove this, this could happen, or if you add this, this could happen." This ability is very convenient to support the decision-making process concerning potential changes. The problem with this method is that creating and fitting a simulation model is a complex task that requires time and specialized technical knowledge. In addition, analysts usually create simulation models through interviews, observations, and sampling. All these techniques are highly prone to biases, which means that the precision of these manually created models is relatively inaccurate. All this makes disappointing the adoption of business process simulation, making it difficult for companies to use this technique. This thesis proposes new techniques for creating business process simulation models that use data extracted from enterprise information systems in conjunction with neural networks and process mining algorithms. This thesis aims to create a more precise automatic simulation technique that requires less human intervention solving the drawbacks of the current process simulation approach. We consolidate the techniques proposed in this thesis in two open-source tools. The first tool, called Simod, can fully automatically discover and fine-tune simulation models through process mining techniques. However, the proposed method often falls short when it comes to predicting the timing of each activity. In response, the second tool called DeepSimulator combines discovery techniques based on process mining with generative models based on deep learning. The evaluation results of this hybrid approach lead to simulations that more closely reflect the observed dynamics of the process than methods based purely on process mining or deep learning.
Kirjeldus
Märksõnad
business processes, business process modeling, intensive classes, data mining