Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.

Process Mining - Chapter 9 - Operational Support

1.759 visualizaciones

Publicado el

Slides supporting the book "Process Mining: Discovery, Conformance, and Enhancement of Business Processes" by Wil van der Aalst. See also http://springer.com/978-3-642-19344-6 (ISBN 978-3-642-19344-6) and the website http://www.processmining.org/book/start providing sample logs.

Publicado en: Empresariales, Tecnología
  • Sé el primero en comentar

  • Sé el primero en recomendar esto

Process Mining - Chapter 9 - Operational Support

  1. 1. Chapter 9Operational Supportprof.dr.ir. Wil van der Aalstwww.processmining.org
  2. 2. OverviewChapter 1IntroductionPart I: PreliminariesChapter 2 Chapter 3Process Modeling and Data MiningAnalysisPart II: From Event Logs to Process ModelsChapter 4 Chapter 5 Chapter 6Getting the Data Process Discovery: An Advanced Process Introduction Discovery TechniquesPart III: Beyond Process DiscoveryChapter 7 Chapter 8 Chapter 9Conformance Mining Additional Operational SupportChecking PerspectivesPart IV: Putting Process Mining to WorkChapter 10 Chapter 11 Chapter 12Tool Support Analyzing “Lasagna Analyzing “Spaghetti Processes” Processes”Part V: ReflectionChapter 13 Chapter 14Cartography and EpilogueNavigation PAGE 1
  3. 3. Process mining spectrum supports/ “world” business controls processes software people machines system components organizations records events, e.g., messages, specifies transactions, models configures etc. analyzes implements analyzes discovery (process) event conformance model logs enhancement PAGE 2
  4. 4. Refined process mining framework people organizations machines business “world” processes documents information system(s) provenance event logs “pre “post mortem” current historic mortem” data data navigation auditing cartography recommend diagnose compare enhance discover promote explore predict detect check models de jure models de facto models control-flow control-flow data/rules data/rules resources/ resources/ organization organization PAGE 3
  5. 5. Business process provenance people organizations machines business “world” processes documents information system(s) provenance event logs “pre “post mortem” current historic mortem” data data PAGE 4
  6. 6. Two types of event data:post and pre mortem• “Post mortem” event data refer to information about cases that have completed, i.e., these data can be used for process improvement and auditing, but not for influencing the cases they refer to.• “Pre mortem” event data refer to cases that have not yet completed. If a case is still running, i.e., the case is still “alive” (pre mortem), then it may be possible that information in the event log about this case (i.e., current data) can be exploited to ensure the correct or efficient handling of this case. PAGE 5
  7. 7. Two types of models: “de jure models”and “de facto models”• A de jure model is normative, i.e., it specifies how things should be done or handled. For example, a process model used to configure a BPM system is normative and forces people to work in a particular way.• A de facto model is descriptive and its goal is not to steer or control reality. Instead, de facto models aim to capture reality. PAGE 6
  8. 8. Cartography “post historic• Discover. This activity is data mortem” concerned with the extraction of (process) models. cartography• Enhance. When existing process diagnose enhance discover models (either discovered or hand-made) can be related to events logs, it is possible to enhance these models. models de facto models• Diagnose. This activity does not directly use event logs and control-flow focuses on classical model-based analysis. data/rules resources/ organization PAGE 7
  9. 9. Auditing event logs• Detect. Compares de jure models “pre “post with current “pre mortem” data. The mortem” current data historic data mortem” moment a predefined rule is violated, an alert is generated auditing (online). compare promote detect check• Check. The goal of this activity is to pinpoint deviations and quantify the level of compliance (offline). models de jure models de facto models• Compare. De facto models can be compared with de jure models to see control-flow control-flow in what way reality deviates from what was planned or expected. data/rules data/rules• Promote. Promote parts of the de resources/ resources/ organization organization facto model to a new de jure model. PAGE 8
  10. 10. Navigation event logs• Explore. The combination of event “pre “post mortem” current historic mortem” data and models can be used to data data explore business processes at run-time. navigation recommend• Predict. By combining information explore predict about running cases with models, it is possible to make predictions about the future, e.g., the models remaining flow time and the probability of success.• Recommend. The information used for predicting the future can also be used to recommend suitable actions (e.g. to minimize costs or time). PAGE 9
  11. 11. Operational support:online process mining using “pre mortem” event data T=10 current stateknown unknown past future a b a b ? ? a b c ? detect: b does not fit the predict: some prediction is recommend: based on pasta b c d model (not allowed, too late, etc.) made about the future (e.g. completion date or outcome) experiences c is recommended (e.g., to minimize costs) PAGE 10
  12. 12. Let us focus one time PAGE 11
  13. 13. b examineTransition system c1 thoroughly c3 g pay c(with start/complete) start a register examine casually e decide c5 compensation end request h c2 d c4 reject check ticket request f reinitiate request [a] astart [start] acomplete [p1,p2] dstart [p1,d] dcomplete [p1,p4] bstart cstart dstart bstart cstart dcomplete bstart cstart [b,p2] [b,d] [c,p4] [b,p4] [c,p2] [c,d] dstart dcomplete bcomplete ccomplete bcomplete ccomplete bcomplete ccomplete [p3,p2] dstart dcomplete [p3,p4] [p3,d] fcomplete [f] fstart [p5] ecomplete [e] estart gstart hstart [g] [h] gcomplete hcomplete PAGE 12 [p5]
  14. 14. Operational support: Detect PAGE 13
  15. 15. Example b alert!!!! examine c3 thoroughly g c1 pay c compensation a examine estart register casually decide c5 end request h c2 d c4 reject check ticket request f reinitiate request PAGE 14
  16. 16. Declare specifications for detecting violations pay • Satisfied: the LTL formula compensation evaluates to true for the g current partial trace. c2 • Temporarily violated: the c1 LTL formula evaluates to a c4 eregister decide false, however, there is arequest c3 longer trace that evaluates h to true. reject request • Permanently violated: the LTL formula evaluates to false for current trace and all its extensions PAGE 15
  17. 17. Conflicting constraints • A Declare specification is pay satisfied for a case if all of its compensation constraints are satisfied. g • A Declare specification is c4 c2 temporarily violated by a case if c1 for the current partial trace at a e decide least one of the constraints is register request c5 c3 violated, however, there is a h possible future in which all reject constraints are satisfied. request • A Declare specification is permanently violated by a case if no such future exists.Note that c1, c2, and c3 imply that e cannotbe executed without permanently violatingthe specification. PAGE 16
  18. 18. Operational support: Predict PAGE 17
  19. 19. Examples of predictions• the predicted remaining flow time is 14 days;• the predicted probability of meeting the legal deadline is 0.72;• the predicted total cost of this case is 4500 euro;• the predicted probability that activity a will occur is 0.34;• the predicted probability that person r will work on this case is 0.57;• the predicted probability that a case will be rejected is 0.67; and• the predicted total service time is 98 minutes. PAGE 18
  20. 20. Annotated transition system t=12,e=0,r=42,s=7 t=17,e=0,r=56,s=6 [a] t=19,e=7,r=35,s=6 astart [start] t=28,e=11,r=45,s=2 acomplete [p1,p2] dstart [p1,d] dcomplete [p1,p4] t=23,e=6,r=50,s=5 b bstart t=30,e=13,r=43,s=2 start cstart t=32,e=15,r=41,s=6 bstart cstart cstart dstart dcomplete [b,p2] [b,d]t=25,e=13,r=29,s=1 [b,p4] [c,p2] [c,d] [c,p4] dstart dcomplete t=33,e=21,r=21,s=2 bcomplete t=26,e=14,r=28,s=6 ccomplete bcomplete ccomplete bcomplete ccomplete [p3,p2] dstart dcomplete t=32,e=20,r=22,s=1 [p3,d] [p3,p4] t=38,e=21,r=35,s=12 fcomplete [f] fstart [p5] ecomplete [e] estart t=35,e=23,r=19,s=5 t=40,e=28,r=14,s=10 gstart hstart t=50,e=33,r=23,s=9 t=59,e=42,r=14,s=11 [g] [h] t=70,e=53,r=3,s=3 gcomplete hcomplete t=50,e=38,r=4,s=4 [p5] t=54,e=42,r=0 PAGE 19 t=73,e=56,r=0
  21. 21. Collect results per state [a] astart [start] acomplete [p1,p2] dstart [p1,d] dcomplete [p1,p4] bstart cstart dstart bstart cstart dcomplete bstart cstart [c,p4] elapsed times:[b,p2] [b,d] [21,21,15,42, … ] [b,p4] [c,p2] [c,d] dstart ccomplete dcomplete remaining times: bcomplete ccomplete bcomplete ccomplete bcomplete [21,35,58,31, … ] [p3,p2] dstart dcomplete [p3,d] [p3,p4] sojourn times: [f] [p5] ecomplete [e] [2,12,5,13, … ] fcomplete fstart estart gstart hstart average remaining [g] [h] flow time is 42.56 gcomplete hcomplete [p5] PAGE 20
  22. 22. Operational support: Recommend PAGE 21
  23. 23. Recommend• Possible recommendations: − next activity; − suitable resource; or − routing decision.• A recommendation is always given with respect to a specific goal.• Examples of goals are: − minimize the remaining flow time; − minimize the total costs; − maximize the fraction of cases handled within 4 weeks; − maximize the fraction of cases that is accepted; and − minimize resource usage. PAGE 22
  24. 24. Relation between prediction andrecommendation possible next state prediction current state a1 a2 ak ... PAGE 23
  25. 25. Process mining spectrum people organizations machines business “world” processes documents information system(s) Chapter 1 Introduction provenance event logs Part I: Preliminaries “pre “post Chapter 2 Chapter 3 mortem” current historic mortem” Process Modeling and Analysis Data Mining data data Part II: From Event Logs to Process Models Chapter 4 Chapter 5 Chapter 6 Getting the Data Process Discovery: An Advanced Processnavigation auditing cartography Introduction Discovery Techniques recommend Part III: Beyond Process Discovery diagnose compare enhance discover promote explore predict detect Chapter 7 Chapter 8 Chapter 9 check Conformance Mining Additional Operational Support Checking Perspectives Part IV: Putting Process Mining to Work Chapter 10 Chapter 11 Chapter 12 Tool Support Analyzing “Lasagna Analyzing “Spaghetti Processes” Processes” models Part V: Reflection de jure models de facto models Chapter 13 Chapter 14 Cartography and Epilogue Navigation control-flow control-flow data/rules data/rules resources/ resources/ organization organization PAGE 24

×