Upload
eric-king
View
216
Download
0
Embed Size (px)
Citation preview
/faculteit technologie management 1
Process Mining: Control-Flow Process Mining: Control-Flow Mining AlgorithmsMining Algorithms
Ana Karla Alves de MedeirosAna Karla Alves de Medeiros
Eindhoven University of Technology
Department of Information Systems
/faculteit technologie management 2
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 3
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 4
Process Mining
1. Register at hospital
2. Talk to doctor
3. Take blood test
4. Take X-ray
5. Get results
6. Talk to doctor
7. Go home
1. Register at hospital
2. Talk to doctor
3. Undergo surgery
4. Take medicines
5. Take blood sample
6. Talk to doctor
7. Go home
1. Register at hospital
2. Talk to doctor
3. Undergo surgery
4. Take medicines
5. Take blood sample
6. Talk to doctor
7. Go home
EventEventLogsLogs
1. Register at hospital
2. Talk to doctor
3. Undergo surgery
4. Take medicines
5. Take blood sample
6. Talk to doctor
7. Go home
1. Register at hospital
2. Talk to doctor
3. Undergo surgery
4. Take medicines
5. Take blood sample
6. Talk to doctor
7. Go home
1. Register at hospital
2. Talk to doctor
3. Undergo surgery
4. Take medicines
5. Take blood sample
6. Talk to doctor
7. Go home
/faculteit technologie management 5
Process Mining Start
Register order
Prepareshipment
Ship goods
(Re)send bill
Receive paymentContact
customer
Archive order
End
Performance AnalysisPerformance Analysis
Process ModelProcess Model Organizational ModelOrganizational Model
Social NetworkSocial Network
EventEventLogLog
MiningMiningTechniquesTechniques
Auditing/SecurityAuditing/Security
MinedMinedModelsModels
/faculteit technologie management 6
Event Logs are Everywhere!aaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaaaaaaaaaaaa
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
Machines, Municipalities, Airports,Machines, Municipalities, Airports,Internet, Hospitals, etc.Internet, Hospitals, etc.
/faculteit technologie management 7
Tools
• www.processmining.org• ProM 4.2• ProMimport• Free tools!
/faculteit technologie management 8
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 9
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 10
information system
modelsanalyzes
discovery
records events, e.g., messages,
transactions, etc.
specifies configures
implements
analyzes
supports/controls
extensionconformance
“world”people machines
organizationscomponents
business processes
(process)model
event logs
Process Mining Tools
Types of Algorithms
/faculteit technologie management 11
information system
modelsanalyzes
discovery
records events, e.g., messages,
transactions, etc.
specifies configures
implements
analyzes
supports/controls
extensionconformance
“world”people machines
organizationscomponents
business processes
(process)model
event logs
Process Mining Tools
Start
Register order
Prepareshipment
Ship goods
(Re)send bill
Receive paymentContact
customer
Archive order
End
Process ModelProcess Model
Organizational ModelOrganizational Model
Social NetworkSocial Network
Types of Algorithms
/faculteit technologie management 12
information system
modelsanalyzes
discovery
records events, e.g., messages,
transactions, etc.
specifies configures
implements
analyzes
supports/controls
extensionconformance
“world”people machines
organizationscomponents
business processes
(process)model
event logs
Process Mining Tools
Auditing/SecurityAuditing/Security
Start
Register order
Prepareshipment
Ship goods
(Re)send bill
Receive paymentContact
customer
Archive order
End
Compliance Compliance Process ModelProcess Model
Types of Algorithms
/faculteit technologie management 13
information system
modelsanalyzes
discovery
records events, e.g., messages,
transactions, etc.
specifies configures
implements
analyzes
supports/controls
extensionconformance
“world”people machines
organizationscomponents
business processes
(process)model
event logs
Process Mining Tools
Start
Register order
Prepareshipment
Ship goods
(Re)send bill
Receive paymentContact
customer
Archive order
End
Bottlenecks/Bottlenecks/Business RulesBusiness RulesProcess ModelProcess Model
Performance AnalysisPerformance Analysis
Types of Algorithms
/faculteit technologie management 14
Process Mining
EventEventLogLog
Discovery Techniques: Discovery Techniques: Control-Flow MiningControl-Flow Mining
MinedMinedModelModel
1. Start
2. Get Ready
3. Travel by Train
4. Beta Event Starts
5. Visit Brewery
6. Have Dinner
7. Go Home
8. Travel by Train
1. Start
2. Get Ready
3. Travel by Train
4. Beta Event Starts
5. Give a Talk
6. Visit Brewery
7. Have Dinner
8. Go Home
9. Travel by Train
1. Start
2. Get Ready
3. Travel by Car
4. Beta Event Starts
5. Give a Talk
6. Visit Brewery
7. Have Dinner
8. Go Home
9. Pay Parking
10. Travel by Car
1. Start
2. Get Ready
3. Travel by Car
4. Conference Starts
5. Join Reception
6. Have Dinner
7. Go Home
8. Pay Parking
9. Travel by Car
10. End
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
StartStart
Get ReadyGet Ready
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Conference StartsConference Starts
Give a TalkGive a Talk
Join ReceptionJoin Reception
Have DinnerHave Dinner
Go HomeGo Home
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Pay Pay ParkingParking
EndEnd
/faculteit technologie management 15
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 16
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 17
Common Constructs
• Sequence• Splits• Joins• Loops• Non-Free Choice• Invisible Tasks• Duplicate Tasks
Pay Pay ParkingParking
Get Ready
Travel by CarTravel by Train
Defence Starts
Ask Question
Defence Ends
Go Home
Travel by Train Pay for Parking
Travel by Car
Give a Talk
Have Drinks
Get Get ReadyReady
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Defense StartsDefense Starts
Give a TalkGive a Talk
Ask QuestionAsk Question
Defense EndsDefense Ends
Go HomeGo Home
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Have DrinksHave Drinks
/faculteit technologie management 18
Common Constructs
• Sequence• Splits• Joins• Loops• Non-Free Choice• Invisible Tasks• Duplicate Tasks
Pay Pay ParkingParking
Get Ready
Travel by CarTravel by Train
Defence Starts
Ask Question
Defence Ends
Go Home
Travel by Train Pay for Parking
Travel by Car
Give a Talk
Have Drinks
Get Get ReadyReady
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Defense StartsDefense Starts
Give a TalkGive a Talk
Ask QuestionAsk Question
Defense EndsDefense Ends
Go HomeGo Home
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Have DrinksHave Drinks
+ noise in logs!
/faculteit technologie management 19
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 20
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 21
Event Log: Mining XML (MXML)
The notion The notion of which of which tasks tasks belong to a belong to a same same instance is instance is crucial for crucial for applying applying process process mining mining techniques!techniques!
/faculteit technologie management 22
Event Log: Mining XML (MXML)
/faculteit technologie management 23
Event Log: Mining XML (MXML)
Compulsory Compulsory fields!fields!
/faculteit technologie management 24
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 25
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 26
α-algorithm
1. Read a log
2. Get the set of tasks
3. Infer the ordering relations
4. Build the net based on inferred relations
5. Output the net
Core Step!Core Step!
/faculteit technologie management 27
• Direct succession: x>y iff for some case x is directly followed by y.
• Causality: xy iff x>y and not y>x.
• Parallel: x||y iff x>y and y>x
• Unrelated: x#y iff not x>y and not y>x.
case 1 : task A case 1 : task A case 2 : task A case 2 : task A case 3 : task A case 3 : task A case 3 : task B case 3 : task B case 1 : task B case 1 : task B case 1 : task C case 1 : task C case 2 : task C case 2 : task C case 4 : task A case 4 : task A case 2 : task B case 2 : task B ......
A>BA>BA>CA>CB>CB>CB>DB>DC>BC>BC>DC>DE>FE>F
AABB
AACC
BBDD
CCDD
EEFF
B||CB||CC||BC||B
ABCDABCD
ACBDACBD
EFEF
α-algorithm - Ordering Relations >,,||,#
/faculteit technologie management 28
Let W be a workflow log over T. (W) is defined as follows.
1. TW = { t T W t },
2. TI = { t T W t = first() },
3. TO = { t T W t = last() },
4. XW = { (A,B) A TW B TW a Ab B a W b a1,a2 A a1#W
a2 b1,b2 B b1#W b2 },
5. YW = { (A,B) X (A,B) XA A B B (A,B) = (A,B) },
6. PW = { p(A,B) (A,B) YW } {iW,oW},
7. FW = { (a,p(A,B)) (A,B) YW a A } { (p(A,B),b) (A,B) YW b
B } { (iW,t) t TI} { (t,oW) t TO}, and
8. (W) = (PW,TW,FW).
α-algorithm - Formalization
/faculteit technologie management 29
A
B
C
D
E F
ABCDABCD
ACBDACBD
EFEF
AABB
AACC
BBDD
CCDD
EEFF
B||CB||CC||BC||B
α-algorithm - Insight
/faculteit technologie management 30
• If log is complete with respect to relation >, it can be used to mine SWF-net without short loops
• Structured Workflow Nets (SWF-nets) have no implicit places and the following two constructs cannot be used:
α-algorithm – Log properties + target nets
/faculteit technologie management 31
One-length
Two-length
B>B and not B>B implies BB (impossible!)
A>B and B>A implies A||B and B||A instead of AB and BA
α-algorithm – No short loops Why no short
loops?
/faculteit technologie management 32
• No invisible tasks, non-free-choice or duplicate tasks• No noisy logs
α-algorithm – Common Constructs
Why no duplicate
tasks?
Why not invible tasks?
Why noise-free
logs?
/faculteit technologie management 33
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Algorithm• Fuzzy Miner
/faculteit technologie management 34
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Algorithm• Fuzzy Miner
/faculteit technologie management 35
Heuristics Miner
1. Read a log
2. Get the set of tasks
3. Infer the ordering relations based on their frequencies
4. Build the net based on inferred relations
5. Output the net
/faculteit technologie management 36
Heuristics Miner
Insight:The more frequently a task A directly follows another task B, and the less frequently the opposite occurs, the higher the probability that A causally follows B!
/faculteit technologie management 37
• No non-free-choice or duplicate tasks• Robust to invisible tasks and noisy logs
α-algorithm – Common Constructs
Why no non-free-choice?
Why no guarantee whole net will be correct?
/faculteit technologie management 38
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 39
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 40
Genetic Process Mining (GPM)
• Genetic Algorithms + Process Mining• Genetic Algorithms
– Search technique that mimics the process of evolution in biological systems
• Advantages– Tackle all common structural constructs– Robust to noise
• Disadvantages– Computational Time
/faculteit technologie management 41
Genetic Process Mining (GPM)
Algorithm:
Internal Representation
Fitness Measure
Genetic Operators
/faculteit technologie management 42
GPM – Fitness MeasureStart
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
StartStart
Get ReadyGet Ready
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Conference StartsConference Starts
Give a TalkGive a Talk
Visit BreweryVisit Brewery
Have DinnerHave Dinner
Go HomeGo Home
Travel byTravel by TrainTrain
Travel byTravel by CarCar
Pay Pay ParkingParking
EndEnd
• Guides
the search!
/faculteit technologie management 43
GPM – Fitness Measure
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
/faculteit technologie management 44
GPM – Fitness Measure
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
Start
Get Ready
Travel by TrainBETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Pay for Parking
Travel by Car
End
Give a Talk
StartStart
Get ReadyGet Ready
Travel byTravel by CarCar
Conference StartsConference Starts
Give a TalkGive a Talk
Visit BreweryVisit Brewery
Have DinnerHave Dinner
Go HomeGo Home
Pay Pay ParkingParking
EndEnd
Travel byTravel by TrainTrain
Punish for the amount of enabled tasks during the parsing!
Overgeneral solution
/faculteit technologie management 45
GPM – Fitness Measure
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
Start
Get Ready
Travel by TrainBETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Pay for Parking
Travel by Car
End
Give a Talk
Start
Get Ready
Travel by CarTravel by Train
BETA PhD Day Starts
Visit Brewery
Have Dinner
Go Home
Travel by Train Pay for Parking
Travel by Car
End
Give a Talk
StartStart Start
Get ReadyGet Ready Get Ready
Travel by Train Travel by Car
BETA PhD Day StartsBETA PhD Day Starts BETA PhD Day Starts
Give a Talk
Visit BreweryVisit Brewery Visit Brewery
Have DinnerHave Dinner Have Dinner
Go HomeGo HomeGo Home
Travel by Train Pay for Parking
Travel by Car
EndEnd End
StartStart
Get ReadyGet Ready
Travel by CarTravel by Car
Conference StartsConference Starts
Give a TalkGive a Talk
Visit BreweryVisit Brewery
Have DinnerHave Dinner
Go HomeGo Home
Travel by TrainTravel by Train
Travel by CarTravel by Car
Pay ParkingPay Parking
EndEnd
Travel by TrainTravel by Train
Punish for the amount of duplicate tasks with common input/output tasks!
Overspecific solution
/faculteit technologie management 46
GPM – DGA ProM Plug-in
Why does the GA Miner takes so
much time?
How could we improve its running time without
changing the code?
/faculteit technologie management 47
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 48
Process Mining
• Short Recap• Types of Process Mining Algorithms• Common Constructs• Input Format• α-algorithm• Heuristics Miner• Genetic Miner• Fuzzy Miner
/faculteit technologie management 49
Fuzzy Miner - Motivation
Mine less structured processes!
/faculteit technologie management 50
Fuzzy Miner - Motivation
/faculteit technologie management 51
Fuzzy Miner
/faculteit technologie management 52
Fuzzy Miner
No “Ask Question” or “Give Talk”!
All details!
Abstracting even more from details!
/faculteit technologie management 53
Conclusions
• The notion of a process instance is crucial!• Ordering of tasks is the basic information• Frequencies are important to handle noise• Local approaches
– α-algorithm, Heuristics Miner
• Global approaches– Genetic Miner and Fuzzy Miner