Download presentation
1
Process Mining Control flow process discovery
Fabrizio Maria Maggi (based on Process Mining book – Springer copyright 2011 and lecture material by Marlon Dumas, Wil van der Aalst and Ana Karla Alves de Medeiros
2
Process Mining
3
Discovery Techniques:
Control-Flow Mining Start Get Ready Travel by Train Car Conference Starts Give a Talk Join Reception Have Dinner Go Home Pay Parking End Start Get Ready Travel by Train Beta Event Starts Visit Brewery Have Dinner Go Home Start Get Ready Travel by Train Beta Event Starts Give a Talk Visit Brewery Have Dinner Go Home Start Get Ready Travel by Car Beta Event Starts Give a Talk Visit Brewery Have Dinner Go Home Pay Parking Start Get Ready Travel by Car Conference Starts Join Reception Have Dinner Go Home Pay Parking End Mined Model Event Log Discovery Techniques: Control-Flow Mining
4
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are.....
5
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are..... + noise in logs!
6
α-algorithm Basic Idea: Ordering relations
case 1 : task A case 2 : task A case 3 : task A case 3 : task B case 1 : task B case 1 : task C case 2 : task C case 4 : task A case 2 : task B ... 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. ABCD ACBD EF A>B A>C B>C B>D C>B C>D E>F AB AC BD CD EF B||C C||B
7
Basic Idea: Example
8
Basic Idea: Example
9
Basic Idea: Footprints
10
Basic Idea: Patterns
11
α-algorithm
12
α-algorithm: Applicative Example
13
α-algorithm: Applicative Example
14
α-algorithm: Applicative Example
15
α-algorithm: Applicative Example
16
α-algorithm: Applicative Example
17
α-algorithm: Applicative Example
18
α-algorithm: Applicative Example
19
α-algorithm: Applicative Example
20
α-algorithm: Applicative Example
21
α-algorithm: Applicative Example
22
α-algorithm: Exercise
23
Limitations: short loops of length 1
b>b and not b>b implies bb (impossible!)
24
Limitations: short loops of length 1
Example “Short1”
25
Limitations: short loops of length 2
a>b and b>a implies a||b and b||a instead of ab and ba
26
Limitations: short loops of length 2
Example “Short2”
27
Limitations: non-free-choice nets
Example “nonlocal”
28
Limitations: invisible tasks
Example “invisible”
29
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are.....
30
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are..... + noise in logs!
31
Heuristic Miner
32
Heuristic Miner
33
Heuristic Miner
34
Heuristic Miner Example “heuristic”
35
Heuristic Miner Example “heuristic”
36
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are.....
37
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are..... + noise in logs!
38
Genetic Miner
39
GPM – Fitness Measure Guides the search! Start Get Ready Travel by
Train Car Conference Starts Give a Talk Visit Brewery Have Dinner Go Home Pay Parking End Guides the search!
40
GPM – Fitness Measure Overgeneral solution
Start Get Ready Travel by Car Conference Starts Give a Talk Visit Brewery Have Dinner Go Home Pay Parking End Train Overgeneral solution Punish for the amount of enabled tasks during the parsing!
41
Overspecific solution
GPM – Fitness Measure Start Overspecific solution Get Ready Travel by Train Travel by Car Conference Starts Give a Talk Visit Brewery Have Dinner Go Home Punish for the amount of duplicate tasks with common input/output tasks! Travel by Train Pay Parking Travel by Car End
42
Genetic Miner: Crossover
43
Genetic Miner: Mutation
44
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are.....
45
Mining Common Constructs
22 april 2017 Mining Common Constructs Pay Parking Get Ready Travel by Train Car Defense Starts Give a Talk Ask Question Defense Ends Go Home Have Drinks Sequence Splits Joins Loops Non-Free Choice Invisible Tasks Duplicate Tasks Since genetic process mining aims at mining the control-flow perspective of process models, we have investigated how the current techniques handle the common control-flow constructs in process models. The common constructs are..... + noise in logs!
46
Fuzzy Miner - Motivation
Mine less structured processes!
47
Fuzzy Miner - Motivation
48
Fuzzy Miner
49
Fuzzy Miner
50
BPI Challenge and … to sum up
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.