Leveraging path information to generate predictions for parallel business processes

• US 9,372,736 B2
• Filed: 05/06/2014
• Issued: 06/21/2016
• Est. Priority Date: 05/06/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Curbera, Francisco, Doganata, Yurdaer N., Lakshmanan, Geetika T., Unuvar, Merve
• Primary Examiner(s): NGUYEN, VAN H
• Application Number:
  US14/271,132
• Publication Number:
  US 20150324241A1
• Time in Patent Office: 777 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 11/3636 by tracing the execution of the program
• CPC Class Codes: G06F 9/52 Program synchronisation; Mutual exclusion, e.g. by means of semaphores
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling

Abstract

Systems and methods for determining a representation of an execution trace include identifying at least one execution trace of a business process model, the business process model including parallel paths where a path influences an outcome of a decision. Path information of the business process model is determined using a processor, the path information including at least one of task execution order for each parallel path, task execution order across parallel paths, and dependency between parallel paths. A path representation for the at least one execution trace is selected based upon the path information to determine a representation of the at least one execution trace.

Claims

1. A computer-implemented method for determining a representation of an execution trace, comprising:

identifying at least one execution trace of a process model, the process model including parallel paths where a path influences an outcome of a decision;

determining path information of the process model using a hardware processor by injecting at least one token in the process model such that the at least one token traces one or more active nodes representing the path information, the path information including at least one of;

task execution order for each parallel path, task execution order across parallel paths, and dependency between parallel paths; and

selecting a path representation for the at least one execution trace based upon the path information to determine a representation of the at least one execution trace.

2. The method as recited in claim 1, wherein selecting includes representing the at least one execution trace as a single path attribute having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and the task execution order information across parallel paths cannot be estimated.

3. The method as recited in claim 1, wherein selecting includes representing the at least one execution trace as multiple path attributes having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and the task execution order information can be estimated.

4. The method as recited in claim 1, wherein selecting includes representing the at least one execution trace as multiple path attributes having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and paths are independent.

5. The method as recited in claim 1, wherein selecting includes representing the at least one execution trace as a single path attribute having the task execution order across parallel paths, where paths are dependent.

6. The method as recited in claim 1, wherein selecting includes representing the at least one execution trace as multiple path attributes having the task execution order for each parallel path, and as a single path attribute having the task execution order across parallel path, where paths are dependent.

7. The method as recited in claim 6, wherein selecting further comprises comparing an information gain between:

a representation of the at least one execution trace as multiple path attributes having the task execution order for each parallel path; and

a representation of the at least one execution trace as the single path attribute having the task execution order across parallel path.

8. The method as recited in claim 7, wherein selecting further comprises representing the at least one execution trace as the representation having a higher information gain.

9. The method as recited in claim 1, further comprising training a predictive model by representing the at least one execution trace with the selected path representation to predict an outcome of the decision in the process model.

10. The method as recited in claim 1, further comprising computing deviation between paths of the process model by representing the at least one execution trace with the selected path representation.

11. The method as recited in claim 1, further comprising clustering paths of the process model by representing the at least one execution trace with the selected path representation.

12. A non-transitory computer readable storage medium comprising a computer readable program for determining a representation of an execution path, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:

identifying at least one execution trace of a process model, the process model including parallel paths where a path influences an outcome of a decision;

determining path information of the process model by injecting at least one token in the process model such that the at least one token traces one or more active nodes representing the path information, the path information including at least one of;

task execution order for each parallel path, task execution order across parallel paths, and dependency between parallel paths; and

selecting a path representation for the at least one execution trace based upon the path information to determine a representation of the at least one execution trace.

13. A system for determining a representation of an execution path, comprising:

a determination module configured to identify at least one execution trace of a process model, the process model including parallel paths where a path influences an outcome of a decision,

the determination module further configured to determine path information of the process model using a hardware processor by injecting at least one token in the process model such that the at least one token traces one or more active nodes representing the path information, the path information including at least one of;

task execution order for each parallel path, task execution order across parallel paths, and dependency between parallel paths; and

a selection module configured to select a path representation for the at least one execution trace based upon the path information to determine a representation of the at least one execution trace.

14. The system as recited in claim 13, wherein the selection module is further configured to represent the at least one execution trace as a single path attribute having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and the task execution order information across parallel paths cannot be estimated.

15. The system as recited in claim 13, wherein the selection module is further configured to represent the at least one execution trace as multiple path attributes having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and the task execution order information can be estimated.

16. The system as recited in claim 13, wherein the selection module is further configured to represent the at least one execution trace as multiple path attributes having the task execution order for each parallel path, where task execution order across parallel paths is not identifiable and paths are independent.

17. The system as recited in claim 13, wherein the selection module is further configured to represent the at least one execution trace as a single path attribute having the task execution order across parallel paths, where paths are dependent.

18. The system as recited in claim 13, wherein the selection module is further configured to:

represent the at least one execution trace as multiple path attributes having the task execution order for each parallel path, and as a single path attribute having the task execution order across parallel path, where paths are dependent; and

compare an information gain between;

a representation of the at least one execution trace as multiple path attributes having the task execution order for each parallel path, and

a representation of the at least one execution trace as the single path attribute having the task execution order across parallel path.

19. The system as recited in claim 18, wherein the selection module is further configured to represent the at least one execution trace as the representation having a higher information gain.

20. The system as recited in claim 13, wherein the selection module is further configured to train a predictive model by representing the at least one execution trace with the selected path representation to predict an outcome of the decision in the process model.