Optimizing the performance of computer tasks using intelligent agent with multiple program modules having varied degrees of domain knowledge

• US 7,386,522 B1
• Filed: 06/19/1998
• Issued: 06/10/2008
• Est. Priority Date: 03/21/1997
• Status: Expired due to Fees

• Current Assignee: ServiceNow Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Cragun, Brian John, Bigus, Joseph Phillip, Delp, Helen Roxlo
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US09/100,595
• Time in Patent Office: 3,644 Days
• Field of Search: 706/16, 706/15, 706/45, 706/49, 705/40, 709/202, 710/20
• US Class Current: 706/15
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards

Abstract

The performance of a given task is optimized by utilizing an intelligent agent having a plurality of program modules suited to perform the computer task but having varied degrees of domain knowledge. Based upon an objective criteria that may be determined for a given situation, one or more of the program modules in the intelligent agent may be selected to perform the task, thereby optimizing the performance of the computer task for a wide variety of situations.

Claims

1. A program product comprising:

(a) a program configured to perform a computer task using an intelligent agent, the program comprising an intelligent agent including at least one of a plurality of program modules having varied degrees of autonomy, wherein the plurality of program modules are each configured to handle a common computer task that includes conducting negotiations in an electronic commerce application, and wherein, based upon an objective criteria, at least one selected program module from the plurality of program modules is selected to handle the computer task; and

(b) a signal bearing media bearing the program.

2. The program product of claim 1, wherein the signal bearing media is transmission type media.

3. The program product of claim 1, wherein the signal bearing media is recordable media.

4. The program product of claim 1, wherein the program further includes an evaluation module configured to select the selected program module based upon the objective criteria.

5. The program product of claim 4, wherein the program further includes a reinforcement learning module, coupled to the evaluation module and configured to adaptively select program modules based upon the performance of the plurality of program modules in handling the computer task.

6. The program product of claim 5, wherein the reinforcement learning module comprises an adaptive heuristic critic neural network.

7. The program product of claim 4, wherein the evaluation module is configured to retrieve information for a selected computer task, determine a selected value for the objective criteria for the selected computer task, and select as the selected program module one of the plurality of program modules which is matched with the selected value of the objective criteria.

8. The program product of claim 4, wherein the evaluation module is implemented in an agent manager.

9. The program product of claim 4, wherein the evaluation module is implemented in the intelligent agent.

10. The program product of claim 4, wherein the intelligent agent includes only the selected program module from the plurality of program modules, and wherein the evaluation module is configured to construct the intelligent agent using the selected program module.

11. The program product of claim 4, wherein the intelligent agent includes each of the plurality of program modules, and wherein the evaluation module is configured to execute only the selected program module to handle the computer task.

12. The program product of claim 4, wherein the plurality of program modules are additive program modules, and wherein the evaluation module is configured to select a subset of the plurality of program modules to handle the computer task.

13. The program product of claim 4, wherein the plurality of program modules are alternative program modules, and wherein the evaluation module is configured to select only one of the plurality of program modules to handle the computer task.

14. The program product of claim 1, wherein the plurality of program modules includes a semi-autonomous program module, a fully-autonomous program module, and a fully-dependent program module.

15. The program product of claim 1, wherein the objective criteria includes a risk that a dispatched agent is subjected to in negotiations.

16. A method of handling a computer task using an intelligent agent, the method comprising the steps of:

(a) based upon an objective criteria, selecting at least one selected program module from a plurality of program modules having varied degrees of autonomy, wherein the plurality of program modules are each configured to handle a common computer task that includes conducting negotiations in an electronic commerce application; and

(b) configuring an intelligent agent to execute the at least one selected program module to handle the computer task.

17. The method of claim 16, wherein the intelligent agent includes only the selected program module from the plurality of program modules, and wherein the configuring step includes the step of constructing the intelligent agent using the selected program module.

18. The method of claim 16, wherein the intelligent agent includes each of the plurality of program modules, and wherein the configuring step includes the step of configuring the intelligent agent to execute only the selected program module to handle the computer task.

19. The method of claim 16, wherein the selecting step is performed by the intelligent agent.

20. The method of claim 16, wherein the selecting step is performed by an agent manager.

21. The method of claim 16, wherein the plurality of program modules are additive program modules, and wherein the selecting step includes the step of selecting a subset of the plurality of program modules to handle the computer task.

22. The method of claim 16, wherein the plurality of program modules are alternative program modules, and wherein the selecting step includes the step of selecting only one of the plurality of program modules to handle the computer task.

23. The method of claim 16, wherein the selecting step includes the step of adaptively selecting the selected program module using a reinforcement learning algorithm.

24. The method of claim 23, further comprising the steps of:

(a) obtaining performance information relating to the performance of the selected program module in handling the computer task; and

(b) supplying the performance information to the reinforcement learning algorithm.

25. The method of claim 23, wherein the reinforcement learning algorithm is implemented in an adaptive heuristic critic neural network.

26. The method of claim 16, wherein the selecting step includes the steps of:

(a) matching each of the plurality of program modules with a value of the objective criteria;

(b) determining a selected value of the objective criteria; and

(c) selecting as the selected program module a program module matching the selected value of the objective criteria.

27. The method of claim 26, wherein the selecting step further includes the step of retrieving information for a selected computer task, wherein the determining step determines the selected value of the objective criteria using the retrieved information.

28. The method of claim 16, wherein the plurality of program modules includes a semi-autonomous program module, a fully-autonomous program module, and a fully-dependent program module.

29. The method of claim 16, wherein the objective criteria includes a risk that a dispatched agent is subjected to in negotiations.

30. An apparatus for handling a computer task, comprising:

a memory; and

an intelligent agent resident in the memory, the intelligent agent including at least one of a plurality of program modules having varied degrees of autonomy, wherein the plurality of program modules are each configured to handle a common computer task that includes conducting negotiations in an electronic commerce application, and wherein, based upon an objective criteria, at least one selected program module from the plurality of program modules is selected to handle the computer task.

31. The apparatus of claim 30, further comprising an evaluation module configured to select the selected program module based upon the objective criteria.

32. The apparatus of claim 31, further comprising a reinforcement learning module, coupled to the evaluation module and configured to adaptively select program modules based upon the performance of the plurality of program modules in handling the computer task.

33. The apparatus of claim 32, wherein the reinforcement learning module comprises an adaptive heuristic critic neural network.

34. The apparatus of claim 31, wherein the evaluation module is configured to retrieve information for a selected computer task, determine a selected value for the objective criteria for the selected computer task, and select as the selected program module one of the plurality of program modules which is matched with the selected value of the objective criteria.

35. The apparatus of claim 31, wherein the evaluation module is implemented in an agent manager.

36. The apparatus of claim 31, wherein the evaluation module is implemented in the intelligent agent.

37. The apparatus of claim 31, wherein the intelligent agent includes only the selected program module from the plurality of program modules, and wherein the evaluation module is configured to construct the intelligent agent using the selected program module.

38. The apparatus of claim 31, wherein the intelligent agent includes each of the plurality of program modules, and wherein the evaluation module is configured to execute only the selected program module to handle the computer task.

39. The apparatus of claim 31, wherein the plurality of program modules are additive program modules, and wherein the evaluation module is configured to select a subset of the plurality of program modules to handle the computer task.

40. The apparatus of claim 31, wherein the plurality of program modules are alternative program modules, and wherein the evaluation module is configured to select only one of the plurality of program modules to handle the computer task.

41. The apparatus of claim 30, wherein the plurality of program modules includes a semi-autonomous program module, a fully-autonomous program module, and a fully-dependent program module.

42. The apparatus of claim 30, wherein the objective criteria includes a risk that a dispatched agent is subjected to in negotiations.

43. A method of handling a computer task on a remote computer system using an intelligent agent, the method comprising the steps of:

(a) determining a risk for the remote computer system;

(b) based upon the risk for the remote computer system, selecting at least one selected program module from a plurality of program modules having varied degrees of domain knowledge, wherein the plurality of program modules are configured to handle a common computer task in the remote computer system; and

(c) configuring an intelligent agent to execute the at least one selected program module to handle the computer task.

44. The method of claim 43, further comprising the step of matching each of the plurality of program modules with a risk level.

45. The method of claim 44, wherein the matching step includes the step of adaptively matching each program module based upon the actual performance of the plurality of program modules.