Communication between intelligent agents and humans in a distributed system environment

• US 20040205034A1
• Filed: 03/31/2003
• Published: 10/14/2004
• Est. Priority Date: 03/31/2003
• Status: Active Grant

• Current Assignee: Wrp IP Management, LLC
• Original Assignee: International Business Machines Corporation
• Inventors: Dunbar, Anthony M., Bigus, Joseph P., Hintermeister, Gregory R.
• Granted Patent: US 7,124,119 B2
• Time in Patent Office: Days
• US Class Current: 706/10
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals

Abstract

A method, apparatus and article of manufacture for problem identification and resolution using intelligent agents. In at least one embodiment, an agent is a software element configured to detect a situation (e.g., problem or problems) and take steps to preserve a context in which the situation occurs. The agent may also be configured to identify one or more courses of action (e.g., solutions) to be taken in response to the situation. In one embodiment, a user trains an agent to take a particular action upon detecting a particular problem. The training may be initiated after accessing a log containing details about the problem context and recommended courses of action.

Claims

1. A method, performed by one or more intelligent software agents in a computerized environment, comprising:

identifying a problem in the computerized environment; and

storing a context of the problem, wherein the stored context of the problem preserves sufficient information to validate an existence of the problem at a later time.

2. The method of claim 1, wherein the context of the problem comprises at least one of (i) data describing a state of the computerized environment at a time when an intelligent software agent identified the problem;

and (ii) internal state data of the intelligent software agent that identified the problem.

3. The method of claim 1, wherein the stored context describes a corrective action taken by an intelligent software agent in response to the problem.

4. The method of claim 1, further comprising notifying a user of the stored context.

5. The method of claim 1, further comprising taking corrective action with respect to the problem according to a user selection from a list of possible actions.

6. The method of claim 1, further comprising:

receiving a request to address the problem according to a specified action;

validating the existence of the problem after receiving the request; and

performing the specified action if the existence of the problem is validated.

7. The method of claim 6, wherein identifying the problem is performed by a first intelligent software agent and the specified action is performed by a second intelligent software agent.

8. The method of claim 1, further comprising storing one or more possible actions to address the problem.

9. The method of claim 8, further comprising identifying, for a user, a suggested corrective action from the stored one or more possible actions.

10. The method of claim 8, further comprising identifying, for a user, a corrective action taken by the intelligent software agent from the one or more possible actions.

11. The method of claim 8, further comprising notifying a user of the stored context and one or more possible actions.

12. The method of claim 8, further comprising making the context of the problem and the one or more possible actions to address the problem available for inspection by a user.

13. The method of claim 8, further comprising taking corrective action with respect to the problem according to a user selection of one of the possible actions.

14. The method of claim 8, further comprising:

receiving a user instruction to take corrective action with respect to the problem according to a user-selected action different from the one or more possible actions; and

configuring attributes of the intelligent software agent, whereby the intelligent software agent is trained.

15. The method of claim 8, wherein the context of the problem describes at least each aspect of a state of the computerized environment considered by the agent in determining the possible actions.

16. The method of claim 8, further comprising automatically performing a corrective action selected from the possible actions without first requesting an instruction from a user indicating a desired action in response to the problem.

17. The method of claim 16, further comprising receiving training from a user with respect to the corrective action.

18. The method of claim 16, further comprising:

logging the corrective action; and

receiving training from a user with respect to the logged corrective action.

19. A method, performed by one or more intelligent software agents in a computerized environment, comprising:

performing an assigned function;

identifying a problem;

storing a context of the problem, wherein the stored context of the problem preserves sufficient information to validate an existence of the problem at a later time; and

continuing performance of the assigned function prior to performing an action directed to resolving the problem.

20. The method of claim 19, further comprising:

receiving a request to address the problem according to a specified action;

validating the existence of the problem after receiving the request; and

performing the specified action if the existence of the problem is validated.

21. The method of claim 19, wherein the context of the problem comprises at least one of (i) data describing a state of the computerized environment at a time when an intelligent software agent identified the problem;

and (ii) internal state data of the intelligent software agent that identified the problem.

22. The method of claim 19, further comprising determining one or more possible actions to address the problem and storing the one or more possible actions with the context of the problem.

23. The method of claim 22, further comprising:

receiving a request to address the problem according to the stored one or more possible actions; and

validating an existence of the problem.

24. The method of claim 19, further comprising:

receiving a request to address the problem; and

addressing the problem.

25. The method of claim 24, wherein addressing the problem comprises correcting the problem.

26. The method of claim 24, wherein storing the context comprises storing one or more possible actions, and wherein the request specifies one of the stored one or more possible actions.

27. The method of claim 24, further comprising;

logging a corrective action taken to address the problem; and

receiving training from a user with respect to the logged corrective action.

28. A computer readable medium containing a program which, when executed, causes one or more intelligent software agents to perform an operation in a computerized environment, the operation comprising:

identifying a problem in the computerized environment;

storing a context of the problem, wherein the stored context of the problem preserves sufficient information to validate an existence of the problem at a later time; and

storing one or more possible actions to address the problem.

29. The computer readable medium of claim 28, wherein the context of the problem comprises at least one of (i) data describing a state of the computerized environment at a time when an intelligent software agent identified the problem;

and (ii) internal state data of the intelligent software agent that identified the problem.

30. The computer readable medium of claim 28, the operation further comprising identifying, for a user, a suggested corrective action.

31. The computer readable medium of claim 28, the operation further comprising identifying, for a user, a corrective action taken by an intelligent software agent.

32. The computer readable medium of claim 28, the operation further comprising notifying a user of the stored context.

33. The computer readable medium of claim 28, the operation further comprising taking corrective action with respect to the problem according to a user selection.

34. The computer readable medium of claim 28, wherein the context of the problem describes at least each aspect of a state of the computerized environment considered by the agent in determining the possible actions.

35. The computer readable medium of claim 28, the operation further comprising automatically performing a corrective action without first requesting an instruction from a user indicating a desired action in response to the problem.

36. The computer readable medium of claim 35, the operation further comprising receiving training from a user with respect to the corrective action.

37. The computer readable medium of claim 28, the operation further comprising:

logging the corrective action; and

receiving training from a user with respect to the logged corrective action.

38. The computer readable medium of claim 28, the operation further comprising:

receiving a request to address the problem according to a specified action;

validating the existence of the problem after receiving the request; and

performing the specified action if the existence of the problem is validated.

39. The computer readable medium of claim 38, wherein identifying the problem is performed by a first intelligent software agent and the specified action is performed by a second intelligent software agent.

40. The computer readable medium of claim 28, further comprising storing one or more possible actions to address the problem.

41. The computer readable medium of claim 40, wherein the context of the problem and the one or more possible actions to address the problem are stored to an object.

42. The computer readable medium of claim 40, further comprising:

receiving a user instruction to take corrective action with respect to the problem according to a user-selected action different from the one or more possible actions; and

configuring attributes of the intelligent software agent, whereby the intelligent software agent is trained.

43. A computer readable medium containing a program which, when executed, causes an intelligent software agent to perform an operation in a computerized environment, the operation comprising:

performing an assigned function;

identifying a problem;

storing a context of the problem, wherein the stored context of the problem preserves sufficient information to validate an existence of the problem at a later time; and

continuing performance of the assigned function prior to performing an action directed to resolving the problem.

44. The computer readable medium of claim 43, the operation further comprising:

receiving a request to address the problem according to a specified action;

validating the existence of the problem after receiving the request; and

performing the specified action if the existence of the problem is validated.

45. The computer readable medium of claim 43, wherein the context of the problem comprises at least one of (i) data describing a state of the computerized environment at a time when an intelligent software agent identified the problem;

and (ii) internal state data of the intelligent software agent that identified the problem.

46. The computer readable medium of claim 43, the operation further comprising receiving a request to address the problem according to the stored one or more possible actions.

47. The computer readable medium of claim 43, the operation further comprising:

receiving a request to address the problem; and

addressing the problem.

48. The computer readable medium of claim 47, wherein addressing the problem comprises correcting the problem.

49. The computer readable medium of claim 47, wherein storing the context comprises storing one or more possible actions directed to the problem, and wherein the request specifies one of the stored one or more possible actions.

50. The computer readable medium of claim 47, the operation further comprising:

logging a corrective action taken to address the problem; and

receiving training from a user with respect to the logged corrective action.

51. The computer readable medium of claim 43, the operation further comprising determining one or more possible actions to address the problem and storing the one or more possible actions with the context of the problem.

52. The computer readable medium of claim 51, the operation further comprising:

receiving a request to address the problem according to the stored one or more possible actions; and

validating an existence of the problem.

53. A computer defining a computerized environment, comprising:

a plurality of intelligent software agents executing in the computerized environment;

a log containing at least one situation data structure, each situation data structure being created by one of the intelligent software agents in response to detecting a problem and containing a problem context describing a state of the computerized environment at a time when the intelligent software agent identified the problem and preserving sufficient information to validate an existence of the problem at a later time; and

a user interface allowing interaction between a user and the plurality of intelligent software agents, and between the user and the situation data structures.

54. The computer of claim 53, wherein the user interface is configured with a user-selectable interface element which, when selected, displays one or more training screens for training one or more of the plurality of intelligent software agents.

55. The computer of claim 54, wherein the interface element is presented to the user upon accessing, by the user, a situation data structure stored in the log.

56. The computer of claim 54, wherein the one or more training screens comprise:

a problem description describing a particular problem detected by an intelligent software agent;

a response description describing an action taken in response to the particular problem; and

a menu of other user-selectable actions which may be taken in response to the particular problem.