AUTOMATIC MODEL EVOLUTION

• US 20120330639A1
• Filed: 09/06/2012
• Published: 12/27/2012
• Est. Priority Date: 05/20/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bisdikian, Chatschik, Branch, Joel W., He, Ting
• Granted Patent: US 8,577,818 B2
• Time in Patent Office: Days
• US Class Current: 703/22
• CPC Class Codes: G06F 11/3447 Performance evaluation by modeling
• CPC Class Codes: G06F 11/3476 Data logging G06F11/14, G06F11/2205 take precedence
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/87 Monitoring of transactions
• CPC Class Codes: G06F 8/355 Round-trip engineering

Abstract

A method includes performing, on a processor, evaluating log data; determining at least one discrepancy between the log data and a system model; generating a candidate model based on the discrepancy and a model template; and updating the system model based on the candidate model.

Claims

1. A method comprising:

performing on a processor,

evaluating log data;

determining at least one discrepancy between the log data and a system model;

generating a candidate model based on the discrepancy and a model template; and

updating the system model based on the candidate model.

2. The method according to claim 1, further comprising selecting the model template from a templates datastore comprising a plurality of model templates.

3. The method according to claim 1, wherein the model template includes a set of rules for updating a model given the discrepancy and a computerized agent for executing the rules.

4. The method according to claim 1, further comprising evaluating the candidate model to determine whether to execute the updating.

5. The method according to claim 4, wherein the evaluating is based on user-entered information.

6. The method according to claim 4, wherein the evaluating is executed automatically based on rules specified in the model template.

7. The method according to claim 6, wherein the evaluating the candidate model includes evaluating for a goodness of fit.

8. The method according to claim 7, further comprising running the candidate model to determine the goodness of fit.

9. The method according to claim 1, wherein the model template includes model generation implementation logic.

10. The method according to claim 1, wherein the model template includes goodness of fit measurement logic.

11. The method according to claim 1, wherein the model template includes confidence of goodness of fit measurement logic.

12. The method according to claim 1, wherein the model template includes decision threshold definitions.