Method and system for modeling a system

• US 7,072,795 B2
• Filed: 12/21/2000
• Issued: 07/04/2006
• Est. Priority Date: 02/28/2000
• Status: Expired due to Fees

• Current Assignee: Panoratio Database Images GmbH (Panoratio Holdings, Inc.)
• Original Assignee: Panoratio Database Images GmbH (Panoratio Holdings, Inc.)
• Inventors: Tresp, Volker, Hofmann, Reimar, Haft, Michael
• Primary Examiner(s): Assouad, Patrick J
• Application Number:
  US10/204,900
• Publication Number:
  US 20030115016A1
• Time in Patent Office: 2,021 Days
• Field of Search: 702/181, 702/179, 702/187, 700/29, 700/47, 700/48, 700/51, 703/2, 709/224, 706/14, 706/15, 706/20, 706/21
• US Class Current: 702/181
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

The invention relates to a method and a system for detecting at least one partial model of a model pertaining to a system. A state of the system is described by state variables. At least on e of the state variables is a discrete state variable. Several value sets of the state variables are detected. A probability distribution for the state variables is detected by using the sets. The partial model of the system is detected using the sets and the probability distribution of the state variables and a statistical learning method. The partial model describes the system under the condition of the probability distribution for the state variables.

Claims

1. A method for determination of at least one partial model of a model of a system, a state of the system being described by state quantities, comprising:

determining sets of values of the state quantities, where at least one of the state quantities is a discrete state quantity;

determining a probability distribution for the state quantities from the sets; and

determining the partial model of the system using the sets, the probability distribution for the state quantities and a statistical learning method, the partial model describing the system under the precondition of the probability distribution for the state quantities.

2. A method according to claim 1, wherein the model includes plural partial models.

3. A method according to claim 2, wherein all the state quantities are discrete state quantities.

4. A method according to claim 3, wherein the probability distribution is a multinomial distribution or a binomial distribution.

5. A method according to claim 4, wherein at least one characteristic set of values of the state quantities is determined and the probability distribution for the state quantities has an extremum for the at least one characteristic set.

6. A method according to claim 5, wherein the extremum is a maximum.

7. A method according to claim 6, wherein a semantic designation is determined for the characteristic set.

8. A method according to claim 7, wherein a plurality of characteristic sets are determined.

9. A method according to claim 8, further comprising determining the at least one discrete state quantity by discretization of a continuous state quantity.

10. A method according to claim 9, further comprising determining a measure of a statistical uncertainty for at least one partial model.

11. A method according to claim 10, wherein a measure of the statistical uncertainty Is taken into account in the statistical learning method.

12. A method according to claim 11, wherein the measure of the statistical uncertainty is taken into account such that only one such partial model is learned which has a small measure of the statistical uncertainty.

13. A method according to claim 12, wherein the measure of the statistical uncertainty is a conditional entropy.

14. A method according to claim 13, wherein the model is a Bayesian network.

15. A method according to claim 14, further comprising determining a logarithmic likelihood in the statistical learning method.

16. A method according to claim 15, further comprising carrying out an expectation maximization method in the statistical learning method.

17. A method according to claim 16, further comprising determining a state of the system by at least one of a measurement of state quantities and a presetting of state quantities.

18. A method according to claim 17, further comprising obtaining a prognosis of a state of the system using the model.

19. A method according to claim 18,

wherein said obtaining the prognosis includes determining only partial state quantities of the set of state quantifies, and

wherein said method further comprises determining state quantities of the set using the model and the partial state quantities.

20. A method according to claim 19, wherein the system is defined as an Internet access.

21. A method according to claim 19, further comprising analysis of a plurality of Internet accesses.

22. A system for determination of at least one partial model of a model of a system, a state of the system being described by state quantities, comprising:

a processor programmed to determine sets of values of the state quantities, where at least one of the state quantities is a discrete state quantity;

to determine a probability distribution for the state quantities from the sets, and to determine the partial model of the system using the sets, the probability distribution for the state quantities and a statistical learning method, the partial model describing the system under the precondition of the probability distribution for the state quantities.

23. At least one computer readable medium storing at least one computer program for controlling a processor to execute a method for determination of at least one partial model of a model of a system, a state of the system being described by state quantities, said method comprising:

determining sets of values of the state quantities, where at least one of the state quantities is a discrete state quantity;

determining a probability distribution for the state quantities from the sets; and

determining the partial model of the system using the sets, the probability distribution for the state quantities and a statistical learning method, the partial model describing the system under the precondition of the probability distribution for the state quantities.