Method and apparatus for interpreting information

• US 7,275,047 B2
• Filed: 10/31/2003
• Issued: 09/25/2007
• Est. Priority Date: 04/15/1997
• Status: Expired due to Term

• Current Assignee: Cerebrus Solutions Ltd (Neural Technologies Limited)
• Original Assignee: Cerebrus Solutions Ltd (Neural Technologies Limited)
• Inventors: Field, Simon, Barson, Paul Colin, Howard, Gary, Hobson, Philip W.
• Primary Examiner(s): Hirl; Joseph P
• Assistant Examiner(s): Holmes; Michael B.
• Application Number:
  US10/698,171
• Publication Number:
  US 20040093316A1
• Time in Patent Office: 1,425 Days
• Field of Search: 706/20, 706/12, 706/13, 706/25
• US Class Current: 706/20
• CPC Class Codes: G06F 18/24765 Rule-based classification
• CPC Class Codes: G06N 3/042 Knowledge-based neural networks; Logical representations of neural networks
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method of processing data relating to a plurality of examples using a data classifier arranged to classify input data into one of a number of classes, and a rule inducer, comprising the steps of:

• • (i) inputting a series of inputs to the data classifier so as to obtain a series of corresponding outputs;
  • (ii) inputting said series of outputs and at least some of said series of inputs to the rule inducer so as to obtain a series of rules which describe relationships between the series of inputs to the data classifier and the series of corresponding outputs from the data classifier.

Claims

1. A method of analyzing first data elements representative of usage of a data processing system by users, the method comprising:

inputting the first data element into a first data classifier;

operating the first data classifier to generate classification outputs from the first data elements, wherein the classification outputs are indicative of classes of the first data elements;

inputting the first data elements and the classification outputs into a rule inducer;

operating the rule inducer to generate rules explaining relationships between the first data elements and the classification outputs; and

outputting the rules explaining the relationships to a user.

2. The method of claim 1, wherein the first data elements include data based on usage of a telecommunications network.

3. The method of claim 2, wherein the data include call detail records.

4. The method of claim 1, wherein the first data classifier includes at least one of:

a neural network, an unsupervised classifier, and a Bayesian classifier.

5. The method of claim 1, wherein operating the rule inducer includes:

combining the first data elements and the corresponding classification outputs.

6. The method of claim 1, further comprising:

based on the generated rules, generating a second data classifier.

16. A method according to claim 1 wherein the first data elements are representative of at least one of financial transactions and chargeable transactions and the data processing system is a transaction handling system.

17. A method according to claim 1, wherein the data processing system is a telecommunication system and the first data elements are data representative of usage of the telecommunications system.

7. An analysis system, comprising:

a first data classifier configured to generate classification outputs from first data elements input into the first data classifier, wherein the classification outputs are indicative of classes of the first data elements, and

a rule inducer configured to generate rules indicative of a relationship between the first data elements and the generated classification outputs, and further configured to output the rules explaining the relationships.

8. The system of claim 7, wherein the first data elements include data based on usage of a telecommunications network.

9. The system of claim 8, wherein the data include call detail records.

10. The system of claim 7, wherein the data classifier includes at least one of:

a neural network, an unsupervised classifier, and a Bayesian classifier.

11. The system of claim 7, further comprising:

a second data classifier based on the rules.

18. A system according to claim 7, wherein in the first data elements are representative of at least one of financial transactions and chargeable transactions and the data processing system is a transaction handling system.

19. A system according to claim 7, wherein the data processing system is a telecommunication system and the first data elements are data representative of usage of the telecommunications system.

12. A processor program for classifying data, the processor program disposed on a processor-readable medium and comprising instructions to cause a processor to:

generate classification outputs from first data elements by inputting the first data elements into a first data classifier configured to generate the classification outputs from the first data elements, wherein the classification outputs are indicative of classes of the first data elements, and

generate rules indicative of a relationship between the first data elements and the classification outputs by inputting the first data elements and the classification outputs into a rule inducer configured to output the rules based on said first data elements and said classification outputs.

13. The processor program of claim 12, wherein the first data elements include data based on usage of a telecommunications network.

14. The processor program of claim 12, further comprising instructions to cause to a processor to:

generate a second data classifier based on the rules.

15. The processor program of claim 12, where the first data classifier is at least one of:

a neural network, an unsupervised classifier, and a Bayesian classifier.

20. A processor program according to claim 12, wherein the first data elements are representative of at least one of financial transactions and chargeable transactions and the data processing system is a transaction handling system.

21. A processor program according to claim 12, wherein the data processing system is a telecommunication system and the first data elements are data representative of usage of the telecommunications system.

22. A method of analysing first data elements representative of usage of a data processing system by system users, the method comprising:

inputting the first data elements into a first data classifier;

operating the first data classifier to generate classification outputs from the first data elements, wherein the classification outputs are indicative of classes of the first data elements;

inputting the first data elements and the classification outputs into a rule inducer; and

operating the rule inducer to generate rules explaining relationships between the first data elements and the classification outputs, such that applying the generated rules to second data elements representative of usage of a data processing system by system users results in classification of the usage of the data processing system.

23. A system according to claim 22, wherein the first data elements are representative of at least one of financial transactions and chargeable transactions and the data processing system is a transaction handling system.

24. A system according to claim 22, wherein the data processing system is a telecommunication system and the first data elements are data representative of usage of the telecommunications system.