Method and system for generating object classification models

• US 20060074829A1
• Filed: 09/17/2004
• Published: 04/06/2006
• Est. Priority Date: 09/17/2004
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Aklilu, Ameha, Hijer, Raed, Velez, Wilson
• Granted Patent: US 7,996,339 B2
• Time in Patent Office: Days
• US Class Current: 706/20
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

A method for generating object classification models is disclosed. Initially, a set of training data is fed into a training algorithm to generate a first object classification model. A set of field data is then applied to the first object classification model to produce a set of field object classifications. The number of data in the set of field data is significantly less than the number of data in the set of training data. Finally, the set of field object classifications and the set of field data are fed into the training algorithm to generate a second object classification model. The second object classification model can be utilized for predicting object classifications.

Claims

1. A method for generating object classification models, said method comprising:

generating a first object classification model by using a set of training data;

applying a set of field data to said first object classification model to produce a set of field object classifications; and

generating a second object classification model by using said set of field data and said set of field object classifications.

2. The method of claim 1, wherein number of records in said set of field data is less than number of records in said set of training data.

3. The method of claim 1, wherein said generating a first object classification model further includes generating a first object classification model via a training algorithm.

4. The method of claim 3, wherein said generating a second object classification model further includes generating a second object classification model via said training algorithm.

5. A system for generating object classification models, said system comprising:

means for generating a first object classification model by using a set of training data;

means for applying a set of field data to said first object classification model to produce a set of field object classifications; and

means for generating a second object classification model by using said set of field data and said set of field object classifications.

6. The system of claim 5, wherein number of records in said set of field data is less than number of records in said set of training data.

7. The system of claim 5, wherein said means for generating a first object classification model further includes means for generating a first object classification model via a training algorithm.

8. The system of claim 7, wherein said means for generating a second object classification model further includes means for generating a second object classification model via said training algorithm.

9. A computer program product residing on a computer usable medium for generating object classification models, said computer program product comprising:

program code means for generating a first object classification model by using a set of training data;

program code means for applying a set of field data to said first object classification model to produce a set of field object classifications; and

program code means for generating a second object classification model by using said set of field data and said set of field object classifications.

10. The computer program product of claim 9, wherein said set of field data is less than said set of training data.

11. The computer program product of claim 9, wherein said program code means for generating a first object classification model further includes program code means for generating a first object classification model via a training algorithm.

12. The computer program product of claim 11, wherein said program code means for generating a second object classification model further includes program code means for generating a second object classification model via said training algorithm.