METHODS AND SYSTEMS FOR COMPOUND FEATURE CREATION, PROCESSING, AND IDENTIFICATION IN CONJUNCTION WITH A DATA ANALYSIS AND FEATURE RECOGNITION SYSTEM

• US 20090231359A1
• Filed: 03/17/2009
• Published: 09/17/2009
• Est. Priority Date: 03/17/2008
• Status: Active Grant

• Current Assignee: IntelliScience Corp.
• Original Assignee: IntelliScience Corp.
• Inventors: Brinson, Robert M. JR., Bass II, Robert Leon, Donaldson, Bryan Glenn, Middleton, Nicholas Levi
• Granted Patent: US 8,175,992 B2
• Time in Patent Office: Days
• US Class Current: 345/619
• CPC Class Codes: G06F 18/24765 Rule-based classification
• CPC Class Codes: G06V 10/765 using rules for classification or partitioning the feature space
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

Methods and systems for creation, processing, and use of compound features during data analysis and feature recognition are disclosed herein. In a preferred embodiment, the present invention functions to apply a new level of data discrimination during data analysis and feature recognition events such that features are more easily discerned from the remainder of the data pool using processing techniques that are more conducive to human visualizations, perceptions, and/or interpretations of data. This is accomplished using an example tool that allows previously processed and identified features (hereafter “known features”) to be aggregated so as to aid the system in recognizing abstract data features, preferably using Boolean operators and user-assigned hit weight values across desired cluster ranges surrounding analyzed data elements.

Claims

1. A system for compound feature determination, comprising:

a computer having a processor and a memory, the memory having a database of known features associated with the compound feature;

the memory further containing stored programming instructions operable by the processor to determine whether the compound feature is present for a given data element within a data set, the presence of the compound feature being a function of a Boolean logical operator association between a plurality of known features associated with the compound feature.

2. The system of claim 1, wherein the stored programming instructions further enable the processor to determine the presence of the compound feature as function of the presence of the known features over a cluster distance extending from the data element in one or more directions.

3. The system of claim 2, wherein the cluster distance is independently user-adjustable for each of the one or more directions.

4. The system of claim 2, wherein the cluster distance must extend in one or more predefined directions from the data element in order to determine that the compound feature is present.

5. The system of claim 2, wherein the stored programming instructions further enable the processor to determine the presence of the compound feature as a function of a plurality of hit weight values, each one of the plurality of hit weight values being assigned to a corresponding one of the plurality of known features, wherein the compound feature is determined to be present if the sum of the hit weights is equal to or greater than a user-defined threshold for the Boolean operation.

6. The system of claim 5, wherein each of the plurality of hit weight values is user-adjustable.

7. The system of claim 5, wherein the stored programming instructions further enable the processor to determine the presence of the compound feature as a function of a cluster count value, the cluster count value representing the number of times within the range of cluster values in which the compound feature is determined to be present.

8. The system of claim 7, wherein each of the plurality of hit weight values is user-adjustable.

9. The system of claim 8, wherein the Boolean operators comprise one or more of AND, OR, XOR, and NOT.

10. The system of claim 8, wherein the stored programming instructions further enable to processor to provide a notification to a user when a compound feature is determined to be present.

11. The system of claim 10, wherein the known features within the database are associated with a visual image and the notification to the user comprises presenting a modified representation of the visual image wherein the modified representation includes an indication of the compound feature.

12. The system of claim 1, wherein one or more of the known features associated with the compound feature further comprise one or more additional compound features, whereby the one or more additional compound features are associated with the compound feature.

13. A computer-based method for compound feature determination, comprising:

providing a computer having a processor and a memory, the memory having a database of known features associated with the compound feature and a data set to be analyzed for the presence of the compound feature; and

processing data within a stored data set, via the computer, to determine whether the compound feature is present for a given data element within the data set, the presence of the compound feature being a function of a Boolean logical operator association between a plurality of known features associated with the compound feature.

14. The system of claim 13, wherein the step of processing occurs over a cluster distance extending from the data element.

15. The system of claim 14, wherein the step of processing is performed as a function of a plurality of hit weight values, each one of the plurality of hit weight values being assigned to a corresponding one of the plurality of known features, wherein the compound feature is determined to be present if the sum of the hit weights is equal to or greater than one for the Boolean operation.

16. The system of claim 15, wherein the step of processing is performed as a function of a cluster count value, the cluster count value representing the number of times within the cluster distance in which the compound feature is determined to be present.

17. A system for compound feature determination, comprising:

a computer having a processor and a memory, the memory having a database of known features associated with the compound feature;

the memory further containing stored programming instructions operable by the processor to;

analyze a data element within a data set stored in the memory to determine the presence of a plurality of known features from the database of known features to produce a plurality of known feature results;

compare the plurality of known feature results via a Boolean logical operation; and

determine whether the compound feature is present as a function of the Boolean logical operation.

18. The system of claim 17, wherein the stored programming instructions further enable the processor to perform the steps of analyzing, comparing, and determining repeatedly over a cluster distance extending from the data element.

19. The system of claim 18, wherein the stored programming instructions further enable the processor to apply a plurality of hit weight values to the plurality of known feature results, each one of the plurality of hit weight values being assigned to a corresponding one of the plurality of known features.

20. The system of claim 19, wherein the stored programming instructions further enable the processor to determine the presence of the compound feature as a function of a cluster count value, the cluster count value representing the number of times within the cluster distance in which the compound feature is determined to be present.