Method for performing and visualizing analytics operations over data using augmented reality

1. A method of operating an augmented reality system, the method comprising:

receiving, by a processor, a video stream from a video capture sensor;

determining, by the processor, a plurality of structured data elements in one or more frames of the video stream by (i) detecting, by the processor, a table schema in the one or more frames of the video stream and (ii) extracting, by the processor, elements in a query space data representation of the table schema;

presenting, by the processor, via a graphical user interface, a first visual output corresponding to the video stream and a second visual output having a plurality of augmented data elements associated with the determined plurality of structured data elements, wherein the second visual output includes the extracted elements in a corresponding presentation model;

receiving, by the processor, a gesture input on an element of the query space data representation of the table schema; and

performing, by the processor, a query in the query space data representation of the received gesture.

2. The method of claim 1 , wherein the query is selected from the group consisting of a grouping command, an exclude command, an append row command, an associate command, an append and aggregate command, and a sorting command.

3. The method of claim 1 , wherein the step of determining the plurality of structured data elements in the frame further comprises:

detecting, by the processor, data elements in the one or more frames;

segmenting, by the processor, the data elements from the frame; and

performing, by the processor, optical character recognition operation of the segmented data elements to generate a plurality of arrayed text data.

4. The method of claim 3 , wherein the step of detecting data elements in the one or more frames comprises:

detecting at least one of parallel lines, straight lines, and co-aligned text groups in a frame of the one or more frames.

5. The method of claim 1 , further comprising:

determining, by the processor, a first set of structured data elements and a second set of structured data elements in one or more frames of the video stream, wherein the first set of structured data elements correspond to an attribute type, and wherein the second set of structured data elements correspond to a data type;

receiving, by processor, via the graphical user interface, a first gesture query input corresponding to a first augmented data element of the plurality of augmented data elements, wherein the first augmented data element is associated with the first set of structured data elements corresponding to the attribute type;

determining, by the processor, one or more structured data elements of the second set of structured data elements associated with the first augmented data element;

rendering the one or more structured data elements of the second set of structured data elements as an augmented object associated with the first augmented data element; and

presenting, by the processor, via the graphical user interface, the rendered augmented object of the one or more structured data elements of the second set of structured data elements.

6. The method of claim 5 , further comprising:

generating, by the processor, a result of a mathematical operator performed on values derived from the one or more structured data elements of the second set of structured data elements; and

presenting, by the processor, via the graphical user interface, the result of the mathematical operator.

7. The method of claim 6 , further comprising:

generating, by the processor, a second result of a second mathematical operator performed on second set of values derived from the one or more structured data elements of a second group of structured data elements; and

co-presenting, by the processor, via the graphical user interface, the second result of the second mathematical operator next to the result of the mathematical operator.

8. The method of claim 7 , wherein the result of the mathematical operator is rendered with a first color value and the second result of the second mathematical operator is rendered with a second color value.

9. The method of claim 6 , wherein the mathematical operator is selected from group consisting of a maximum operator, a minimum operator, an average (mean) operator, and a mode operator.

10. The method of claim 1 , further comprising:

finding, by the processor, contours of table cells in the one or more frames;

sub-selecting, by the processor, a plurality of corner elements of the table cells using an optical flow tracking operation; and

updating, by the processor, rendered augmented object of the one or more structured data elements based on a grounding space derived from the optical flow tracking operation.

11. The method of claim 10 , wherein the optical flow tracking operation is performed using the Lucas-Kanade method.

12. The method of claim 1 , further comprising:

determining, by the processor, a first set of structured data elements according to a data model;

parameterizing, by the processor, the first set of structured data elements to a pre-defined encoding space, wherein the parameterized first set of structured data elements are presented via a pre-defined presentation model.

13. The method of claim 12 , wherein the parameterized first set of structured data elements are presented via a pre-defined presentation model by encoding the parameterized first set of structured data elements to a pre-defined grounding space, wherein the encoding space is independent of the grounding space.

14. The method of claim 1 , further comprising:

evaluating, by the processor, a plurality of interactive visual querying grammar; and

executing, by the processor, an associated operator corresponding to a determined interactive visual querying grammar.

15. The method of claim 1 , further comprising:

tracking, by the processor, the extracted elements in the query space data representation.

16. The method of claim 1 , wherein the plurality of augmented data elements of the second visual output are presented as augmented highlights selected from the group consisting of occlusion masks, colors, and text annotations.

17. The method of claim 1 , wherein the processor and the video capture sensor are part of a smart phone, a tablet, or a wearable headset.

18. A system comprising:

a video capture sensor;

a display;

a processor; and

a memory having instructions stored thereon, wherein execution of the instructions cause the processor to:

receive a video stream from the video capture sensor;

determine a plurality of structured data elements in one or more frames of the video stream by (i) detecting a table schema in the one or more frames of the video stream and (ii) extracting elements in a query space data representation of the table schema;

present, via a graphical user interface, on the display, a first visual output corresponding to the video stream and a second visual output having a plurality of augmented data elements associated with the determined plurality of structured data elements, wherein the second visual output includes the extracted elements in a corresponding presentation model;

receive a gesture input on an element of the query space data representation of the table schema; and

perform a query in the query space data representation of the received gesture.

19. A non-transitory computer readable medium comprising having instructions stored thereon, wherein execution of the instructions by a processor of a computing system cause the processor to:

receive a video stream from a video capture sensor of the computing system;

determine a plurality of structured data elements in one or more frames of the video stream by (i) detecting a table schema in the one or more frames of the video stream and (ii) extracting elements in a query space data representation of the table schema;

present, via a graphical user interface, on a display of the computing system, a first visual output corresponding to the video stream and a second visual output having a plurality of augmented data elements associated with the determined plurality of structured data elements;

receive a gesture input on an element of the query space data representation of the table schema; and

perform a query in the query space data representation of the received gesture.