Automatic recognition and insights of data

1. A method executed on a computing device for automatic recognition and insight derivation on data, the method comprising:

receiving underlying data;

inferring user data sets within the underlying data;

analyzing the user data sets;

determining one or more insights on the user data sets based on analysis results, the one or more insights including one or more of a trend, a correlation, an outlier, a pattern, and a comparison for each data set or combinations of data sets;

presenting a visualization of one or more user data sets highlighting an insight associated with each data set from the one or more insights, an emphasis on presented raw underlying data, and a data formatting suggestion, wherein the visualization is a chart highlighting the insight, the emphasis on the presented raw underlying data is one of a shading and a highlighting of a portion of the raw underlying data, and the data formatting suggestion is one or more suggested presentations of the underlying data; and

presenting the one or more insights.

2. The method of claim 1 , wherein the underlying data is in tabular format and inferring the user data sets comprises:

identifying combinations of rows and columns within the underlying data that are of interest to a user.

3. The method of claim 2 , further comprising:

identifying the combinations of rows and columns based on one or more of a type of the underlying data, a context of data processing, a structure of the underlying data, a usage history of the user, and a credential of the user.

4. The method of claim 1 , wherein analyzing the user data sets comprises:

performing one or more of statistical, transformational, heuristic analyses on the user data sets to determine the one or more insight.

5. The method of claim 1 , further comprising:

creating a background by one of converting a tabular presentation of the underlying data to a three dimensional background image, selecting an image associated with the underlying, data, and selecting a graphic associated with the underlying data;

placing the visualization over the background such that a correlation between the underlying data and the visualized insight is presented.

6. The method of claim 5 , further comprising:

displaying a miniaturized graphic representation of the background and the visualization for selection of visualizations of insights associated with multiple user data sets.

7. The method of claim 1 , further comprising one or more of:

generating multiple visualizations for a single data set, each visualization highlighting a different insight; and

generating different visualizations for multiple data sets associated with the user within a spreadsheet.

8. The method of claim 1 , further comprising:

displaying one or more textual and graphical highlights on the visualization emphasizing selected data points.

9. A computing device configured to provide automatic recognition and insight derivation on data, the computing device comprising:

a memory;

a display device; and

a processor coupled to the memory and the display device, the processor adapted to execute a data processing application in conjunction with instructions stored in the memory, wherein the data processing application is configured to:

receive underlying data;

infer user data sets within the underlying data based on one or more of a type of the underlying data, a context of data processing, a structure of the underlying data, a usage history of the user, and a credential of the user;

analyze the user data sets through one or more of statistical, transformational, heuristic analyses on the user data sets;

determine one or more insights on the user data sets based on analysis results, the one or more insights including one or more of a trend, a correlation, an outlier, a pattern, and a comparison for each data set or combinations of data sets;

present a visualization of one or more user data sets highlighting an insight associated with each data set from the one or more insights, an emphasis on presented raw underlying data, and a data formatting suggestion, wherein the visualization is a chart highlighting the insight, the emphasis on the presented raw underlying data is one of a shading and a highlighting of a portion of the raw underlying data, and the data formatting suggestion is one or more suggested presentations of the underlying data.

10. The computing device of claim 9 , herein the data processing application is further configured to:

initiate the automatic recognition and presentation of the insights automatically upon loading of the underlying data to the data processing application or detecting activation of a control element.

11. The computing device of claim 9 , wherein the data processing application is further configured to:

enable the user to further explore the underlying data and the presented insights by selecting available choices to adjust a visualization configuration, switching to the underlying data, and trying alternative scenarios based on the presented insights based on one or more of predefined parameters, user selectable parameters, and automatically configurable parameters.

12. The computing device of claim 11 , wherein the visualization configuration includes one or more of a color scheme, a border style scheme, a relative size, a placement, a perspective, and the data processing application is further configured to:

present the available choices through one or more of a dropdown menu, a radial menu, a pop-up menu, and a direct action on the visualization based on touch or gesture input.

13. The computing device of claim 11 , wherein the data processing application is further configured to:

detect user actions following presentation of the one or more insights; and

employ a machine learning algorithm to adjust future determination and presentation of insights based on the detected user actions.

14. The computing device of claim 9 , wherein the data processing application is one of a spreadsheet application, a database application, a presentation application, a note taking application, and a word processing application.

15. A computer-readable memory device with instructions stored thereon for providing automatic recognition and insight derivation on data, the instructions comprising:

receiving underlying data in a spreadsheet;

inferring user data sets within the spreadsheet based on one or more of a type of the underlying data, a context of data processing, a structure of the underlying data, a usage history of the user, and a credential of the user;

analyzing the user data sets through one or more of statistical, transformational, heuristic analyses on the user data sets;

determining one or more insights on the user data sets based on analysis results, wherein the insights including one or more of a trend, a correlation, an outlier, a pattern, and a comparison for each data set or combinations of data sets;

presenting a visualization of one or more user data sets highlighting an insight associated with each data set from the one or more insights, an emphasis on presented raw underlying data, and a data formatting suggestion; and

presenting the insights as one or more visualizations over a correlated background by:

creating a background by one of converting a tabular presentation of the underlying data to a three dimensional background image, selecting an image associated with the underlying data, and selecting a graphic associated with the underlying data;

placing the visualization over the background such that a correlation between the underlying data and the visualized insight is presented.

16. The computer-readable memory device of claim 15 , wherein the instructions further comprise:

displaying suggested charts highlighting discovered insights as pages under each analyzed sheet of the spreadsheet that includes multiple sheets of underlying data.

17. The computer-readable memory device of claim 15 , wherein the insights further include one or more of overall statistics about the underlying data, a number of dimensions associated with the user data sets, a number of incomplete rows within the user data sets, a percentage of useless data within the user data sets, a number of selected data types and values within the underlying data, a concentration of data inside one or more entities within the underlying data, a growth trend, and extreme values.