Systems and methods for privacy-preserving summarization of digital activity

1. A method for privacy-preserving summarization of digital activity, comprising:

in an information processing apparatus comprising at least one computer processor and at least one display, a privacy-preserving digital activity computer program performing the following:

capturing a screenshot of the at least one display;

blurring the screenshot using an image-scaling algorithm;

labeling a plurality of computer applications visible in the blurred screenshot using a neural network;

identifying a foreground or actively-used application out of the plurality of computer applications in the blurred screenshot based on at least one of a color layout of each of the plurality of computer applications and a positioning of each of a plurality of windows for the plurality of computer applications relative to each other; and

logging the visible computer applications and the foreground or actively-used application in a log file.

2. The method of claim 1 , wherein the plurality of computer applications are further identified using graphical features, spatial patterns, and layout identification landmarks.

3. The method of claim 1 , wherein the foreground or actively-used application is identified based on user feedback.

4. The method of claim 1 , wherein the foreground or actively-used application is further identified based on the color layout of the foreground or actively-used application.

5. The method of claim 1 , wherein the foreground or actively-used application is further identified based on a mouse cursor location or a pixelated area relative to another visible computer application.

6. The method of claim 1 , wherein the foreground or actively-used application is further identified by identifying a center of attention and gaze duration for a user.

7. The method of claim 1 , further comprising:

logging a time that the visible computer applications and foreground or actively-used application are used.

8. The method of claim 1 , wherein the image-scaling algorithm resizes the screenshot to a fraction of its original resolution.

9. The method of claim 8 , wherein the image-scaling algorithm is selected from the group consisting of Nearest-neighbor interpolation, Bilinear and Bicubic algorithms, Sinc and Lanczos resampling, Fourier-transform methods, Convolutional Neural Networks, and combinations thereof.

10. A system for privacy-preserving summarization of digital activity, comprising:

a backend executing a logging program; and

an electronic device comprising at least one computer processor and at least one display and executing a privacy-preserving digital activity computer program;

wherein:

the privacy-preserving digital activity computer program captures a screenshot of the at least one display;

the privacy-preserving digital activity computer program blurs the screenshot using an image scaling algorithm;

the privacy-preserving digital activity computer program labels a plurality of computer applications visible in the blurred screenshot using a neural network;

the privacy-preserving digital activity computer program identifies a foreground or actively-used application out of the plurality of computer applications in the blurred screenshot based on at least one of a color layout of each of the plurality of computer applications and a positioning of each of a plurality of windows for the plurality of computer applications relative to each other;

the privacy-preserving digital activity computer program logs the visible computer applications and the foreground or actively-used application in a log; and

the privacy-preserving digital activity computer program communicates the log to the logging program on the backend.

11. The system of claim 10 , wherein the plurality of computer applications are further identified using graphical features, spatial patterns, and layout identification landmarks using image-recognition techniques.

12. The system of claim 10 , wherein the foreground or actively-used application is identified based on user feedback.

13. The system of claim 10 , wherein the foreground or actively-used application is further identified based on the color layout of the foreground or actively-used application.

14. The system of claim 10 , wherein the foreground or actively-used application is further identified based on a mouse cursor location or a pixelated area relative to another visible computer application.

15. The system of claim 10 , further comprising:

eye tracking equipment;

wherein the eye tracking equipment identifies a center of attention and gaze duration for a user, and wherein the foreground or actively-used application is further identified based on the center of attention and gaze duration.

16. The system of claim 10 , wherein the privacy-preserving digital activity computer program logs a time that the visible computer applications and foreground or actively-used application are used.

17. The system of claim 10 , wherein the image-scaling algorithm resizes the screenshot to a fraction of its original resolution.

18. The system of claim 17 , wherein the image-scaling algorithm is selected from the group consisting of Nearest-neighbor interpolation, Bilinear and Bicubic algorithms, Sinc and Lanczos resampling, Fourier-transform methods, Convolutional Neural Networks, and combinations thereof.