Systems and methods for detecting hand usage in keyboard interaction
Systems and methods are provided for detecting when a user uses one or both hands to interact with a device having a physical or virtual keyboard. In one implementation, one-handed typing is determined by analyzing intragroup and intergroup keyflight timing distributions between different groups of clustered keys, each cluster having distinctly different proximal properties. A statistical measure made between the intragroup and intergroup keyflight timing distributions may be performed to determine one-handed or two-handed typing input, which may be used to enhance a user experience by adapting a viewing or input element to an appropriate hand setting. In another implementation, the detection may be used as input to determine a likelihood of suspected coaching fraud for online banking applications. In yet another implementation, the detection of one-handed typing is used as an input to bot detection algorithms to reduce false positives from other modalities.
1. A method, comprising:
dividing a key layout of a keyboard into two or more clusters of keys, each cluster defining a centroid based on physical coordinates of the keys of a corresponding cluster;
receiving intragroup keyflight timing distributions corresponding to key presses within clusters of the two or more clusters;
receiving intergroup keyflight timing distributions corresponding to key presses between clusters of the two or more clusters;
determining, based on the intragroup keyflight timing distributions and the intergroup keyflight timing distributions that the key presses correspond to one-handed typing input responsive to determining that one or more statistical measures of the intergroup keyflight timing distributions is greater than corresponding statistical measures of the intragroup keyflight timing distributions; and
outputting a notification or adapting an input element key layout based on the determining.
2. The method of claim 1 , further comprising determining, based on the intragroup keyflight timing distributions and the intergroup keyflight timing distributions that the key presses correspond to two-handed typing input responsive to determining that one or more statistical measure of the intergroup keyflight timing distributions is less than corresponding statistical measures of the intragroup keyflight timing distributions.
3. The method of claim 1 , wherein the one or more statistical measures comprises a statistical distance between the intragroup keyflight timing distributions A and intergroup keyflight timing distributions B.
4. The method of claim 3 , wherein the one or more statistical measures comprise a statistical distance d, wherein median d=med(A)−med(B).
5. The method of claim 3 , wherein one-handed typing is determined based on med(B)−med(A) being greater than zero.
6. The method of claim 1 , wherein dividing the key layout comprises maximizing a distance between the centroids of the two or more clusters.
7. The method of claim 1 , further comprising determining a likelihood of suspected coaching based on determining the one-handed typing input.
8. The method of claim 1 , further comprising detecting bot-related input based on determining the one-handed typing input.
9. The method of claim 8 , wherein the detecting the bot-related input is utilized to reduce false positives from other determined input modalities.
10. A system, comprising:
a physical or virtual keyboard;
a processor; and
memory in communication with the processor, and storing instructions that, when executed by the processor, cause the processor to:
virtually divide a key layout of the keyboard into two or more clusters of keys, each cluster defining a centroid based on physical coordinates of the keys of a corresponding cluster;
receive intragroup keyflight timing distributions corresponding to key presses within clusters of the two or more clusters;
receive intergroup keyflight timing distributions corresponding to key presses between clusters of the two or more clusters;
determine, based on the intragroup keyflight timing distributions and the intergroup keyflight timing distributions that the key presses correspond to one-handed typing input responsive to determining that one or more statistical measures of the intergroup keyflight timing distributions is greater than corresponding statistical measures of the intragroup keyflight timing distributions; and
output a notification or adapt an input element key layout based on determined one-handed or two-handed typing.
11. The system of claim 10 , wherein the instructions that, when executed by the processor, further cause the processor to determine, based on the intragroup keyflight timing distributions and the intergroup keyflight timing distributions that the key presses correspond to two-handed typing input responsive to determining that one or more statistical measures of the intergroup keyflight timing distributions is less than corresponding statistical measures of the intragroup keyflight timing distributions.
12. The system of claim 10 , wherein the one or more statistical measures comprises a statistical distance between the intragroup keyflight timing distributions A and intergroup keyflight timing distributions B.
13. The system of claim 12 , wherein the one or more statistical measures comprise a statistical distance d, wherein median d=med(A)−med(B).
14. The system of claim 12 , wherein one-handed typing is determined based on med(B)−med(A) the statistical distance d being less greater than zero.
15. The system of claim 10 , wherein dividing the key layout comprises maximizing a distance between the centroids of the two or more clusters.
16. The system of claim 10 , further comprising determining a likelihood of suspected coaching based on determining the one-handed typing input.
17. The system of claim 10 , further comprising detecting bot-related input based on determining the one-handed typing input.
18. The system of claim 17 , wherein the detecting the bot-related input is utilized to reduce false positives from other determined input modalities.
19. A non-transitory computer-readable storage medium storing instructions that are configured to cause one or more processors to perform a method of:
dividing a key layout of a keyboard into two or more clusters of keys, each cluster defining a centroid based on physical coordinates of the keys of a corresponding cluster;
receiving intragroup keyflight timing distributions corresponding to key presses within clusters of the two or more clusters;
receiving intergroup keyflight timing distributions corresponding to key presses between clusters of the two or more clusters;
determining, based on the intragroup keyflight timing distributions and the intergroup keyflight timing distributions that the key presses correspond to one-handed typing input responsive to determining that one or more statistical measures of the intergroup keyflight timing distributions is greater than corresponding statistical measures of the intragroup keyflight timing distributions; and
outputting a notification or adapting an input element key layout based on the determining.
20. The non-transitory computer-readable storage medium of claim 19 ,
wherein the one or more statistical measures comprises a statistical distance between the intragroup keyflight timing distributions A and intergroup keyflight timing distributions B, and wherein one-handed typing is determined based on med(B)−med(A) the statistical distance d being less greater than zero.