Intelligent prevention of unintended mobile touch screen interaction

1. A method of detecting unintentional touch screen interaction, the method comprising:

receiving touch data specifying information about a plurality of inputs on a touch screen, wherein the touch screen comprises a graphical user interface (GUI) comprising a first plurality of logical user interface (UI) elements;

determining that the plurality of inputs was unintentional, based on a second plurality of logical UI elements that the plurality of inputs touch, comprising determining that a ratio between a number of touches on invalid UI elements and a number of touches on valid UI elements exceeds a predefined ratio threshold, wherein valid UI elements are UI elements that are configured to respond to input from a user, and invalid UI elements are UI elements that are not configured to respond to input from the user; and

prompting the user to verify that the plurality of inputs is intentional.

2. The method of claim 1 , wherein the touch data comprises a coordinate of an associated input, a timestamp of when the associated input occurred, and a logical UI element that the associated input touched, wherein the logical UI element that the associated input touched is determined based on the coordinate of the associated input and a coordinate of the logical UI element.

3. The method of claim 2 , wherein the predefined ratio threshold is set by the user.

4. The method of claim 2 , wherein a probabilistic automaton is used to determine that the plurality of inputs was unintentional.

5. The method of claim 4 , wherein the probabilistic automaton is a Markov chain.

6. The method of claim 2 , wherein a support vector machine is used to determine that the plurality of inputs was unintentional.

7. The method of claim 2 , wherein machine learning is used to create a plausibility model to determine that the plurality of inputs was unintentional.

8. The method of claim 7 , wherein the plausibility model is unique to a specific program application.

9. The method of claim 7 , wherein the plausibility model is applicable to any program.

10. The method of claim 1 , wherein the touch data comprises a plurality of tuples.

11. A system, comprising:

one or more computer processors; and

a memory containing computer program code that, when executed by operation of the one or more computer processors, performs an operation comprising:

receiving touch data specifying information about a plurality of inputs on a touch screen, wherein the touch screen comprises a graphical user interface (GUI) comprising a first plurality of logical user interface (UI) elements;

determining that the plurality of inputs was unintentional, based on a second plurality of logical UI elements that the plurality of inputs touch, comprising determining that a ratio between a number of touches on invalid UI elements and a number of touches on valid UI elements exceeds a predefined ratio threshold, wherein valid UI elements are UI elements that are configured to respond to input from a user, and invalid UI elements are UI elements that are not configured to respond to input from the user; and

prompting the user to verify that the plurality of inputs is intentional.

12. The system of claim 11 , wherein the touch data comprises a coordinate of an associated input, a timestamp of when the associated input occurred, and a logical UI element that the associated input touched, wherein the logical UI element that the associated input touched is determined based on the coordinate of the associated input and a coordinate of the logical UI element.

13. The system of claim 12 , wherein a probabilistic automaton is used to determine that the plurality of inputs was unintentional.

14. The system of claim 12 , wherein machine learning is used to create a plausibility model to determine that the plurality of inputs was unintentional.

15. A computer program product for resource pooling, the computer program product comprising:

a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation comprising:

receiving touch data specifying information about a plurality of inputs on a touch screen, wherein the touch screen comprises a graphical user interface (GUI) comprising a first plurality of logical user interface (UI) elements;

determining that the plurality of inputs was unintentional, based on a second plurality of logical UI elements that the plurality of inputs touch, comprising determining that a ratio between a number of touches on invalid UI elements and a number of touches on valid UI elements exceeds a predefined ratio threshold, wherein valid UI elements are UI elements that are configured to respond to input from a user, and invalid UI elements are UI elements that are not configured to respond to input from the user; and

prompting the user to verify that the plurality of inputs is intentional.

16. The computer program product of claim 15 , wherein the touch data comprises a coordinate of an associated input, a timestamp of when the associated input occurred, and a logical UI element that the associated input touched, wherein the logical UI element that the associated input touched is determined based on the coordinate of the associated input and a coordinate of the logical UI element.

17. The computer program product of claim 16 , wherein machine learning is used to create a plausibility model to determine that the plurality of inputs was unintentional.