System, method and computer program product for stateful instruction-based dynamic man-machine interactions for humanness validation

1. A computer-implemented humanness validation method, the method comprising:

generating a sequence of actions including a combination of gaze actions and emotional state actions including a facial expression and a facial action as a primary input modality;

instructing an access requestor to perform the actions in the sequence one-by-one; and

granting access to the access requestor if a total error rate in each of the performed one-by-one actions in the sequence of actions is less than a predefined threshold value,

wherein the gaze actions and the emotional state actions include changing a current gaze action and a current emotional state action to the sequence of actions including a combination of gaze actions and emotional state actions as a result of receiving the instructing to perform the actions,

further comprising detecting an initial gaze point and an initial emotional state of the access requestor prior to generating the sequence of actions,

wherein a first depth distance is calculated between a fixed point on a device and a first point on the access requestor,

wherein a second depth distance is calculated between the fixed point on the device and a second point on the access requestor, and

wherein access is denied to the access requestor if the first depth distance is within a predetermined amount of the second depth distance.

2. The computer-implemented method of claim 1 , further comprising continuously generating a different sequence of actions to instruct the access requestor to repeat the performance of the actions in the different sequence one-by-one if the total error rate is greater than the predefined threshold value.

3. The computer-implemented method of claim 2 , wherein the granting grants access to the access requestor if the total error rate for each of the performed one-by-one actions in the different sequence of actions is less than the predefined threshold value and a number of the different sequences of actions generated is less than a length constraint.

4. The computer-implemented method of claim 1 ,

wherein the generated sequence of actions includes a gaze action different than the initial gaze point of the access requestor and an emotional state action different than the initial emotional state of the access requestor.

5. The computer-implemented method of claim 1 , wherein the instructing instructs a next action in the sequence of actions to the access requestor after an error rate in a previous action is determined.

6. The computer-implemented method of claim 1 , wherein the instructing instructs each action independently of other actions such that the access requestor performs the actions in the one-by-one sequence to determine an error rate associated with each action, the total error rate being a summation of the error rate associated with each action.

7. The computer-implemented method of claim 1 , wherein the detecting the initial gaze point and the initial emotional state of the access requestor is prior to generating the sequence of actions,

wherein a first depth distance is calculated between a fixed point on a device and a first point on the access requestor,

wherein a second depth distance is calculated between the fixed point on the device and a second point on the access requestor, and

wherein access is denied to the access requestor if the first depth distance is within a predetermined amount of the second depth distance.

8. The computer-implemented method of claim 1 , embodied in a cloud-computing environment.

9. A computer program product for humanness validation, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform:

generating a sequence of actions including a combination of gaze actions and emotional state actions including a facial expression and a facial action as a primary input modality;

instructing an access requestor to perform the actions in the sequence one-by-one; and

granting access to the access requestor if a total error rate of each of the performed one-by-one actions in the sequence of actions is less than a predefined threshold value,

wherein the gaze actions and the emotional state actions include changing a current gaze action and a current emotional state action to the sequence of actions including a combination of gaze actions and emotional state actions as a result of receiving the instructing to perform the actions,

further comprising detecting an initial gaze point and an initial emotional state of the access requestor, wherein a first depth distance is calculated between a fixed point on a device and a first point on the access requestor,

wherein a second depth distance is calculated between the fixed point on the device and a second point on the access requestor, and

wherein access is denied to the access requestor if the first depth distance is within a predetermined amount of the second depth distance.

10. The computer program product of claim 9 , further comprising continuously generating a different sequence of actions to instruct the access requestor to repeat the performance of the actions in the different sequence one-by-one if the total error rate is greater than the predefined threshold value.

11. The computer program product of claim 10 , wherein the granting grants access to the access requestor if the total error rate for each of the performed one-by-one actions in the different sequence of actions is less than the predefined threshold value and a number of the different sequences of actions generated is less than a length constraint.

12. The computer program product of claim 9 ,

wherein the generated sequence of actions includes a gaze action different than the initial gaze point of the access requestor and an emotional state action different than the initial emotional state of the access requestor.

13. The computer program product of claim 9 , wherein the instructing instructs a next action in the sequence of actions to the access requestor after an error rate in a previous action is determined.

14. The computer program product of claim 9 , wherein the instructing instructs each action independently of other actions such that the access requestor performs the actions in the one-by-one sequence to determine an error rate associated with each action, the total error rate being a summation of the error rate associated with each action.

15. The computer program product of claim 9 , wherein the detecting the initial gaze point and the initial emotional state of the access requestor is prior to generating the sequence of actions,

wherein a first depth distance is calculated between a fixed point on a device and a first point on the access requestor,

wherein a second depth distance is calculated between the fixed point on the device and a second point on the access requestor, and

wherein access is denied to the access requestor if the first depth distance is within a predetermined amount of the second depth distance.

16. A humanness validation system, said system comprising:

a processor; and

a memory, the memory storing instructions to cause the processor to perform:

generating a sequence of actions including a combination of gaze actions and emotional state actions including a facial expression and a facial action as a primary input modality;

instructing an access requestor to perform the actions in the sequence one-by-one; and

granting access to the access requestor if a total error rate of each of the performed one-by-one actions in the sequence of actions is less than a predefined threshold value,

wherein the gaze actions and the emotional state actions include changing a current gaze action and a current emotional state action to the sequence of actions including a combination of gaze actions and emotional state actions as a result of receiving the instructing to perform the actions,

further comprising detecting an initial gaze point and an initial emotional state of the access requestor,

wherein a first depth distance is calculated between a fixed point on a device and a first point on the access requestor,

wherein a second depth distance is calculated between the fixed point on the device and a second point on the access requestor, and

wherein access is denied to the access requestor if the first depth distance is within a predetermined amount of the second depth distance.

17. The system of claim 16 , embodied in a cloud-computing environment.