Methods, devices, and systems for unobtrusive mobile device user recognition

1. A method for unobtrusively recognizing a user of a mobile device, the method comprising the steps of:

(a) unobtrusively and continuously collecting a stream of motion data from the mobile device during normal device usage by monitoring standard authorized-user interaction with the device, without any form of challenge or device-specified action;

(b) determining a plurality of motion-states from said stream of motion data, wherein a motion-state refers to a placement and a speed of the mobile device at a point in time;

(c) demarcating said stream of said motion data into user motion-sequences based on changes in said plurality of motion-states;

(d) calculating a plurality of user motion-characteristics from said user motion-sequences locally within the mobile device;

(e) generating a motion-repertoire from a subset of said plurality of said user motion-characteristics, whereby said motion-repertoire enables unobtrusive recognition of the user; and

(f) detecting unidentified motion-sequences having motion-characteristics that are not associated with said motion-repertoire, thereby enabling unobtrusive recognition of unidentified usage.

2. The method of claim 1 , the method further comprising the step of:

(g) upon said step of detecting, triggering a defensive action and/or providing authentication services, wherein said defensive action includes at least one action selected from the group consisting of: blocking access to the device, blocking access to selected applications, deleting sensitive data, encrypting sensitive data, setting off a siren, sending a notification to a designated individual associated with the device, and wherein said authentication services include at least one service selected from the group consisting of: privacy protection, authentication to an external system, use as a universal key, authorizing a payment, and identifying friendly forces in a battle-field environment.

3. The method of claim 1 , wherein said step of detecting is performed repeatedly, during said normal device usage, thereby providing perpetual protection of the device from unauthorized usage.

4. The method of claim 1 , wherein said motion data is obtained from at least one sensor selected from the group consisting of: a motion sensor, a haptic sensor, an accelerometer, a gyroscope, a touch sensor, and a combination thereof.

5. The method of claim 1 , wherein said steps of collecting, determining, demarcating, calculating, and generating are performed repeatedly during said standard authorized-user interaction, thereby providing ongoing improvement to recognition accuracy.

6. The method of claim 5 ,

wherein said step of detecting is initiated based on a learning-stage parameter, as a degree of user recognition, indicating whether a threshold value has been reached in said motion-repertoire in order to initiate said step of detecting, and wherein said threshold value is based on at least one measurement selected from the group consisting of: automatically basing said learning-stage parameter on a quantity of said motion-sequences collected, time elapsed, or a statistical variation of said motion data collected, and manually setting said learning-stage parameter by the user.

7. The method of claim 6 , wherein said learning-stage parameter is operative to regulate a trigger for a defensive action and/or providing authentication services upon detecting unidentified motion-characteristics that are not associated with said motion-repertoire.

8. The method of claim 1 , wherein said step of collecting is performed at a frequency based on said motion-state.

9. The method of claim 1 , wherein said motion-state is determined by:

(i) comparing at least one current motion-sensor value to at least one prior motion-sensor value; and

(ii) assessing a degree of change in said motion-sensor values based on an Absolute Total Acceleration Change (ATAC).

10. The method of claim 1 , wherein said placement has at least one designation selected from the group consisting of: a hand-held state, an on-body state, a pocket state, a flat rest-state, and a non-flat rest-state; and wherein said speed has at least one designation selected from the group consisting of: a traveling state at or above a delimited speed, a walking state, a running state, a hand-moving state, a stable state, and a motionless state.

11. The method of claim 1 , the method further comprising the steps of:

(g) discretizing said motion-characteristics into discrete values; and

(h) selectively increasing the number of said discrete values, thereby dynamically controlling recognition accuracy.

12. A device for unobtrusively recognizing a mobile-device user, the device comprising:

(a) a processing module including:

(i) a CPU for performing computational operations;

(ii) a memory module for storing data; and

(iii) at least one sensor for detecting interaction with the device; and

(b) a recognition module, operationally connected to said processing module, configured for:

(i) unobtrusively and continuously collecting a stream of motion data from the mobile device during normal device usage by monitoring standard authorized-user interaction with the device, without any form of challenge or device-specified action;

(ii) determining a plurality of motion-states from said stream of motion data, wherein a motion-state refers to a placement and a speed of the mobile device at a point in time;

(iii) demarcating said stream of said motion data into user motion-sequences based on changes in said plurality of motion-states;

(iv) calculating a plurality of user motion-characteristics from said user motion-sequences locally within the mobile device;

(v) generating a motion-repertoire from a subset of said plurality of said user motion-characteristics, whereby said motion-repertoire enables unobtrusive recognition of the user; and

(vi) detecting unidentified motion-sequences having motion-characteristics that are not associated with said motion-repertoire, thereby enabling unobtrusive recognition of unidentified usage.

13. A non-transitory computer-readable medium, having computer-readable code embodied on the non-transitory computer-readable medium, the computer-readable code comprising:

(a) program code for unobtrusively and continuously collecting a stream of motion data from the mobile device during normal device usage by monitoring standard authorized-user interaction with the device, without any form of challenge or device-specified action;

(b) program code for determining a plurality of motion-states from said stream of motion data, wherein a motion-state refers to a placement and a speed of the mobile device at a point in time;

(c) program code for demarcating said stream of said motion data into user motion-sequences based on changes in said plurality of motion-states;

(d) program code for calculating a plurality of user motion-characteristics from said user motion-sequences locally within the mobile device;

(e) program code for generating a motion-repertoire from a subset of said plurality of said user motion-characteristics, whereby said motion-repertoire enables unobtrusive recognition of the user; and

(f) program code for detecting unidentified motion-sequences having motion-characteristics that are not associated with said motion-repertoire, thereby enabling unobtrusive recognition of unidentified usage.

14. A method for unobtrusively recognizing a mobile-device user, the method comprising the steps of:

(a) utilizing a plurality of population motion-sequences demarcated from a stream of motion data of a plurality of users of mobile devices;

(b) calculating population motion-characteristics from said plurality of population motion-sequences;

(c) comparing an occurrence frequency of each user motion-characteristic in a user motion-repertoire of a subset of a plurality of user motion-sequences to an occurrence frequency of a respective population motion-characteristic in said plurality of said population motion-sequences;

(d) calculating a respective probability indicator representing a likelihood that a respective user motion-characteristic is associated with a respective user motion-sequence of a particular user;

(e) generating a differentiation-template for each said user having a plurality of said respective probability indicators for each said user motion-sequence;

(f) detecting motion-sequences having motion-characteristics that conform with said differentiation-template; and

(g) continuously calculating a probability authorized-use indicator representing a likelihood that a given motion-sequence is associated with an authorized user of the mobile device, thereby enabling unobtrusive recognition of unidentified usage.

15. A system for unobtrusively recognizing a mobile-device user, the system comprising:

(a) a server including:

(i) a CPU for performing computational operations;

(ii) a memory module for storing data; and

(b) a processing module configured for:

(i) utilizing a plurality of population motion-sequences demarcated from a stream of motion data of a plurality of users of mobile devices;

(ii) calculating population motion-characteristics from said plurality of population motion-sequences;

(iii) comparing an occurrence frequency of each user motion-characteristic in a user motion-repertoire of a subset of a plurality of user motion-sequences to an occurrence frequency of a respective population motion-characteristic in said plurality of said population motion-sequences;

(iv) calculating a respective probability indicator representing a likelihood that a respective user motion-characteristic is associated with a respective user motion-sequence of a particular user;

(v) generating a differentiation-template for each said user having a plurality of said respective probability indicators for each said user motion-sequence;

(vi) detecting motion-sequences having motion-characteristics that conform with said differentiation-template; and

(vii) continuously calculating a probability authorized-use indicator representing a likelihood that a given motion-sequence is associated with an authorized user of the mobile device, thereby enabling unobtrusive recognition of unidentified usage.

16. A non-transitory computer-readable medium, having computer-readable code embodied on the non-transitory computer-readable medium, the computer-readable code comprising:

(a) program code for utilizing a plurality of population motion-sequences demarcated from a stream of motion data of a plurality of users of mobile devices;

(b) program code for calculating population motion-characteristics from said plurality of population motion-sequences;

(c) program code for comparing an occurrence frequency of each user motion-characteristic in a user motion-repertoire of a subset of a plurality of user motion-sequences to an occurrence frequency of a respective population motion-characteristic in said plurality of said population motion-sequences;

(d) program code for calculating a respective probability indicator representing a likelihood that a respective user motion-characteristic is associated with a respective user motion-sequence of a particular user;

(e) program code for generating a differentiation-template for each said user having a plurality of said respective probability indicators for each said user motion-sequence;

(f) program code for detecting motion-sequences having motion-characteristics that conform with said differentiation-template; and

(g) program code for continuously calculating a probability authorized-use indicator representing a likelihood that a given motion-sequence is associated with an authorized user of the mobile device, thereby enabling unobtrusive recognition of unidentified usage.

17. The method of claim 1 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.

18. The device of claim 12 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.

19. The computer-readable medium of claim 13 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.

20. The method of claim 14 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.

21. The system of claim 15 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.

22. The computer-readable medium of claim 16 , wherein said stream includes data collected from at least one sensor selected from the group consisting of: an accelerometer sensor and a touch sensor.