Virtual keyboard based on adaptive language model

1. A method comprising:

determining, by one or more processors, a level of focus of a user when providing a hand motion with respect to a virtual keyboard, using data from at least one sensor including an image sensor communicably coupled to the one or more processors, the data indicative of a gaze or face direction of the user relative to a position of the virtual keyboard, wherein determining the level of focus of the user when providing the hand motion includes determining, by the one or more processors, a speed of the hand motion using the data acquired by the image sensor;

detecting, by the one or more processors via the image sensor, an input to the virtual keyboard based on the hand motion;

determining, by the one or more processors, weight of a language model according to the data indicative of the gaze or face direction of the user relative to the position of the virtual keyboard; and

modifying, by the one or more processors, the detected input according to the determined weight of the language model.

2. The method of claim 1 , wherein determining the level of focus of the user when providing the hand motion includes:

determining, by the one or more processors, an orientation of a head of the user.

3. The method of claim 2 , wherein determining the weight of the language model includes:

determining, by the one or more processors, the weight to be a first value, in response to determining that the head is oriented to face towards the virtual keyboard, and determining, by the one or more processors, the weight to be a second value, in response to determining that the head is oriented to face away from the virtual keyboard, the second value higher than the first value.

4. The method of claim 1 , wherein determining the level of focus of the user when providing the hand motion includes:

determining, by the one or more processors, the gaze direction of the user.

5. The method of claim 4 , wherein determining the weight of the language model includes:

determining, by the one or more processors, the weight to be a first value, in response to determining that the gaze direction of the user is directed to the virtual keyboard, and

determining, by the one or more processors, the weight to be a second value, in response to determining that the gaze direction of the user is away from the virtual keyboard, the second value higher than the first value.

6. The method of claim 1 , wherein determining the weight of the language model includes:

determining, by the one or more processors, the weight to be a first value, in response to determining that the speed of the hand motion is less than a predetermined threshold, and

determining, by the one or more processors, the weight to be a second value, in response to determining that the speed of the hand motion is higher than the predetermined threshold, the second value higher than the first value.

7. The method of claim 1 , further comprising:

determining, by the one or more processors, a type of content corresponding to the input,

wherein the weight of the language model is determined according to the determined type of content.

8. The method of claim 1 , wherein modifying, by the one or more processors, the detected input according to the determined weight of the language model includes:

determining, by the one or more processors, a distribution of first characters in the detected input during a time period,

predicting, by the one or more processors via the language model according to the determined weight and the distribution of the first characters, semantically meaningful characters, one or more characters in the semantically meaningful characters different from one or more corresponding characters in the first characters, and

replacing the one or more corresponding characters with the one or more characters.

9. A device comprising:

at least one processor configured to:

determine a level of focus of a user when providing a hand motion with respect to a virtual keyboard, using data from at least one sensor including an image sensor communicably coupled to the at least one processor, the data indicative of a gaze or face direction of the user relative to a position of the virtual keyboard, wherein the at least processor is configured to determine the level of focus of the user when providing the hand motion by determining a speed of the hand motion using the data acquired by the image sensor,

detect, via the image sensor, an input to the virtual keyboard based on the hand motion,

determine weight of a language model according to the data indicative of the gaze or face direction of the user relative to the position of the virtual keyboard, and

modify the detected input according to the determined weight of the language model.

10. The device of claim 9 , wherein the at least one processor is configured to determine the level of focus of the user when providing the hand motion by determining an orientation of a head of the user.

11. The device of claim 9 , wherein the at least one processor is configured to determine the level of focus of the user when providing the hand motion by determining the gaze direction of the user.

12. The device of claim 9 , wherein the at least one processor is configured to determine a type of content corresponding to the input, wherein the at least one processor is configured to determine the weight of the language model according to the determined type of content.

13. The device of claim 9 , wherein the at least one processor is configured to modify the detected input according to the determined weight of the language model by:

determining a distribution of first characters in the detected input during a time period,

predicting, via the language model according to the determined weight and the distribution of the first characters, semantically meaningful characters, one or more characters in the semantically meaningful characters different from one or more corresponding characters in the first characters, and

replacing the one or more corresponding characters with the one or more characters.

14. A non-transitory computer readable medium storing instructions when executed by at least one processor cause the at least one processor to:

determine a level of focus of a user when providing a hand motion with respect to a virtual keyboard, using data from at least one sensor including an image sensor communicably coupled to the at least one processor, the data indicative of a gaze or face direction of the user relative to a position of the virtual keyboard, wherein the at least one processor is configured to determine the level of focus of the user when providing the hand motion by determining a speed of the hand motion using the data acquired by the image sensor;

detect, via the image sensor, an input to the virtual keyboard based on the hand motion;

determine weight of a language model according to the data indicative of the gaze or face direction of the user relative to the position of the virtual keyboard; and

modify the detected input according to the determined weight of the language model.

15. The non-transitory computer readable medium of claim 14 , wherein the instructions when executed by the at least one processor cause the at least one processor to determine the level of focus of the user when providing the hand motion by determining an orientation of a head of the user.

16. The non-transitory computer readable medium of claim 14 , wherein the instructions when executed by the at least one processor cause the at least one processor to determine the level of focus of the user when providing the hand motion by determining the gaze direction of the user.

17. The non-transitory computer readable medium of claim 14 , wherein the instructions when executed by the at least one processor cause the at least one processor to:

determine a type of content corresponding to the input, and

determine the weight of the language model according to the determined type of content.