Information processing apparatus and control method

1 . An information processing apparatus, comprising:

a time-of-flight (ToF) sensor that obtains a plurality of measured distances by measuring a distance to each of a plurality of points within a field of view of the ToF sensor;

a screen; and

a controller that:

detects a presence of a user within the field of view based on the plurality of measured distances;

in response to detecting the presence of the user within the field of view:

classifies, using an artificial intelligence (AI) model, a posture of the user based on the plurality of measured distances, and

adjusts a brightness of the screen based on the posture of the user;

in response to classifying the posture of the user as an abnormal posture, maintains a brightness of the screen regardless of the posture of the user; and

in response to classifying the posture of the user as a normal posture:

determines an orientation of a face of the user based on the plurality of measured distances, and

adjusts the brightness of the screen based on the orientation of the face of the user.

2 . The information processing apparatus of claim 1 , wherein the ToF sensor repeatedly obtains the plurality of measured distances with a predetermined sampling frequency.

3 . The information processing apparatus of claim 2 , wherein, with the predetermined sampling frequency, the controller:

detects the presence of the user within the field of view of the ToF sensor;

classifies the posture of the user; and

adjusts the brightness of the screen based on the posture of the user.

4 . The information processing apparatus of claim 2 , wherein the controller:

calculates a summary statistic based on the plurality of measured distances obtained with the predetermined sampling frequency, wherein the summary statistic is selected from a group consisting of mean, median, and mode;

detects the presence of the user within the field of view based on the summary statistic; and

in response to detecting the presence of the user within the field of view, classifies the posture of the user based on the summary statistic.

5 . The information processing apparatus of claim 2 , wherein the controller:

calculates a change in one of the plurality of measured distances by applying a linear differential operator to the plurality of measured distances obtained repeatedly with the predetermined sampling frequency, wherein the change indicates motion within the field of view, and

detects the presence of the user within the field of view based on the calculated change.

6 . The information processing apparatus of claim 1 , wherein the AI model is pretrained using training distance measurements corresponding to a plurality of different users interacting with the information processing apparatus in a plurality of predetermined categories of postures.

7 . The information processing apparatus of claim 6 , further comprising a camera that obtains an image of the user, wherein the controller validates the posture of the user based on the image of the user.

8 . A method, comprising:

obtaining, using a time-of-flight (ToF) sensor of an information processing apparatus, a plurality of measured distances by measuring a distance to each of a plurality of points within a field of view of the ToF sensor;

detecting a presence of a user within the field of view of the ToF sensor based on the plurality of measured distances;

in response to detecting the presence of the user within the field of view:

classifying, using an artificial intelligence (AI) model, a posture of the user based on the plurality of measured distances; and

adjusting a brightness of a screen of the information processing apparatus based on the posture of the user;

in response to classifying the posture of the user as an abnormal posture, maintaining a brightness of the screen regardless of the posture of the user; and

in response to classifying the posture of the user as a normal posture:

determining an orientation of a face of the user based on the plurality of measured distances, and

adjusting the brightness of the screen based on the orientation of the face of the user.

9 . The method of claim 8 , further comprising repeatedly obtaining, using the ToF sensor, the plurality of measured distances with a predetermined sampling frequency.

10 . The method of claim 9 , further comprising, with the predetermined sampling frequency:

detecting the presence of the user within the field of view of the ToF sensor;

classifying the posture of the user; and

adjusting the brightness of the screen based on the posture of the user.

11 . The method of claim 9 , further comprising:

calculating a summary statistic based on the plurality of measured distances obtained with the predetermined sampling frequency, wherein the summary statistic is selected from a group consisting of mean, median, and mode;

detecting the presence of the user within the field of view based on the summary statistic; and

in response to detecting the presence of the user within the field of view, classifying the posture of the user based on the summary statistic.

12 . The method of claim 9 , further comprising:

calculating a change in one of the plurality of measured distances by applying a linear differential operator to the plurality of measured distances obtained repeatedly with the predetermined sampling frequency, wherein the change indicates motion within the field of view, and

detecting the presence of the user within the field of view based on the calculated change.

13 . The method of claim 8 , wherein the AI model is pretrained using training distance measurements corresponding to a plurality of different users interacting with the information processing apparatus in a plurality of predetermined categories of postures.

14 . The method of claim 13 , further comprising obtaining an image of the user by a camera of the information processing apparatus and validating the posture of the user based on the image of the user.