Method of supporting self-learning and system for performing the same

1. A method of supporting self-learning, the method comprising:

estimating an object of interest of a user in content based on user performance information inputted by the user in response to content situation information and the content being received from a learning module comprising the content;

analyzing the content situation information;

determining whether to generate support information for supporting the user to perform the content based on the estimated object of interest and the analyzed content situation information; and

generating the support information that allows the user to self-learn the content according to whether to generate the support information, and outputting the support information to the learning module,

wherein the user performance information includes position information and rotation information of a head-mounted display (HMD) worn by the user and a controller while performing the content and information input to the controller, and

wherein the content situation information includes one or more of information about all performance stages included in the content, information about a performance stage currently being performed by the user, information about a time taken to perform the content, and information about properties of one or more objects included in the content.

2. The method of claim 1 , further comprising:

generating an evaluation for the support information based on a response of the user according to the support information and updating the support information based on the evaluation; and

storing the evaluation and the updated support information in a database.

3. The method of claim 1 , wherein the user performance information is received by the learning module from the HMD that does not have an eye tracking function and the controller.

4. The method of claim 3 , wherein the estimating comprises:

selecting, as a collision plane, one of a plurality of finite planes forming the one or more objects comprised in the content from the position information and the rotation information of the HMD and the controller, and position information, rotation information and size information of the one or more objects;

generating a plurality of feature vectors based on center coordinates of the collision plane, a plurality of collision coordinates, positions of the HMD and the controller and center coordinates of the object;

generating an estimation model based on the plurality of feature vectors; and

estimating the object of interest using the estimation model.

5. The method of claim 1 , wherein the selecting comprises:

extracting front vectors of the HMD and the controller;

obtaining a plurality of collision coordinates on a plurality of infinite planes by calculating coordinates at which the front vectors collide on the plurality of infinite planes, the plurality of infinite planes extending from a plurality of finite planes forming an object comprised in the content; and

selecting, as a collision plane, a finite plane having a minimum distance from the plurality of collision coordinates from among the plurality of finite planes.

6. The method of claim 1 , wherein the analyzing comprises

dividing one of one or more performance stages comprised in the content into a plurality of sub-stages; and

defining a main object among the one or more objects for each of the plurality of sub-stages and defining an action to be performed by the user using the main object.

7. The method of claim 6 , wherein the determining of whether to generate the support information comprises:

generating a decision model based on feature data for a first time spent in the performance stage for which the user requests help and feature data for a second time spent in the performance stage for which the user does not request help; and

determining whether to generate the support information using the decision model.

8. The method of claim 6 , wherein the support information comprises:

position clue information to find the main object; and

motion information about an action required for the user to perform the content.

9. A device comprising:

a memory comprising instructions; and

a processor electrically connected to the memory and configured to execute the instructions;

wherein when the instructions are executed by the processor, the processor is configured to:

estimate an object of interest of a user in content based on user performance information inputted by the user in response to content situation information and the content being received from a learning module comprising the content;

analyze the content situation information;

determine whether to generate support information for supporting the user to perform the content based on the estimated object of interest and the analyzed content situation information; and

generate the support information that allows the user to self-learn the content according to whether to generate the support information, and output the support information to the learning module,

wherein the user performance information includes position information and rotation information of a head-mounted display (HMD) worn by the user and a controller while performing the content and information input to the controller, and

wherein the content situation information includes one or more of information about all performance stages included in the content, information about a performance stage currently being performed by the user, information about a time taken to perform the content, and information about properties of one or more objects included in the content.

10. The device of claim 9 , wherein the processor is configured to:

generate an evaluation of the support information based on a response of the user according to the support information and update the support information based on the evaluation; and

store the evaluation and the updated support information in a database.

11. The device of claim 9 , wherein the user performance information is received by the learning module from the HMD that does not have an eye tracking function and the controller.

12. The device of claim 11 , wherein the processor is configured to:

select, as a collision plane, one of a plurality of finite planes forming the one or more objects comprised in the content from the position information and the rotation information of the HMD and the controller, and position information, rotation information and size information of the one or more objects;

generate a plurality of feature vectors based on center coordinates of the collision plane, a plurality of collision coordinates, positions of the HMD and the controller and center coordinates of the object;

generate an estimation model based on the plurality of feature vectors; and

estimate the object of interest using the estimation model.

13. The device of claim 9 , wherein the processor is configured to:

extract front vectors of the HMD and the controller;

obtain a plurality of collision coordinates on a plurality of infinite planes by calculating coordinates at which the front vectors collide on the plurality of infinite planes, the plurality of infinite planes extending from a plurality of finite planes forming an object comprised in the content; and

select, as a collision plane, a finite plane having a minimum distance from the plurality of collision coordinates from among the plurality of finite planes.

14. The device of claim 9 , wherein the processor is configured to:

divide one of one or more performance stages comprised in the content into a plurality of sub-stages; and

define a main object among the one or more objects for each of the plurality of sub-stages and define an action to be performed by the user using the main object.

15. The device of claim 14 , wherein the processor is configured to:

generate a decision model based on feature data for a first time spent in the performance stage for which the user requests help and feature data for a second time spent in the performance stage for which the user does not request help; and

determine whether to generate the support information using the decision model.

16. The device of claim 14 , wherein the support information comprises:

position clue information to find the main object; and

motion information about an action required for the user to perform the content.