Robot and controlling method thereof

1 . A method of controlling a robot, the method comprising:

detecting occurrence of an event;

identifying an interaction corresponding to the event;

identifying a user context of a user corresponding to the event;

identifying an interaction parameter based on history information stored in the robot, the interaction, and the user context, wherein the interaction parameter is identified by performing regression on at least one interaction parameter or by using a second history among the history information based on a result of comparing a number of at least one first history corresponding to the interaction and the user context with a first threshold value, or based on a result of comparing a score of a response of the user included in the at least one first history corresponding to the interaction and the user context with a second threshold value;

performing the interaction based on the identified interaction parameter;

obtaining information on a user's response according to a result of the performing of the interaction; and

updating the history information based on the information on the identified interaction parameter and the user's response.

2 . The method of claim 1 , wherein the identifying of the interaction parameter comprises, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the first threshold value, identifying the interaction parameter by performing regression on the at least one interaction parameter included in the at least one first history and the score of the response of the user.

3 . The method of claim 1 , wherein the identifying of the interaction parameter comprises, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being less than the first threshold value, identifying the interaction parameter by using at least one interaction parameter included in the second history among the history information.

4 . The method of claim 1 , wherein the identifying of the interaction parameter comprises, based on the score of the response of the user included in the at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the second threshold value, identifying the interaction parameter by performing regression on the at least one interaction parameter included in the at least one first history and the score of the response of the user.

5 . The method of claim 1 , wherein the identifying of the interaction parameter comprises, based on the score of the response of the user included in the at least one first history corresponding to the interaction and the user context among the history information being less than the second threshold value, identifying the interaction parameter by using at least one interaction parameter included in the second history among the history information.

6 . The method of claim 1 , further comprising:

updating history information by removing a duplicate history or incorporating similar histories among a plurality of histories included in the history information.

7 . The method of claim 1 , wherein the identifying of the user context comprises identifying the user context based on information comprising at least one of identification information of the user, location information of the user, pose information of the user, weather information, or stock price information.

8 . The method of claim 1 , wherein the obtaining of information on the user's response comprises, based on user information to obtain information on the user's response being set:

obtaining the user's response based on set user's information; and

converting the obtained user's response into the score of the response of the user.

9 . A robot comprising:

at least one sensor;

a driver;

memory storing one or more computer programs; and

one or more processors operatively coupled with the at least one sensor, the driver, and the memory,

wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the robot to:

detect, through the at least one sensor, occurrence of an event,

identify an interaction corresponding to the event,

identify a user context of a user corresponding to the event,

identify an interaction parameter based on history information stored in the memory, the interaction, and the user context, wherein the interaction parameter is identified by performing regression on at least one interaction parameter or by using a second history among the history information based on a result of comparing a number of at least one first history corresponding to the interaction and the user context with a first threshold value, or based on a result of comparing a score of a response of the user included in the at least one first history corresponding to the interaction and the user context with a second threshold value,

control the driver to perform the interaction based on the identified interaction parameter,

obtain information on a user's response according to a result of the performing of the interaction, and

update the history information based on information on the identified interaction parameter and the user's response.

10 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the first threshold value, identify the interaction parameter by performing regression on the at least one interaction parameter included in the at least one first history and the score of the response of the user.

11 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being less than the first threshold value, identify the interaction parameter by using at least one interaction parameter included in the second history among the history information.

12 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to, based on the score of the response of the user included in the at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the second threshold value, identify the interaction parameter by performing regression on the at least one interaction parameter included in the first history and the score of the response of the user.

13 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to, based on the score of the response of the user included in at least one first history corresponding to the interaction and the user context among the history information being less than the second threshold value, identify the interaction parameter by using at least one interaction parameter included in the second history among the history information.

14 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to update history information by removing a duplicate history or incorporating similar histories among a plurality of histories included in the history information.

15 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to identify the user context based on information comprising at least one of identification information of the user, location information of the user, pose information of the user, weather information, or stock price information.

16 . The robot of claim 9 , wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors, cause the robot to, based on user information to obtain information on the user's response being set:

obtain the user's response based on set user's information, and convert the obtained user's response into the score of the response of the user.

17 . One or more non-transitory computer-readable storage media storing computer-executable instructions that, when executed by one or more processors of a robot individually or collectively, cause the robot to perform operations, the operations comprising:

detecting occurrence of an event;

identifying an interaction corresponding to the event;

identifying a user context of a user corresponding to the event;

identifying an interaction parameter based on history information stored in the robot, the interaction, and the user context, wherein the interaction parameter is identified by performing regression on at least one interaction parameter or by using a second history among the history information based on a result of comparing a number of at least one first history corresponding to the interaction and the user context with a first threshold value, or based on a result of comparing a score of a response of the user included in the at least one first history corresponding to the interaction and the user context with a second threshold value;

performing the interaction based on the identified interaction parameter;

obtaining information on a user's response according to a result of the performing of the interaction; and

updating the history information based on the information on the identified interaction parameter and the user's response.

18 . The one or more non-transitory computer-readable storage media of claim 17 , wherein the identifying of the interaction parameter comprises, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the first threshold value, identifying the interaction parameter by performing regression on the at least one interaction parameter included in the at least one first history and the score of the response of the user.

19 . The one or more non-transitory computer-readable storage media of claim 17 , wherein the identifying of the interaction parameter comprises, based on the number of the at least one first history corresponding to the interaction and the user context among the history information being less than the first threshold value, identifying the interaction parameter by using at least one interaction parameter included in the second history among the history information.

20 . The one or more non-transitory computer-readable storage media of claim 17 , wherein the identifying of the interaction parameter comprises, based on the score of the response of the user included in at least one first history corresponding to the interaction and the user context among the history information being greater than or equal to the second threshold value, identifying the interaction parameter by performing regression on the at least one interaction parameter included in the first history and the score of the response of the user.