Electronic apparatus and operating method thereof for determining session duration time of chatbot

1. A method of determining a session duration time of a chatbot, the method comprising:

outputting a response message regarding an input message of a user;

determining a default session time during which a session is maintained based on a difficulty level of the output response message;

determining an additional session time based on conversation history information through the chatbot prior to outputting of the response message;

waiting for an input of an additional message of the user during a session duration time, which is a sum of the default session time and the additional session time; and determining an end of the session based on whether the additional message is input, and

wherein the determining of the default session time comprises: obtaining a label value of the difficulty level by applying the response message to a deep neural network model as an input; and determining a session time mapped to correspond to the obtained label value as the default session time.

2. The method of claim 1 , wherein the deep neural network model is trained through supervised learning, wherein a plurality of training messages are applied as an input, and wherein the label value of the difficulty level is applied as an output groundtruth.

3. The method of claim 1 , wherein the conversation history information includes information about at least one of a number of previously output response messages in a conversation prior to the outputting of the response message or a session use time in a scenario performed according to the previously output response message.

4. The method of claim 3 , wherein the additional session time is determined by a preset ratio of a sum of the session use time for each scenario.

5. The method of claim 1 , further comprising: storing session usage history information of a plurality of users regarding the output response message; and adjusting the default session time based on the stored session usage history information of the plurality of users.

6. The method of claim 5 , wherein the session usage history information comprises statistical data of the plurality of users regarding at least one of a number of session extension requests at a time point prior to outputting of the response message, a number of scenarios performed prior to the response message, or a session use time used for the response message.

7. An electronic apparatus for determining a session duration time of a chatbot, the electronic apparatus comprising: a communication interface configured to perform transmission and reception of data with other devices; a memory; and a processor configured to execute one or more instructions, wherein the processor is further configured to execute the one or more instructions to: obtain an input message input by a user through the communication interface, output a response message regarding the input message of the user, determine a default session time during which a session is maintained based on a difficulty level of the output response message, determine an additional session time based on a conversation history information through the chatbot prior to outputting of the response message, wait for an input of an additional message by the user during a session duration time, which is a sum of the default session time and the additional session time, and determine an end of the session based on whether the additional message is input, and wherein the processor, to determine the default session time, is further configured to execute the one or more instructions to: obtain an output label value of the difficulty level by applying the response message to a deep neural network model as an input; and determine a session time mapped to correspond to the obtained label value as the default session time.

8. The electronic apparatus of claim 7 , wherein the deep neural network model is trained through supervised learning, wherein a plurality of training messages are applied as an input, and wherein the label value of the difficulty level is applied as an output groundtruth.

9. The electronic apparatus of claim 7 , wherein the conversation history information comprises information about at least one of a number of previously output response messages in a conversation prior to the outputting of the response message or a session use time in a scenario performed according to the previously output response message.

10. The electronic apparatus of claim 9 , wherein the processor is further configured to execute the one or more instructions to determine the additional session time by a preset rate of a sum of the session use time for each scenario.

11. The electronic apparatus of claim 7 , wherein the processor is further configured to execute the one or more instructions to: store, in a database of the memory, a session usage history information of a plurality of users regarding the output response message, and adjust the default session time based on the stored session usage history information of the plurality of users.

12. The electronic apparatus of claim 11 , wherein the session usage history information comprises statistical data of the plurality of users regarding at least one of a number of session extension requests prior to the outputting of the response message, a number of scenarios performed prior to the response message, or a session use time used for the response message.

13. At least one non-transitory computer program product comprising a computer-readable storage medium, wherein the computer-readable storage medium comprises instructions, performed by a device, for: outputting a response message regarding an input message of a user; determining a default session time during which a session is maintained based on a difficulty level of the output response message; determining an additional session time based on a conversation history information through a chatbot prior to outputting of the response message; waiting for an input of an additional message by the user during a session duration time, which is a sum of the default session time and the additional session time; and determining an end of the session based on whether the additional message is input, wherein the determining of the default session time comprises: obtaining a label value of difficulty level by applying the response message to a deep neural network model as an input, and determining, a session time mapped to correspond to the obtained label value as the default session time.