Electronic apparatus and control method thereof
The disclosure relates to an artificial intelligence (AI) system using a learned AI model according to at least one of machine learning, neural network, or a deep learning algorithm and applications thereof. In the disclosure, a control method of an electronic apparatus is provided. The control method comprises the steps of: displaying an image including at least one object receiving a voice; inputting the voice to an AI model learned by an AI algorithm to identify an object related to the voice among the at least one object included in the image and acquire tag information about the identified object; and providing the obtained tag information.
1. A control method of an electronic apparatus, the method comprising:
displaying an image including a plurality of objects;
receiving a voice of a user;
obtaining first feature information on the plurality of objects by inputting the image to a first AI model;
obtaining second feature information of the voice by inputting the voice to a second AI model;
comparing the first feature information with the second feature information;
identifying an object whose first feature information matches a portion of the second feature information, from among the plurality of objects in the image, based on the comparison;
generating tag information corresponding to the identified object based on the second feature information; and
providing the tag information for the identified object,
wherein the second feature information comprises personalized information which is reflected with a unique thinking of the user and a feeling of the user.
2. The method of claim 1 , wherein the tag information further comprises information on the identified object among the first feature information.
3. The method of claim 1 , wherein the obtaining the second feature information comprises inputting the voice into the second AI model and receiving, as an output from the second AI model, at least one keyword, and
wherein the providing comprises displaying the at least one keyword along with the image.
4. The method of claim 3 , further comprising:
displaying a keyword of a voice subsequently input along with the at least one keyword previously displayed.
5. The method of claim 1 , further comprising:
displaying a user interface (UI) element to delete the second feature information of the voice from the tag information.
6. The method of claim 1 , wherein the identifying the object comprises identifying a first object associated with the voice and obtaining tag information for the first object by referring to pre-generated tag information associated with a second object included in the image.
7. The method of claim 1 , further comprising:
based on the object associated with the voice being identified, displaying a UI element notifying that the identified object is a target object to be tagged.
8. The method of claim 1 , wherein the obtaining the first feature information comprises, based on the plurality of objects associated with the voice being identified from the image, obtaining tagging information for each of the plurality of objects based on the voice.
9. The method of claim 1 , further comprising:
storing the tag information associated with the image.
10. The method of claim 1 , wherein the obtaining the second feature information comprises inputting the voice into the second AI model and receiving, as an output from the second AI model, one or more keywords, and
wherein the tag information is generated from the one or more keywords.
11. An electronic apparatus comprising:
a display;
a microphone;
a memory configured to store computer executable instructions; and
a processor configured to execute the computer executable instructions to:
control the display to display an image including a plurality of objects,
receive a voice of a user through the microphone,
obtain first feature information on the plurality of objects, by inputting the image to a first AI model,
obtain second feature information of the voice by inputting the voice to a second AI model,
compare the first feature information with the second feature information,
identify an object whose first feature information matches a portion of the second feature information, from among the plurality of objects in the image, based on the comparison,
generate tag information corresponding to the identified object based on the second feature information, and
provide the tag information for the identified object,
wherein the second feature information comprises personalized information which is reflected with a unique thinking of the user and a feeling of the user.
12. The electronic apparatus of claim 11 , wherein the tag information further comprises information on the identified object among the first feature information obtained by inputting the image to the first AI model.
13. The method of claim 1 , wherein a plurality of keywords of the voice are identified by inputting the voice to the second AI model, and receiving, as an output from the second AI model, the plurality of keywords,
the object among the plurality of objects in the image is identified based on one or more first keywords of the plurality of keywords, and
the tag information corresponding to the identified object is generated based on the first feature information and one or more second keywords among the plurality of keywords.
14. The electronic apparatus of claim 11 , wherein the processor is configured to identify a plurality of keywords of the voice by inputting the voice to the second AI model, and receiving, as an output from the second AI model, the plurality of keywords,
identify the object among the plurality of objects in the image based on one or more first keywords of the plurality of keywords, and
generate the tag information corresponding to the identified object based on the first feature information and one or more second keywords among the plurality of keywords.
15. The electronic apparatus of claim 11 , wherein the second feature information is obtained by inputting the voice into the second AI model and receiving, as an output from the second AI model, one or more keywords, and
wherein the tag information is generated from the one or more keywords.