Samsung Electronics Co., Ltd.

Wonho Ryu

Jiyeon Hong

Cheolseung Jung

Seohyun Back

Haejun Lee

Sai Chetan

Yonghyun Ryu

Seokho Yoon

Lyesuk Lee

Haenam Yang

A method of improving output content through iterative generation is provided. The method includes receiving a natural language input, obtaining user intention information based on the natural language input by using a natural language understanding (NLU) model, setting a target area in base content based on a first user input, determining input content based on the user intention information or a second user input, generating output content related to the base content based on the input content, the target area, and the user intention information by using a neural network (NN) model, generating a caption for the output content by using an image captioning model, calculating similarity between text of the natural language input and the generated output content, and iterating generation of the output content based on the similarity.

Device, method, and program for enhancing output content through iterative generation

An electronic device, according to various embodiments of the present disclosure, include: a communication module configured to receive a keyword list that includes a topic keyword and one or more related keywords concerning the topic keyword from another electronic device; and a processor configured to create a topic channel by using the keyword list, collect social media data by using the one or more related keywords, extract related content by analyzing the social media data, and provide the social media data and the related content to the other electronic device through the topic channel.

Method for providing social media content and electronic device using the same

Growing community of inventors

Gyeonggi-do, South Korea

Wonho Ryu