公开(公告)号：US12079565B2

公开(公告)日：2024-09-03

申请号：US17441766

申请日：2021-08-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sanghyuk Yoon ,  Heejun Song ,  Jeongho Mok ,  Jaemin Song ,  Heejae Yu

IPC: G10L15/22 ,  G06F40/166 ,  G06F40/20 ,  G06F40/35

CPC classification number: G06F40/166 ,  G06F40/20 ,  G06F40/35

Abstract: A method, performed by an electronic device, of generating summary information of a conversation text, includes: obtaining at least one first summary text extracted from at least one conversation text of a previous conversation; extracting at least one second summary text from a conversation text of a current conversation; identifying, from among the at least one first summary text, a summary text having a same type as a type of the at least one second summary text; adjusting a score indicating an accuracy of the identified summary text; selecting, from among the at least one first summary text and the at least one second summary text, a summary text corresponding to each of at least one specified type based on a score of each summary text; and generating the summary information based on the selected summary text.

公开(公告)号：US11893813B2

公开(公告)日：2024-02-06

申请号：US17294594

申请日：2020-01-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jeongho Mok ,  Heejun Song ,  Sanghyuk Yoon

IPC: G06V30/148 ,  G06V20/00 ,  G10L15/00 ,  G06V30/10 ,  G06N3/08

CPC classification number: G06V30/153 ,  G06N3/08 ,  G06V20/00 ,  G10L15/00 ,  G06V30/10

Abstract: An electronic device and a control method therefor are provided. The present electronic device comprises: a communication interface including a circuit, a memory for storing at least one instruction, and a processor for executing the at least one instruction, wherein the processor acquires contents through the communication interface, acquires information about a text included in an image of the contents, and acquires, on the basis of the information about the text included in the image of the contents, caption data of the contents by performing voice recognition for voice data included in the contents.