公开(公告)号：US20230177356A1

公开(公告)日：2023-06-08

申请号：US17599973

申请日：2021-07-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Wonjong CHOI ,  Soofeel KIM ,  Yewon PARK ,  Jina HAM

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: Provided is a system and method of modifying a knowledge graph for providing a service. A method, performed by a server, of modifying a knowledge graph for providing a service includes obtaining text related to an inquiry of a user; identifying a service related to an intention of the user by interpreting the text using at least one natural language understanding (NLU) model; obtaining a detailed knowledge graph related to the identified service; identifying at least one parameter indicating a constraint based on the intention of the user, based on a result of the interpreting; selecting a common knowledge graph related to a parameter representing the constraint from among a plurality of common knowledge graphs related to the identified service; extracting a first knowledge triple related to the parameter from the selected common knowledge graph; and modifying the detailed knowledge graph based on the extracted first knowledge triple.

公开(公告)号：US20220318512A1

公开(公告)日：2022-10-06

申请号：US17312699

申请日：2021-03-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Wonjong CHOI ,  Soofeel KIM ,  Yewon PARK ,  Jina HAM

IPC: G06F40/30

Abstract: Disclosed are an electronic device and a control method thereof. The electronic device includes a memory, and a processor configured to, based on a text being input, determine semantic roles of sentence components included in the text by inputting information on the input text to a first model trained to determine semantic roles of sentence components included in a sentence, obtain a risk level of the text by inputting the sentence components corresponding to the determined semantic roles to a second model trained to output a risk level based on the semantic roles of the sentence components included in the sentence, and perform an operation corresponding to the obtained risk level of the text.