Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020091187 - ELECTRONIC APPARATUS AND CONTROLLING METHOD THEREFOR

Publication Number WO/2020/091187
Publication Date 07.05.2020
International Application No. PCT/KR2019/008468
International Filing Date 10.07.2019
IPC
G10L 15/18 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
G10L 15/26 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
26Speech to text systems
G10L 15/22 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialog
Applicants
  • 삼성전자주식회사 SAMSUNG ELECTRONICS CO., LTD. [KR]/[KR]
Inventors
  • 유영준 RYU, Youngjun
  • 진장호 JIN, Jangho
Agents
  • 김태헌 KIM, Tae-hun
  • 정홍식 JEONG, Hong-sik
Priority Data
10-2018-013168931.10.2018KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) ELECTRONIC APPARATUS AND CONTROLLING METHOD THEREFOR
(FR) APPAREIL ÉLECTRONIQUE ET SON PROCÉDÉ DE COMMANDE
(KO) 전자 장치 및 그 제어 방법
Abstract
(EN)
In the present disclosure, provided are an electronic apparatus and a controlling method therefor. The electronic apparatus of the present disclosure comprises: a memory in which a first model and a second model are stored; and a processor configured to, when user voice is received, generate a response to the user voice according to completion of the received user voice, the completion being determined on the basis of the first model and the second model. Here, the first model uses, as training data, sentence structures of a plurality of completed sentences, and the second model uses, as training data, a plurality of completed sentences and intents corresponding to the plurality of completed sentences. In particular, the first model and the second model may be artificial intelligence models trained according to at least one of machine learning, a neural network, or a deep learning algorithm.
(FR)
La présente invention concerne un appareil électronique et son procédé de commande. L'appareil électronique de la présente invention comprend : une mémoire dans laquelle un premier modèle et un second modèle sont stockés ; et un processeur configuré de manière, lorsqu'une voix d'utilisateur est reçue, à générer une réponse à la voix d'utilisateur en fonction de l'achèvement de la voix d'utilisateur reçue, l'achèvement étant déterminé sur la base du premier modèle et du second modèle. Ici, le premier modèle utilise, en tant que données d'apprentissage, des structures de phrases d'une pluralité de phrases achevées, et le second modèle utilise, en tant que données d'apprentissage, une pluralité de phrases et d'intentions achevées correspondant à la pluralité de phrases achevées. En particulier, le premier modèle et le second modèle peuvent être des modèles d'intelligence artificielle entraînés selon un apprentissage machine et/ou un réseau neuronal et/ou un algorithme d'apprentissage profond.
(KO)
본 개시에서는 전자 장치 및 그 제어 방법이 제공된다. 본 개시의 전자 장치는, 제1 모델 및 제2 모델이 저장된 메모리 및 사용자 음성이 수신되면, 제1 모델 및 제2 모델을 기초로 판단된 수신된 사용자 음성의 완결 여부에 대응하여 사용자 음성에 대한 응답을 생성하는 프로세서를 포함한다. 여기에서, 제1 모델은, 복수의 완결된 문장의 문형을 학습 데이터로 한 모델이고, 제2 모델은, 복수의 완결된 문장 및 상기 복수의 완결된 문장과 대응된 의도(intent)를 학습 데이터로 한 모델이다. 특히, 제1 모델 및 제2 모델은 기계학습, 신경망 또는 딥러닝 알고리즘 중 적어도 하나에 따라 학습된 인공지능 모델일 수 있다.
Latest bibliographic data on file with the International Bureau