METHOD FOR CONTROLLING DEVICE ON BASIS OF COMMAND EXTRACTED FROM USER UTTERANCE AND COMPUTING APPARATUS FOR PERFORMING SAME
A method according to the present disclosure may comprise the steps of: acquiring a user utterance; determining whether target text requesting the performance of a function of a device is included in the utterance by using a language model; and controlling the device on the basis of the target text...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Patent |
Sprache: | eng ; fre ; kor |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | A method according to the present disclosure may comprise the steps of: acquiring a user utterance; determining whether target text requesting the performance of a function of a device is included in the utterance by using a language model; and controlling the device on the basis of the target text when it is determined that the target text is included, wherein the language model may be a model trained to extract text related to a request from continuous sentences.
La présente divulgation concerne un procédé qui peut comprendre les étapes consistant à : acquérir un énoncé d'utilisateur ; déterminer si un texte cible demandant les performances d'une fonction d'un dispositif est inclus dans l'énoncé à l'aide d'un modèle de langage ; et commander le dispositif sur la base du texte cible lorsqu'il est déterminé que le texte cible est inclus, le modèle de langage pouvant être un modèle entraîné en vue d'extraire un texte lié à une demande provenant de phrases continues.
본 개시에 따른 방법은 사용자의 발화(utterance)를 획득하는 단계, 언어 모델을 이용하여 발화에 디바이스의 기능 수행을 요청하는 타겟 텍스트가 포함되는지 여부를 판단하는 단계, 타겟 텍스트가 포함되는 것으로 판단되는 경우, 타겟 텍스트에 기초하여 디바이스를 제어하는 단계를 포함하며, 언어 모델은 연속적인 문장(sentence)들로부터 요청(request)과 관련된 텍스트를 추출하도록 학습된 모델일 수 있다. |
---|