	US 11,861,318 B2
	Method for providing sentences on basis of persona, and electronic device supporting same
Eunchung Noh, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Appl. No. 17/311,559
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
PCT Filed Dec. 9, 2019, PCT No. PCT/KR2019/017293 § 371(c)(1), (2) Date Jun. 7, 2021, PCT Pub. No. WO2020/130447, PCT Pub. Date Jun. 25, 2020.
Claims priority of application No. 10-2018-0164198 (KR), filed on Dec. 18, 2018.
Prior Publication US 2022/0027574 A1, Jan. 27, 2022
Int. Cl. G10L 13/033 (2013.01); G06F 40/35 (2020.01); G06F 40/253 (2020.01); G06F 40/166 (2020.01); G06N 3/08 (2023.01); H04L 51/02 (2022.01)

CPC G06F 40/35 (2020.01) [G06F 40/166 (2020.01); G06F 40/253 (2020.01); G06N 3/08 (2013.01); H04L 51/02 (2013.01); G10L 13/033 (2013.01)]

14 Claims

1. An electronic device comprising:

a memory; and

at least one processor,

wherein the at least one processor is configured to:

receive a user input for requesting a content, in response to obtaining the user input, identify at least one word representing the requested content in the sentence,

determining at least one persona related to the requested content, based on the at least one word,

acquire a first response sentence corresponding to the user input and the requested content,

convert the first response sentence to at least one second response sentence having a style corresponding to the at least one persona, using a neural network,

based on at least one of speech rate, accent, pitch, or habit of the at least one persona, change the at least one second response sentence to voice-type information, and

provide the voice-type information through sound output device.