Samsung Electronics Co., Ltd.

Jun Seong Kim

Ji Hyun Kim

Ji Min Lee

Kyu Young Kim

Kyoung Gu Woo

In Chul Hwang

Jung Hoe Kim

Ho Jun Jaygarl

An electronic device using an artificial neural network model including an attention mechanism, according to various embodiments, can comprise: a memory configured to store information including a plurality of recurrent neural network (RNN) layers; and at least one processor connected with the memory and configured to set, as a first key and a value, at least one first hidden representation acquired through at least one layer among the plurality of RNN layers, set, as a second key, at least one second hidden representation acquired through at least one second layer among the plurality of RNN layers, and acquire an attention included in an attention structure at least on the basis of data on the first key, data on the second key, or data on the value.

Electronic device for analyzing meaning of speech, and operation method therefor

A system, apparatus, and method for generating one or more path rules or combination or path rules for performing the operations of an application. According to various embodiments, a user terminal through an intelligence server may generate a path rule and may perform the operation of an application based on the path rule to provide a service. The user terminal may provide a user with the processing status of a user utterance and may receive an additional user input to process the user utterance. For example, when a keyword (or parameter) required to process the user utterance is insufficient, the user terminal may provide the user with a state requiring additional information and may output feedback corresponding to the insufficient state in order to receive the necessary information from the user.

Electronic apparatus for processing user utterance and controlling method thereof

Growing community of inventors

Suwon-si, South Korea

Jun Seong Kim