US 10,706,847 B2Granted

Method for operating speech recognition service and electronic device supporting the same

AssigneeSamsung Electronics Co., Ltd.

InventorsJang Seok Seo, Sang Ki Kang, Han Jun Ku, Sung Pa Park, In Jong Rhee, Ji Soo Yi, Yoo Jin Hong, Kyung Tae Kim, Ji Hyun Kim, Yong Joon Jeon

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

An electronic device includes a communication module, a sensor module, a microphone, a memory, a display, and a processor. The processor is configured to determine whether a user is in proximity to the electronic device, to transmit at least one of voice input information or information on the proximity of the user to the external device, to receive at least one action associated with the execution of the function of the electronic device corresponding to a recognition result from the external device, based on voice input recognition of the external device, to output content associated with execution and/or processing of each of the at least one action, when the user is spaced apart from the electronic device, and to prevent at least a portion of the at least one content from being output in a state that the user is within the specified proximity to the electronic device.

Claims20

Dependent claims

An electronic system comprising:

an electronic device including a housing including a first surface, a viewable display, a proximity sensor disposed on the first surface and adjacent to the display, a microphone, a first speaker disposed on the first surface and adjacent to the display, a second speaker disposed to be spaced apart from the first speaker, a wireless communication circuit, a first processor electrically connected with the display, the proximity sensor, the microphone, the first speaker, the second speaker, and the wireless communication circuit, and a first memory electrically connected with the first processor, and
a first server including a network interface, a second processor electrically connected with the network interface, and a second memory electrically connected with the second processor,
wherein the second memory includes an automatic speech recognition (ASR) module comprising processing circuitry and program elements, a natural language understanding (NLU) module comprising processing circuitry and program elements, and a natural language generator (NLG) module comprising processing circuitry and program elements,
wherein the first memory stores instructions that, when executed, cause the first processor to:
receive proximity data from the proximity sensor;
receive a voice input using the microphone;
and
provide, to the second processor, first data associated with the voice input and second data associated with the proximity data through the wireless communication circuit,
wherein the second memory stores instructions that, when executed, cause the second processor to:
process the first data using at least one of the ASR module and/or the NLU module;
generate a natural language response based on at least a portion of the second data using the NLG module;
generate a path rule including a sequence of at least one function based on the first data and the second data;
and
provide the natural language response and the path rule to the first processor, and
wherein the first memory further stores instructions that, when executed, cause the first processor to:
output at least a portion of the natural language response through the first speaker and/or through the display and the second speaker by executing the at least one function based on the path rule.

13 more elements

An electronic device configured to support a speech recognition service, the electronic device comprising:

a communication module comprising communication circuitry configured to communicate with an external device;
a sensor module comprising sensing circuitry configured to sense a proximity of an object to the electronic device;
a microphone configured to receive a voice input;
a memory configured to store information associated with operation of the speech recognition service;
a display configured to output a screen associated with execution of a function of the electronic device;
and
a processor electrically connected with the communication module, the sensor module, the microphone, the memory, and the display,
wherein the processor is configured to:
determine whether a user and the electronic device are within a specified proximity to each other using the sensor module;
control the electronic device to transmit, to the external device, voice input information and information on the proximity between the user and the electronic device;
control the electronic device to receive a path rule including a sequence of at least one action associated with the execution of the function of the electronic device corresponding to a recognition result from the external device based on voice input recognition of the external device;
control the electronic device to output at least one content associated with execution and/or processing of each of the at least one action based on the path rule, when the user and the electronic device are spaced apart from each other;
and
control the electronic device to prevent at least a portion of the at least one content from being output when the user and the electronic device are within the specified proximity to each other.

11 more elements

A method for operating a speech recognition service of an electronic device, the method comprising:

receiving a voice input;
determining whether the electronic device and a user are within a specified proximity to each other;
transmitting, to an external device which supports the operation of the speech recognition service, voice input information and information on the proximity between the user and the electronic device;
receiving a path rule including a sequence of at least one action associated with execution of a function of the electronic device corresponding to a recognition result of the voice input information from the external device;
outputting at least one content associated with execution or processing of each of the at least one action based on the path rule, when the electronic device and the user are spaced apart from each other;
and
preventing at least a portion of the at least one content from being output when the electronic device and the user are within the specified proximity to each other.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/938,094Filed 28 Mar 2018
Priority: KR 10-2017-003959028 Mar 2017
Published: US 2018/0286400 A14 Oct 2018
Granted: 7 Jul 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G06F 3/167
Sound input; Sound output: audio in a user interface, e.g. using voice commands for navigating, audio feedback
G10L 15/1815
Using natural language modelling: semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
G10L 15/30
Constructional details of speech recognition systems: distributed recognition, e.g. in client-server systems, for mobile phones or network…