IP Library › Granted Patent US 9,454,964
Granted Patent B2
US 9,454,964 · App. 14/450,810 · Granted Sep 27, 2016

Interfacing device and method for supporting speech dialogue service

Inventors: Hayoung Jeon (Seoul, KR); Sora Kim (Seoul, KR); Heewoon Kim (Suwon-si, KR); Yumi Ahn (Hanam-si, KR); Jihyun Ahn (Seoul, KR)
Assignee: Samsung Electronics Co., Ltd.
G10L15/26G06F3/167G10L15/22G06K9/6253G06K9/6293
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,454,964
App. No.
14/450,810
Granted
Sep 27, 2016
Kind
B2
Abstract

An interfacing device and method to support a speech dialogue service based on a multi-modal input are provided. The method includes executing an interface for the speech dialogue service, receiving a user input, through the executed interface, including a voice input and a non-voice input, transmitting, as a request signal to a server, at least one of the voice input or a text extracted from the voice input when the received user input is the voice input, transmitting, as the request signal to the server, a text extracted from the non-voice input when the received user input is the non-voice input, receiving a result of dialogue recognition in response to the request signal from the server, and executing a response to the received user input on the basis of the received result of dialogue recognition.

Claims (44)

1. An interfacing method for supporting a speech dialogue service, the interfacing method comprising:

executing an interface for the speech dialogue service;

receiving a user input, through the executed interface, including a voice input and a non-voice input, the non-voice input being an image input;

transmitting, as a request signal to a server, at least one of the voice input or a text extracted from the voice input when the received user input is the voice input;

transmitting, as the request signal to the server, a text extracted from the non-voice input when the received user input is the non-voice input;

receiving a result of dialogue recognition in response to the request signal from the server; and

executing a response to the received user input on the basis of the received result of dialogue recognition.

2. The interfacing method of claim 1 , further comprising:

setting an input mode of the interface based on a user control,

wherein the setting the input mode comprises at least one of:

selecting a menu of the input mode displayed on a screen in response to a input; or

executing an application related to the input mode in response to a voice command.

3. The interfacing method of claim 1 , wherein the method further comprises:

recognizing text of metadata contained in the image input; and

selecting a specific part among the recognized text through a filtering process.

4. The interfacing method of claim 1 , wherein the method further comprises:

recognizing text from the image input through an optical character recognition process; and

selecting a specific part among the recognized text through a filtering process.

5. The interfacing method of claim 1 , further comprising:

receiving, from the server, a request for checking whether to apply an associated content provider determined by the server; and

checking whether to apply the associated content provider determined by the server, and transmitting a result of the checking to the server.

6. The interfacing method of claim 5 , wherein the executing of the response to the received user input comprises executing the associated content provider when applicability of the associated content provider is accepted.

7. An interfacing device for supporting a speech dialogue service, the interfacing device comprising:

an input unit configured to receive a user input including a voice input and a non-voice input, the non-voice input being an image input;

a communication unit configured to communicate with a server;

a control unit configured to:

execute an interface for the speech dialogue service, to receive the user input through the executed interface,

transmit, as a request signal to the server, at least one of the voice input or a text extracted from the voice input when the received user input is the voice input,

transmit, as the request signal to the server, a text extracted from the non-voice input when the received user input is the non-voice input,

receive a result of dialogue recognition in response to the request signal from the server, and

execute a response to the received user input on the basis of the received result of dialogue recognition; and

an output unit configured to output a result of executing the response to the received user input.

8. The interfacing device of claim 7 , wherein the control unit is further configured to set an input mode of the interface based on a user control, by performing at least one of selecting a menu of the input mode displayed on a screen in response to a input or executing an application related to the input mode in response to a voice command.

9. The interfacing device of claim 7 , wherein the control unit is further configured to:

recognize text of metadata contained in the image input, and

select a specific part among the recognized text through a filtering process.

10. The interfacing device of claim 7 , wherein the control unit is further configured to:

recognize text from the image input through an optical character recognition process, and

select a specific part among the recognized text through a filtering process.

11. The interfacing device of claim 7 , wherein the control unit is further configured to:

receive, from the server, a request for checking whether to apply an associated content provider determined by the server, and

check whether to apply the associated content provider determined by the server, and to transmit a result of the checking to the server.

12. The interfacing device of claim 11 , wherein the control unit is further configured to execute the associated content provider when applicability of the associated content provider is accepted.

13. At least one non-transitory processor readable medium for storing a computer program of instructions configured to be readable by at least one processor for instructing the at least one processor to execute a computer process for performing the method as recited in claim 1 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 4, 2014
From: JEON, HAYOUNG; KIM, SORA; KIM, HEEWOON; AHN, YUMI; AHN, JIHYUN
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 033457/0029 →
Priority Claims (1)
KR 10-2013-0092649 · Aug 5, 2013 · national
Continuity (1)
Related Publication 20150039307A1 · Feb 5, 2015