Electronic device and method for controlling the same

• US 9,953,648 B2
• Filed: 04/15/2016
• Issued: 04/24/2018
• Est. Priority Date: 05/11/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Choi, Hyung-tak, Hwang, In-chul, Kim, Deok-ho, Lee, Jung-sup, Jeon, Hee-sik
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US15/130,399
• Publication Number:
  US 20160336024A1
• Time in Patent Office: 739 Days
• Field of Search: 704239, 704246, 704247, 704251, 704252
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

An electronic device and a method for controlling the same are provided. The electronic device includes a storage configured to store domain information that is categorized for dialog subjects, a speaker configured to output a system response based on a user utterance sound, and a processor configured to detect a domain, among the domain information, based on the user utterance sound, determine one among the detected domain and a previous domain as a domain to be used to process the user utterance sound, based on a confidence between the user utterance sound and the detected domain, and process the user utterance sound to generate the system response, based on the determined domain.

Claims

1. An electronic device for generating an audible system response comprising:

a storage configured to store domain information that is categorized for dialogue subjects, and control information for performing tasks corresponding to the dialogue subjects and dialogue patterns for the dialogue subjects

a microphone configured to receive a user utterance sound;

a speaker configured to output a first audible system response, based on the user utterance sound; and

a processor configured to;

detect a current domain, among the domain information, based on the user utterance sound received by the microphone;

determine one among the current domain and a previous domain as a selected domain to be used to process the user utterance sound received by the microphone, said selected domain being determined based on a first confidence between the user utterance sound and the current domain and a second confidence between the user utterance sound and the previous domain that is used before the current domain to process a previous user utterance sound; and

process the user utterance sound to generate the first audible system response with the speaker, based on the selected domain, wherein

in response to the current domain being determined as the selected domain, the processor stores information of the previous domain in the storage as interrupted domain information, and after the user utterance sound is processed based on the current domain as the selected domain, the processor controls the speaker to output a second audible system response responding to the previous user utterance sound based on the stored interrupted domain information.

2. The electronic device of claim 1, wherein the storage is further configured to:

categorize the dialogue subjects corresponding to respective domains for contexts; and

store the categorized dialogue subjects, and

wherein the processor is further configured to;

select a context, from the contexts, based on the user utterance sound, in response to the previous domain being determined as the selected domain;

determine one among the selected context and a previous context as a determined context to be used to process the user utterance sound, based on a confidence between the user utterance sound and the selected context; and

process the user utterance sound to generate the first audible system response, based on the determined context.

3. The electronic device of claim 2, wherein the processor is further configured to:

store information of the previous context in the storage as interrupted context information in response to the selected context being determined as the determined context; and

process a new utterance sound, based on the interrupted context information, after the user utterance sound is processed based on the selected context as the determined context.

4. The electronic device of claim 1, wherein the processor is further configured to:

process a new utterance sound, based on the stored interrupted domain information, after the user utterance sound is processed based on the current domain as the selected domain.

5. The electronic device of claim 1, wherein the processor is further configured to determine the first confidence between the user utterance sound and the current domain, based on whether an utterance element of the user utterance sound coincides with an utterance element of the current domain.

6. The electronic device of claim 1, further comprising a communicator configured to communicate with an external device,

wherein the processor is further configured to, in response to the processor processing the user utterance sound to generate the first audible system response based on a context using a control of a function of the external device in the selected domain, generate a system response for controlling the function of the external device, based on information of the function of the external device.

7. The electronic device of claim 6, wherein the storage is further configured to store the information of the function of the external device,

wherein the communicator is further configured to receive new information of the function of the external device that is added in a network, and

wherein the processor is further configured to update the stored information, based on the received new information.

8. The electronic device of claim 1, wherein the processor is further configured to determine one among the current domain and the previous domain as the selected domain to be used to process the user utterance sound, based on utterance history information, and

the utterance history information comprises at least one among a previously received user utterance sound, information of a domain that was used to process the previously received user utterance sound, and a system response that was generated based on the previously received user utterance sound.

9. The electronic device of claim 1, wherein the domain information comprises at least one among the control information for performing the tasks corresponding to the dialogue subjects and the dialogue patterns for the dialogue subjects.

10. The electronic device of claim 1, wherein the processor is further configured to:

determine only the first confidence between the user utterance sound and the current domain and the second confidence between the user utterance sound and the previous domain that is used immediately before the current domain to process the previous user utterance sound immediately before the user utterance sound; and

control the speaker to output a message inquiring whether the current domain or the previous domain is the selected domain to be used to process the user utterance sound, in response to the determined first confidence being equal to the determined second confidence.

11. A method of controlling an electronic device for generating a system response, including a storage storing domain information that is categorized for dialogue subjects, and control information for performing tasks corresponding to the dialogue subjects and dialogue patterns for the dialogue subjects, the method comprising:

receiving, with a microphone, a user utterance sound;

detecting, with a processor, a current domain, among the domain information, based on the user utterance sound;

determining, with the processor, one among the current domain and a previous domain as a selected domain to be used to process the user utterance sound received by the microphone, said selected domain being determined based on a first confidence between the user utterance sound and the current domain and a second confidence between the user utterance sound and the previous domain that is used before the current domain to process a previous user utterance sound, wherein the processor determines the current domain as the selected domain;

storing, with the processor, information of the previous domain in the storage as interrupted domain information in response to the current domain being determined as the selected domain;

processing, with the processor, the user utterance sound to generate a first system response, based on the selected domain;

outputting, with an external device or a speaker of the electronic device, the first system response; and

outputting, with the speaker of the electronic device, an audible second system response responding to the previous user utterance sound based on the stored interrupted domain information, after the user utterance sound is processed based on the current domain as the selected domain.

12. The method of claim 11, further comprising:

processing a new utterance sound, based on the stored interrupted domain information, after the user utterance sound is processed based on the current domain as the selected domain.

13. The method of claim 11, further comprising determining the first confidence between the user utterance sound and the current domain, based on whether an utterance element of the user utterance sound coincides with an utterance element of the current domain.

14. The method of claim 11, further comprising, in response to the processing the user utterance sound to generate the first system response based on a context using a control of a function of the external device in the selected domain, generating a system response for controlling the function of the external device, based on information of the function of the external device.

15. The method of claim 14, further comprising:

receiving new information of the function of the external device that is added in a network; and

updating the information of the function of the external device, based on the received new information.

16. The method of claim 11, further comprising determining one among the current domain and the previous domain as the selected domain to be used to process the user utterance sound, based on utterance history information,

wherein the utterance history information comprises at least one among a previously received user utterance sound, information of a domain that was used to process the previously received user utterance sound, and a system response that was generated based on the previously received user utterance sound.

17. The method of claim 11, wherein the domain information comprises at least one among the control information for performing the tasks corresponding to the dialogue subjects and the dialogue patterns for the dialogue subjects.

18. A non-transitory computer-readable storage medium storing a program to cause a computer to perform the method of claim 11.