SYSTEM, APPARATUS, AND METHOD FOR PROCESSING NATURAL LANGUAGE, AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM

• US 20170069315A1
• Filed: 07/18/2016
• Published: 03/09/2017
• Est. Priority Date: 09/09/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: CHUNG, Ji-hye, KIM, Kyung-duk
• Granted Patent: US 10,553,210 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A system, apparatus, and method for processing a natural language, and a computer readable recording medium are provided. The system includes a user device configured to receive a compound or complex sentence and a natural language processing apparatus configured to generate a plurality of control commands for the user device based on whether operations intended by a user are sequentially performable in the compound or complex sentence received from the user device.

Claims

1. An apparatus for processing a natural language, the apparatus comprising:

a memory storing operation information describing whether certain operations are sequentially performable;

a communication interface configured to receive a compound or complex sentence uttered by a user corresponding to a plurality of operations intended by the user; and

a natural language processor configured to generate a plurality of control commands for a user device by determining whether the plurality of operations intended by the user in the received compound or complex sentence are sequentially performable, based on the operation information stored in the memory.

2. The apparatus of claim 1, wherein the natural language processor is further configured to divide the received compound or complex sentence into a plurality of shorter sentences and to determine whether the operations intended by the user in each of the plurality of shorter sentences are sequentially performable operations.

3. The apparatus of claim 2, wherein the natural language processor comprises:

an intention verifier configured to determine whether the operations intended by the user in each of the plurality of shorter sentences are sequentially performable;

a dialog context manager configured to, in response to the intention verifier determining that the operations intended by the user in each of the plurality of shorter sentences are sequentially performable, determine the operations intended by the user in each of the plurality of shorter sentences based on a dialog context of the operations and a stored dialog history; and

a system behavior generator configured to generate a control command corresponding to the determined operations.

4. The apparatus of claim 3, wherein the system behavior generator is configured to generate a system answer for performing a sub-dialog with the user to determine the operations.

5. The apparatus of claim 3, wherein in response to the intention verifier determining that the operations intended by the user in each of the plurality of shorter sentences are not sequentially performable, the system behavior generator is configured to generate a control command for outputting a warning message and to generate a control command for performing only one operation from among the operations intended by the user in each of the plurality of shorter sentences.

6. The apparatus of claim 3, further comprising:

a voice synthesizer configured to, in response to a voice signal corresponding to the control command being provided to the user, synthesize the control command and the voice signal.

7. The apparatus of claim 1, wherein the memory further stores direction information which describes an order in which the certain operations are sequentially performable.

8. A method of processing a natural language, the method comprising:

storing operation information describing whether certain operations intended are sequentially performable;

receiving a compound or complex sentence uttered by a user corresponding to a plurality of operations intended by the user; and

generating a plurality of control commands for a user device by determining whether the plurality of operations intended by the user in the received compound or complex sentence are sequentially performable, based on the stored operation information.

9. The method of claim 8, further comprising:

dividing the received compound or complex sentence into a plurality of shorter sentences; and

determining whether the operations intended by the user in each of the plurality of shorter sentences are sequentially performable operations.

10. The method of claim 9, further comprising:

in response to the operations intended by the user in each of the plurality of shorter sentences being determined as being sequentially performable, determining the operations intended by the user in each of the plurality of shorter sentences based on a dialog context of the operations and a stored dialog history; and

generating a control command corresponding to the determined operations.

11. The method of claim 10, wherein the generating the control command comprises generating a system answer for performing a sub-dialog with the user to determine the operations.

12. The method of claim 10, wherein the generating of the control command comprises, in response to the operations intended by the user in each of the plurality of shorter sentences being determined as being not sequentially performable, generating a control command for outputting a warning message and generating a control command for performing only one operation from among the operations intended by the user in each of the plurality of shorter sentences.

13. The method of claim 10, further comprising:

in response to a voice signal corresponding to the control command being provided to the user synthesizing the control command and the voice signal.

14. The method of claim 8, wherein the storing comprises storing direction information which describes an order in which the certain operations are sequentially performable.

15. A non-transitory computer readable recording medium comprising a program for executing a method of processing a natural language, wherein the method comprises:

storing operation information describing whether certain operations are sequentially performable;

receiving a compound or complex sentence uttered by a user corresponding to a plurality of operations intended by the user; and

generating a plurality of control commands for a user device by determining whether the plurality of operations intended by the user in the received compound or complex sentence are sequentially performable, based on the stored operation information.