INTERACTIVE SERVER, CONTROL METHOD THEREOF, AND INTERACTIVE SYSTEM

• US 20140195249A1
• Filed: 01/07/2014
• Published: 07/10/2014
• Est. Priority Date: 01/07/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: CHUNG, Ji-hye, LEE, Cheong-jae, LEE, Hye-jeong, SHIN, Yong-wook
• Granted Patent: US 10,891,968 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• 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
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

An interactive server, a control method thereof, and an interactive system are provided. The interactive server includes: a communicator which communicates with a display apparatus to receive an uttered voice signal; a storage device which stores utterance history information of a second uttered voice signal received from the display apparatus before the first uttered voice signal is received; an extractor which extracts uttered elements from the received first uttered voice signal; and a controller which generates response information based on the utterance history information stored in the storage device and the extracted uttered elements and transmits the response information to the display apparatus. Therefore, the interactive server comprehends intentions of the user with respect to various uttered voices of the user to generate response information according to the intentions and transmits the response information to the display apparatus.

Claims

1. An interactive server comprising:

a communicator configured to communicate with a apparatus to receive a first uttered voice signal;

a storage device configured to store utterance history information of a second uttered voice signal received from the apparatus before the first uttered voice signal is received;

an extractor configured to extract uttered elements from the received first uttered voice signal; and

a controller configured to generate response information based on at least one from among the utterance history information stored in the storage device and the extracted uttered elements, and transmit the response information to the apparatus.

2. The interactive server of claim 1, wherein:

if an execution language and a command respectively corresponding to the extracted uttered elements are stored in the storage device, the controller combines the execution language and the command respectively corresponding to the uttered elements to generate the response information; and

if the execution language and the command respectively corresponding to the extracted uttered elements are not stored in the storage device, the controller estimates the execution language and the command respectively corresponding to the extracted uttered elements based on the utterance history information stored in the storage device and combines the estimated execution language and the command to generate the response information.

3. The interactive server of claim 2, wherein:

the first uttered voice signal comprises first and second uttered elements; and

if the execution language and the command respectively corresponding to the extracted uttered elements are not stored in the storage device, the controller acquires the utterance history information stored within a preset time range based on a time when the second uttered voice signal is received and estimates an execution language corresponding to the first uttered element and a command corresponding to the second uttered element as the execution language and the command corresponding to the first uttered voice signal within the acquired utterance history information.

4. The interactive server of claim 3, wherein if the utterance history information stored in the storage device does not comprise the utterance history information stored within the preset time based on the time when the second uttered voice signal is received, the controller does not generate the response information.

5. The interactive server of claim 3, wherein if the first uttered voice signal does not comprise at least one of the first uttered element and the second uttered element, the controller generates response information corresponding to the second uttered voice signal based on the utterance history information stored within the preset time range based on the time when the second uttered voice signal is received.

6. The interactive server of claim 1, further comprising:

a voice processor configured to convert the received first uttered voice signal into text information.

15. The interactive server of claim 3, wherein the time is related to a time difference between utterance of the first uttered voice signal and the second uttered voice signal.

17. The interactive server of claim 1, wherein the first uttered voice signal is uttered by a first user and the utterance history information of the second uttered voice signal relates to an uttered voice input of a second user.

20. The interactive server of claim 1, wherein the apparatus comprises a display apparatus.

7. A method of controlling an interactive server, the method comprising:

receiving a first uttered voice signal from an apparatus;

extracting uttered elements from the received first uttered voice signal;

generating response information based on at least one from among stored utterance history information and the extracted uttered elements; and

transmitting the generated response information to the apparatus,

wherein the stored utterance history information is information which is generated based on a second uttered voice signal received from the apparatus before the first uttered voice signal is received.

8. The method of claim 7, further comprising:

determining whether an execution language and a command respectively corresponding to the extracted uttered elements exist,

wherein if the execution language and the command respectively corresponding to the uttered elements exist, the execution language and the command respectively corresponding to the uttered elements are combined to generate response information, and if the execution language and the command respectively corresponding to the uttered elements do not exist, the execution language and the command corresponding to the extracted uttered elements are estimated based on the stored utterance history information and are combined to generate the response information.

9. The method of claim 8, wherein:

the first uttered voice signal comprises first and second uttered elements; and

if the execution language and the command respectively corresponding to the uttered elements do not exist, utterance history information stored within a preset time range is acquired based on a time when the second uttered voice signal is received, and the execution language corresponding to the first uttered element and the command corresponding to the second uttered element are estimated as the execution language and a command corresponding to the uttered voice signal within the acquired utterance history information.

10. The method of claim 9, wherein if the utterance history information does not comprise the utterance history information stored within the preset time range based on the time when the second uttered voice signal is received, the response information is not generated.

11. The method of claim 9, wherein if the first uttered voice signal does not comprise at least one of the first uttered element and the second uttered element, response information corresponding to the first uttered voice signal is generated based on the utterance history information stored within the preset time range based on the time when the second uttered voice signal is received.

12. The method of claim 7, further comprising:

converting the received first uttered voice signal into text information.

16. The method of claim 9, wherein the time is related to a time difference between utterance of the first uttered voice signal and the second uttered voice signal.

18. The method of claim 7, wherein the first uttered voice signal is uttered by a first user and the utterance history information relates to an uttered voice input of a second user.

21. The method of claim 7, wherein the apparatus comprises a display apparatus.

13. An interactive system comprising:

an apparatus which, if an uttered voice of a user is input, performs a function corresponding to the input uttered voice; and

an interactive server which, if a first uttered voice signal is received from the apparatus, extracts uttered elements from the first uttered voice signal, generates response information based on at least one from among stored utterance history information and the extracted uttered elements, and transmits the response information to the apparatus,

wherein the apparatus performs a function corresponding to an intention of the user based on the response information received from the interactive server, and the stored utterance history information is information which is generated based on a second uttered voice signal received from the apparatus before the first uttered voice signal is received.

14. The interactive system of claim 13, wherein the interactive server generates the response information based on an execution language and a command respectively corresponding to the uttered elements if the execution language and the command respectively corresponding to the extracted uttered elements exist, and, if the execution language and the command respectively corresponding to the extracted uttered elements do not exist, estimates the execution language and the command respectively corresponding to the extracted uttered elements based on the stored utterance history information and combines the estimated execution language and command to generate the response information.

19. The interactive system of claim 13, wherein the first uttered voice signal is uttered by a first user and the utterance history information relates to an uttered voice input of a second user.

22. The interactive system of claim 13, wherein the apparatus comprises a display apparatus.