Server and method of controlling the same

• US 9,230,559 B2
• Filed: 06/14/2013
• Issued: 01/05/2016
• Est. Priority Date: 06/15/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Cha, Tae-hwan, Yoon, Seung-il
• Primary Examiner(s): VO, HUYEN X
• Application Number:
  US13/918,538
• Publication Number:
  US 20130339032A1
• Time in Patent Office: 935 Days
• Field of Search: 704/201, 704/251, 704/235, 704/270, 704/255, 704/257, 704/275, 704 1- 10, 704/231, 704/270.1
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• 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: G10L 25/54 for retrieval
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/472 End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content end-user interfaces for retrieving video data from a database G06F16/739; network services for supporting unicast streaming H04L65/612

Abstract

A server which interacts with a display apparatus is provided. The server includes a storage unit configured to store conversation patterns for each service domain, a communication unit configured to receive a user'"'"'s voice from the display apparatus, and a control unit configured to determine a service domain including the user'"'"'s voice, generate response information corresponding to the user'"'"'s voice based on a conversation pattern of the determined service domain, and to control the communication unit to transmit the response information to the display apparatus. When it is determined that a currently received user'"'"'s voice is included in another service domain which is different from a service domain including a previously received user'"'"'s voice, the control unit generates the response information corresponding to the currently received user'"'"'s voice based on a conversation pattern of the other service domain.

Claims

1. A server which interacts with a display apparatus, the server comprising:

a storage which stores conversation patterns for service domains;

a communicator configured to receive a digital voice signal which is converted by the display apparatus; and

a controller configured to convert the received digital voice signal into a text, determine a service domain related to the converted text, extract a component slot from the converted text based on the determined service domain, generate response information corresponding to the received digital voice signal based on the extracted component slot and a conversation pattern of the determined service domain, and to control the communicator to transmit the response information to the display apparatus,

wherein when it is determined that a currently received digital voice signal is included in another service domain which is different from a service domain including a previously received digital voice signal, the controller generates the response information corresponding to the currently received digital voice signal based on a conversation pattern of the other service domain, and

wherein if a component slot cannot be extracted from a currently received digital voice signal, the controller generates the response information corresponding to the currently received digital voice signal based on a component slot extracted from the previously received digital voice signal.

2. The server as claimed in claim 1, wherein when it is determined that the currently received digital voice signal is included in the other service domain even before slots constituting the service domain are filled with the previously received digital voice signal, the controller generates the response information corresponding to the currently received digital voice signal based on the conversation pattern of the other service domain.

3. The server as claimed in claim 2, wherein the controller determines an utterance intention included in the currently received digital voice signal, generate the response information corresponding to the determined utterance intention based on the conversation pattern of the other service domain, and controls the communicator to transmit the response information to the display apparatus.

4. The server as claimed in claim 1, wherein the response information comprises response message information corresponding to the voice, and the display apparatus outputs the response message corresponding to the voice based on the response message information.

5. The server as claimed in claim 4, wherein the response information further comprises a control command for controlling a function of the display apparatus.

6. The server as claimed in claim 1, wherein the voice expression is a voice expression of a user.

7. A method of controlling a server which interacts with a display apparatus, the method comprising:

receiving a digital voice signal which is converted by the display apparatus;

converting the received digital voice signal into a text;

determining a service domain including the converted text, using conversation patterns;

extracting a component slot from the converted text based on the determined service domain;

generating response information corresponding to a currently received digital voice signal based on the extracted component slot and a conversation pattern of another service domain when the currently received digital voice signal is included in the other service domain which is different from a domain having a previously received digital voice signal; and

transmitting the generated response information to the display apparatus,

wherein the generating comprises, if a component slot cannot be extracted from a currently received digital voice signal, generating the response information corresponding to the currently received digital voice signal based on a component slot extracted from the previously received digital voice signal.

8. The method as claimed in claim 7 wherein the generating comprises generating the response information corresponding to the currently received digital voice signal based on the conversation pattern of the other service domain when it is determined that the currently received digital voice signal is included in the other service domain before slots constituting the service domain are filled with the previously received digital voice signal.

9. The method as claimed in claim 8, wherein the generating includes determining an utterance intention included in the received digital voice signal and generating the response information corresponding to the determined utterance intention based on the conversation pattern of the other service domain.

10. The method as claimed in claim 7, wherein the response information includes response message information corresponding to the received digital voice signal, and the display apparatus outputs a response message corresponding to the received digital voice signal based on the response message information.

11. The method as claimed in claim 10, wherein the response information further includes a control command for controlling a function of the display apparatus.

12. The method as claimed in claim 7, wherein the voice expression is a voice expression of a user.

13. A server which interacts with a display apparatus, the server comprising:

a storage which stores conversation patterns for service domains;

a communicator configured to receive a digital voice signal which is converted by the display apparatus; and

a controller configured to convert the received digital voice signal into a text, determine a service domain among a plurality of service domains, each of said plurality of service domains being related to a corresponding conversation pattern, extract a component slot from the converted text based on the determined service domain, generate response information corresponding to the received digital voice signal based on the extracted component slot and a conversation pattern of the determined service domain, and to control the communicator to transmit the response information to the display apparatus,

wherein if a component slot cannot be extracted from a currently received digital voice signal, the controller generates the response information corresponding to the currently received digital voice signal based on a component slot extracted from a previously received digital voice signal, the currently received digital voice signal being included in a domain different from another domain which includes the previously received digital voice signal.

14. The server as claimed in claim 13, wherein the controller determines an utterance intention included in the received digital voice signal, generate the response information corresponding to the determined utterance intention based on the conversation pattern, and controls the communicator to transmit the response information to the display apparatus.

15. A method of controlling a server which interacts with a display apparatus, the method comprising:

receiving a digital voice signal which is converted by the display apparatus;

converting the received digital voice signal into a text;

determining a service domain related to the received digital voice signal among a plurality of service domains, using conversation patterns, each of the plurality of service domains being related to corresponding conversation patterns;

extracting a component slot from the converted text based on the determined service domain;

generating response information corresponding to the receive digital voice signal based on the extracted component slot and a conversation pattern of the determined service domain; and

transmitting the generated response information to the display apparatus,

wherein the generating comprises, if a component slot cannot be extracted from a currently received digital voice signal, generating the response information corresponding to the currently received digital voice signal based on a component slot extracted from a previously received digital voice signal, the currently received digital voice signal being included in a domain different from another domain which includes the previously received digital voice signal.