DIALOGUE SUPPORT APPARATUS, METHOD AND TERMINAL

• US 20170337036A1
• Filed: 08/09/2017
• Published: 11/23/2017
• Est. Priority Date: 03/12/2015
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Fujii, Hiroko
• Granted Patent: US 10,248,383 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

According to one embodiment, a dialogue support apparatus includes a processing circuitry. The processing circuitry receives input information indicating a user'"'"'s intention. The processing circuitry determines at least one target dialogue state among dialogue histories related to dialogue states indicating dialogue results between a user and a dialogue system which estimates the user'"'"'s intention and performs processing in accordance with the user'"'"'s intention, the target dialogue state being a target of instructions from the user. The processing circuitry acquires a processing result from the dialogue system by inputting the input information and the target dialogue state into the dialogue system. The processing circuitry generates first update information to update a display of the processing result.

Claims

1. A dialogue support apparatus comprising:

a processing circuitry configured to;

receive input information indicating a user'"'"'s intention;

determine at least one target dialogue state among dialogue histories related to dialogue states indicating dialogue results between a user and a dialogue system which estimates the user'"'"'s intention and performs processing in accordance with the user'"'"'s intention, the target dialogue state being a target of instructions from the user;

acquire a processing result from the dialogue system by inputting the input information and the target dialogue state into the dialogue system; and

generate first update information to update a display of the processing result.

2. The apparatus according to claim 1, wherein the processing circuitry is further configured to:

receive an operation of the user on a screen; and

determine a dialogue state designated by the operation as the target dialogue state.

3. The apparatus according to claim 1, further comprising a storage which stores dialogue information which includes an identifier of a dialogue state and a display flag indicating whether the dialogue state is in a normal display or in a thumbnail display,

wherein the processing circuitry determines a dialogue state for which the display flag indicates the normal display as the target dialogue state.

4. The apparatus according to claim 3, wherein the processing circuitry is further configured to update the dialogue information when the user'"'"'s operation on the screen is an operation to change a display flag of the dialogue state.

5. The apparatus according to claim 3, wherein

the dialogue information further includes a dialogue sequence identifier which indicates a group of dialogue states related to a predetermined dialogue in a dialogue scenario, and

the processing circuitry generates second update information to display a displayed dialogue state in a thumbnail display when a dialogue sequence identifier of the displayed dialogue state is different from a dialogue sequence identifier of a current dialogue state.

6. The apparatus according to claim 1, wherein when a current dialogue state is to change a condition of a dialogue state included in the dialogue history, the processing circuitry acquires one or more dialogue states after the dialogue state which is a target of change included in the dialogue history, and

generates third update information to display the current dialogue state and the one or more dialogue states.

7. The apparatus according to claim 6, wherein the processing circuitry generates fourth update information to display a switch display for a user to select whether or not the one or more dialogue state is displayed in addition to the current dialogue state.

8. The apparatus according to claim 1, wherein the processing circuitry generates fifth update information to display processing results side by side when the processing results are generated respectively to a plurality of dialogue states.

9. The apparatus according to claim 1, wherein the input information is a speech recognition result of utterance of the user.

20. A terminal comprising:

a speech acquiring unit which acquires a user'"'"'s utterance to obtain a speech recognition result;

a communicating unit which sends the speech recognition result to the dialogue support apparatus according to claim 1 to receive a processing result; and

a display unit which displays the processing result.

10. A dialogue support method comprising:

receiving input information indicating a user'"'"'s intention;

determining at least one target dialogue state among dialogue histories related to dialogue states indicating dialogue results between a user and a dialogue system which estimates the user'"'"'s intention and performs processing in accordance with the user'"'"'s intention, the target dialogue state being a target of instructions from the user;

acquiring a processing result from the dialogue system by inputting the input information and the target dialogue state into the dialogue system; and

generating first update information to update a display of the processing result.

11. The method according to claim 10, further comprising:

receiving an operation of the user on a screen; and

determining a dialogue state designated by the operation as the target dialogue state.

12. The method according to claim 10, further comprising storing, in the storage, dialogue information which includes an identifier of a dialogue state and a display flag indicating whether the dialogue state is in a normal display or in a thumbnail display,

wherein the determining determines a dialogue state for which the display flag indicates the normal display as the target dialogue state.

13. The method according to claim 12, further comprising updating the dialogue information when the user'"'"'s operation on the screen is an operation to change a display flag of the dialogue state.

14. The method according to claim 12, wherein

the dialogue information further includes a dialogue sequence identifier which indicates a group of dialogue states related to a predetermined dialogue in a dialogue scenario, and

the generating generates second update information to display a displayed dialogue state in a thumbnail display when a dialogue sequence identifier of the displayed dialogue state is different from a dialogue sequence identifier of a current dialogue state.

15. The method according to claim 10, wherein when a current dialogue state is to change a condition of a dialogue state included in the dialogue history, the acquiring acquires one or more dialogue states after the dialogue state which is a target of change included in the dialogue history, and

the generating generates third update information to display the current dialogue state and the one or more dialogue states.

16. The method according to claim 15, wherein the generating generates fourth update information to display a switch display for a user to select whether or not the one or more dialogue state is displayed in addition to the current dialogue state.

17. The method according to claim 10, wherein the generating generates fifth update information to display processing results side by side when the processing results are generated respectively to a plurality of dialogue states.

18. The method according to claim 10, wherein the input information is a speech recognition result of utterance of the user.

19. A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method that uses utterance intention of a user, the utterance intention being inferred from a first text representing results of speech recognition of user'"'"'s utterances, the method comprising:

receiving input information indicating a user'"'"'s intention;

determining at least one target dialogue state among dialogue histories related to dialogue states indicating dialogue results between a user and a dialogue system which estimates the user'"'"'s intention and performs processing in accordance with the user'"'"'s intention, the target dialogue state being a target of instructions from the user;

acquiring a processing result from the dialogue system by inputting the input information and the target dialogue state into the dialogue system; and

generating first update information to update a display of the processing result.