Dialog supporting apparatus

• US 20060136227A1
• Filed: 02/14/2006
• Published: 06/22/2006
• Est. Priority Date: 10/08/2004
• Status: Active Grant

• Current Assignee: Intertrust Technologies Corporation (Fidelio Acquisition Co LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Mizutani, Kenji, Okimoto, Yoshiyuki
• Granted Patent: US 7,346,515 B2
• Time in Patent Office: Days
• US Class Current: 704/277
• 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

To provide a dialog supporting apparatus which can support an on-going dialog so that the dialog is smoothly completed irrespective of who the other party in the dialog. The dialog supporting apparatus 100 includes: an utterance receiving unit 101 which receives an utterance of a dialog participant and outputs utterance information for identifying the utterance; an utterance processing unit 102 which translates the utterance identified by the utterance information into the other utterance form; an utterance output unit 103 which outputs the translated utterance information which is the utterance to the other dialog participant; a dialog history database 104 storing dialog histories, each of which includes two or more pieces of past utterance information of the dialog participant which are placed in time sequence; an utterance prediction unit 105 which generates a first utterance prediction information, based on the dialog history, obtains a second utterance prediction information from the other dialog supporting apparatus, and predicts the next utterance of the dialog participant who uses the dialog supporting apparatus 100, based on the first utterance prediction information and the second utterance prediction information.

Claims

1. A dialog supporting apparatus which supports an on-going dialog made by dialog participants, said apparatus comprising:

a dialog history database in which a dialog history of one of the dialog participants is stored; and

an utterance prediction unit operable (a) to generate a first utterance prediction information based on the dialog history stored in said dialog history database, and (b) to obtain a second utterance prediction information from the other dialog supporting apparatus, and (c) to predict a next utterance in the dialog of the dialog participant who uses said dialog supporting apparatus.

2. The dialog supporting apparatus according to claim 1,

wherein said utterance prediction unit is operable to notify the generated first utterance prediction information to said the other dialog supporting apparatus.

3. The dialog supporting apparatus according to claim 1,

wherein said utterance prediction unit is operable to extract a dialog history which is most similar in the situation of the dialog from among dialog histories stored in said dialog history database, the extracted dialog history being the first utterance prediction information.

4. The dialog supporting apparatus according to claim 3,

wherein said utterance prediction unit is operable to generate a prediction stack based on an assembly which corresponds to successive utterances and is commonly included in the dialog histories respectively included in the first utterance prediction information and the second utterance prediction information.

5. The dialog supporting apparatus according to claim 4,

wherein said utterance prediction unit is operable to predict the next utterance of the dialog participant which is an opening utterance of said prediction stack.

6. The dialog supporting apparatus according to claim 4,

wherein, in the case where an utterance of the dialog participant appears in the assembly of utterances of the prediction stack, said utterance prediction unit is operable to move the assembly to an opening part of the prediction stack and to delete, from the prediction stack, utterances from an opening utterance to the utterance.

7. The dialog supporting apparatus according to claim 4,

wherein said utterance prediction unit is operable to judge whether or not an utterance is commonly included in the respective two dialog histories by performing at least one of the following matchings:

a matching based on utterance information for identifying the utterance;

a matching based on a surface expression; and

a matching based on a content word.

8. The dialog supporting apparatus according to claim 3,

wherein said utterance prediction unit is operable to adjust, the numbers of utterances to the same number using a dynamic programming, the respective numbers of utterances being included in the first utterance prediction information and the second utterance prediction information.

9. The dialog supporting apparatus according to claim 1, further comprising:

an utterance receiving unit operable to receive an utterance of one of the dialog participants;

an utterance processing unit operable to transform the utterance received by said utterance receiving unit into the other utterance form; and

an utterance output unit operable to output the utterance of the other utterance form transformed by said utterance processing unit.

10. The dialog supporting apparatus according to claim 9,

wherein said utterance receiving unit is operable to perform speech recognition of a speech to be inputted, after narrowing down a speech recognition dictionary to one of the followings:

prediction utterances predicted by said utterance prediction unit;

sentences which are similar to the prediction utterances;

words included in the prediction utterances; and

words associating with the prediction utterances, and operable to receive a result of the speech recognition as the utterance.

11. The dialog supporting apparatus according to claim 9, said apparatus further comprising

a display unit,

wherein said utterance prediction unit is operable to display the prediction utterance on said display unit;

and

said utterance receiving unit is operable to receive the prediction utterance as the utterance, when the prediction utterance is selected by one of the dialog participants.

12. The dialog supporting apparatus according to claim 9, said apparatus further comprising

a display unit,

wherein said utterance prediction unit is operable to predict a development of the utterances made by the dialog participants, based on the first utterance prediction information and the second utterance prediction information, and to display the predicted development on said display unit.

13. The dialog supporting apparatus according to claim 12,

wherein said utterance prediction unit is operable to notify the predicted development of the utterances to said the other dialog supporting apparatus.

14. The dialog supporting apparatus according to claim 1, said apparatus further comprising

a history registration unit operable to register a history of the dialog made by the dialog participants in the dialog history database.

15. A dialog supporting system for supporting an on-going dialog made by dialog participants, said system comprising:

a first dialog supporting apparatus; and

a second dialog supporting apparatus,

wherein said first dialog supporting apparatus includes;

a first dialog history database in which a dialog history of one of the dialog participants is stored; and

a first utterance prediction unit operable (a) to generate a first utterance prediction information, based on the dialog history stored in said dialog history database, and (b) to obtain a second utterance prediction information from said second dialog supporting apparatus, and to (c) predict a next utterance in the dialog of the dialog participant who uses said first dialog supporting apparatus, and

said second dialog supporting apparatus includes;

a second dialog history database in which a dialog history of the other dialog participant is stored; and

a second utterance prediction unit operable (a) to generate a second utterance prediction information based on the dialog history stored in said second dialog history database, and (b) to obtain the first utterance prediction information from said first dialog supporting apparatus, and to (c) predict a next utterance in the dialog of the dialog participant who uses said second dialog supporting apparatus.

16. A dialog supporting method for supporting a dialog made by dialog participants, said method comprising utterance prediction which includes:

generating a first utterance prediction information based on a past dialog history of one of the dialog participants;

obtaining a second utterance prediction information from the other dialog supporting apparatus; and

predicting a next utterance in the dialog of the dialog participant who uses said dialog supporting apparatus, based on the first utterance prediction information and the second utterance prediction information.

17. A program for supporting an on-going dialog made by dialog participants, said program causing a computer to execute utterance prediction which includes:

generating a first utterance prediction information based on a past dialog history of one of the dialog participants;

obtaining a second utterance prediction information from the other dialog supporting apparatus; and

predicting a next utterance in the dialog of the dialog participant who uses said dialog supporting apparatus, based on the first utterance prediction information and the second utterance prediction information.