Method of operating a speech dialogue system

• US 8,543,405 B2
• Filed: 11/15/2002
• Issued: 09/24/2013
• Est. Priority Date: 11/20/2001
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Breuer, Richard, Halberschmidt, Martin, Hodam, Henrik, Prangenberg, Martin, Schroeer, Olaf, Vranken, Peter, Woehrmann, Thomas
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US10/295,122
• Publication Number:
  US 20030110041A1
• Time in Patent Office: 3,966 Days
• Field of Search: 704270-275
• 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: H04M 2203/303 Marking
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

The invention relates to a method of operating a speech dialogue system which communicates with a user while a speech recognition device and/or a speech output device and a dialogue control unit are used which unit controls a dialogue run between the user and the speech dialogue system on the basis of a dialogue description (B). According to the invention at least one position (P′) that can be reached during a dialogue between the user and the dialogue system is marked in the dialogue run in the speech dialogue system, with which an address (A) belonging to the position (P′) is stored with a marker (M) assigned to the position (P′) in the dialogue description. At a later entry of the stored marker (M) by the user the speech dialogue system automatically jumps to the assigned address (A) in the dialogue description (B) and proceeds with the dialogue from that respective position (P′) onwards. In addition, the invention relates to a speech dialogue system.

Claims

1. A method of operating a speech dialogue system adapted to communicate with a user while a speech recognition device and a speech output device and a dialogue control unit are used, the method comprising:

controlling a dialogue run between a user and a speech dialogue system on the basis of a dialogue description;

marking at least a certain position that can be reached during a dialogue between the user and the speech dialogue system in the dialogue run as an entry position in the speech dialogue system;

storing an address belonging to the position in the dialogue description together with a marker assigned to the position;

automatically selecting the assigned address in the dialogue description if the user enters the stored marker at a later instant and the dialogue is continued from the respective position onwards,

wherein when an entry position is marked, environment parameters are stored which environmental parameters are needed by the dialogue control unit for a further dialogue at the marked position, the environmental parameters include an address of a database and a parameter which is transferred to the database when the stored marker is selected.

2. The method according to claim 1, wherein when a position is marked as an entry position, the speech dialogue system suggests various possible markers to the user from which the user can select a marker belonging to this position and wherein the speech dialogue system predefine the possible markers.

3. The method according to claim 1, further including:

when a marked entry position is reached in the dialogue, storing the order in which the marked entry position was reached relative to other marked entry positions during the dialogue.

4. A method as claimed in claim 3, wherein the user controls the speech dialogue system while using the protocol data, so that he again reaches a marked entry position reached during the previous dialogue in a current session and/or a previous session.

5. A method of operating a speech dialog system which includes a speech recognition unit which receives spoken inputs from a user, a speech output device which delivers spoken outputs to the user, and a speech dialog control unit which controls a spoken dialog with the user based on a speech dialog description, the method comprising:

controlling the spoken dialog with the user based on the speech dialog description;

during the spoken dialog, marking an entry position in the spoken dialog with a corresponding marker;

storing the marker, an address in the speech dialog description corresponding to the marked position in the spoken dialog, and a user selection for an input to be input at the marked position;

in response to the user inputting the stored marker at a later time, selecting the address in the speech dialog description corresponding to the marked entry position and inputting the user selection at the marked entry position such that the spoken dialog continues from the marked position without the user inputting a user selection.

6. The method according to claim 5, wherein marking the position includes:

with the speech dialog system, suggesting potential markers;

inputting a user selection of one of the potential markers.

7. The method according to claim 5, wherein the storing step further includes:

storing an order in which the user reached the marked entry position relative to other marked positions.

8. The method according to claim 5, wherein the stored user selection includes an address of a database.

9. The method according to claim 5, wherein the stored user selection includes an address of a database and a parameter to be transferred to the database such that the user reaches a corresponding position in the database.

10. The method according to claim 9, wherein the user reaches the corresponding position in the database in response to inputting the marker and without further user inputs.

11. The method according to claim 9, wherein the database includes a timetable.

12. The method according to claim 9, wherein the database includes a transportation timetable.

13. The method according to claim 12, wherein the parameter is a point of departure.

14. The method according to claim 9, further including:

receiving the parameter in a user input;

searching for the marker stored with the parameter.

15. The method according to claim 5, wherein the user selection includes a keyword.

16. The method according to claim 15, further including:

storing a plurality of markers and corresponding keywords;

receiving an input keyword;

retrieving one or more markers which are stored with the received keyword.

17. The method according to claim 16, wherein the marker for each position is predefined by the speech dialog system.