Method of operating a speech dialogue system

• US 20030110041A1
• Filed: 11/15/2002
• Published: 06/12/2003
• 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: Halberschmidt, Martin, Prangenberg, Martin, Woehrmann, Thomas, Schroeer, Olaf, Vranken, Peter, Breuer, Richard, Hodam, Henrik
• Granted Patent: US 8,543,405 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: 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 (1) which communicates with a user while a speech recognition device (2) and/or a speech output device (3) and a dialogue control unit (4) are used, which unit controls a dialogue run between the user and the speech dialogue system on the basis of a dialogue description (B), characterized in that at least a certain position (P′

) that can be reached during a dialogue between the user and the speech dialogue system (1) in the dialogue run is marked as an entry position (P′

) in the speech dialogue system (1), an address (A) belonging to the position (P′

) being stored in the dialogue description together with a marker (M) assigned to the position (P′

), so that the speech dialogue system (1) automatically jumps to the assigned address (A) in the dialogue description (B) if the user enters the stored marker (M) at a later instant and the dialogue is continued from the respective position (P′

) onwards.

2. A method as claimed in claim 1, characterized in that the user, when reaching a certain position in a dialogue, causes the speech dialogue system to mark this position as an entry position.

3. A method as claimed in claim 1 or 2, characterized in that the speech dialogue system automatically offers the user to mark this position as an entry position when a certain position in a dialogue has been reached.

4. A method as claimed in one of the claims 1 to 3, characterized in that the speech dialogue system automatically marks certain positions as entry positions.

5. A method as claimed in one of the claims 1 to 4, characterized in that, 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/or in that the speech dialogue system predefines a marker.

6. A method as claimed in one of the claims 1 to 5, characterized in that when an entry position (P′

) is marked, environment parameters (U) are stored which are needed by the dialogue control unit for a further dialogue at this position (P′

).

7. A method as claimed in one of the claims 1 to 6, characterized in that in a certain session the addresses (A) in the dialogue description (B) and the assigned markers (M) as well as any associated environment parameters (U) are stored as user-specific data (A, M, U) in a memory (8) and are re-used at least partially by the control of the dialogue run in a later session.

8. A method as claimed in one of the claims 1 to 7, characterized in that during the marking of an entry position the speech dialogue system automatically and/or after the predefinition by the user at least an associated keyword (S) is stored while the concept of this keyword (S) has a connection with the marked entry position (P′

) in the dialogue.

9. A method as claimed in claim 8, characterized in that the speech dialogue system, after the user has entered a keyword, automatically jumps to an address assigned to an associated entry position in the dialogue description or delivers to the users the markers of various entry positions belonging to this keyword.

10. A method as claimed in one of the claims 1 to 9, characterized in that when an entry position is marked and/or when a marked entry position is reached in a dialogue, the speech dialogue system stores protocol data which contain information about the order in which the marked entry position was reached relative to other marked entry positions during the dialogue.

11. A method as claimed in claim 10, characterized in that 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.

13. A computer program with program code means to carry out all the steps of a method as claimed in one of the claims 1 to 11, if the program is run on a computer of a speech dialogue system.

14. A computer program with program code means as claimed in claim 13, which are stored on a data carrier that can be read by a computer.

12. A speech dialogue system (1) comprising a speech recognition device (2) and/or a speech output device (3) for communication with a user and with a dialogue control unit (4) for controlling a dialogue run between the user and the speech dialogue system (1) based on a dialogue description (B), characterized by

means for marking certain positions (P′

) in the dialogue run as entry positions (P′

) in the speech dialogue system (1), which positions (P′

) can be reached during a dialogue between the user and the speech dialogue system (1), the means comprising a memory (8) for storing an address (A) belonging to the position (P′

) in the dialogue description (B) as well as a marker (M) assigned to the position (P′

), and

means for automatically jumping to the assigned address (A) in the dialogue description (B) when a stored marker (M) is entered by the user and for proceeding with the dialogue from the respective position (P′

) onwards.