Dialogue method, dialogue system, dialogue apparatus and program

Patent metadata

Field	Value
Publication number	US-11222633-B2
Application number	US-201716301641-A
Country	US
Kind code	B2
Filing date	May 19, 2017
Priority date	May 20, 2016
Publication date	Jan 11, 2022
Grant date	Jan 11, 2022

Abstract

The present invention improves a sense of participation in a topic and enables a dialogue to continue for a long time. A dialogue system 12 includes at least an input part 1 that receives a user's utterance and a presentation part 5 that presents an utterance. In an utterance receiving step, the input part 1 receives an utterance performed by the user. In a first presentation step, the presentation part 5 presents an utterance determined based on scenarios stored in advance. In a second presentation step, the presentation part 5 presents the utterance determined based on the user's utterance contents. A dialogue control part 8 performs control to execute a dialogue at least including a first dialogue flow which is a dialogue including the utterance receiving step and the first presentation step at least one time respectively based on a predetermined scenario, and a second dialogue flow which is a dialogue including the utterance receiving step and the second presentation step at least one time respectively.

First claim

What is claimed is:

1. A dialogue method executed by a dialogue system that performs a dialogue with a user, the method comprising:
a first utterance receiving step in which an input part receives a first user utterance which is an utterance performed by the user;
a first presentation step in which a presentation part presents an utterance provided in a pre-stored scenario, wherein the utterance provided in the pre-stored scenario is presented in response to the first user utterance;
a second utterance receiving step in which an input part receives a second user utterance which is an utterance performed by the user;
a second presentation step in which the presentation part presents an utterance explicitly responding to the second user utterance; and
a dialogue control step in which a dialogue control part performs control at least including:
a first dialogue flow which is a dialogue consisted of the first utterance receiving step and the first presentation step at least one time respectively; and
a second dialogue flow which is a dialogue consisted of the second utterance receiving step and the second presentation step at least one time respectively,
wherein the control includes at least one of:
executing the dialogue of the first dialogue flow and the dialogue of the second dialogue flow sequentially; and
executing the dialogue of the second dialogue flow and the dialogue of the first dialogue flow sequentially,
wherein
when the first dialogue flow is executed immediately after the second dialogue flow, selection criteria for selecting one scenario from among a plurality of pre-stored scenarios as a scenario of the first dialogue flow comprise criteria based on utterance contents of the second dialogue flow,
the plurality of pre-stored scenarios are stored with information indicating likelihood of selection of each scenario associated with each scenario, and
the selection criteria are criteria according to which a selection is performed based on the likelihood when a selection of one scenario from among the plurality of pre-stored scenarios based on utterance contents of the second dialogue flow is judged to be inappropriate.

2. A dialogue system that performs a dialogue with a user, comprising:
an input part that receives a first utterance performed by the user and a second user utterance performed by the user;
an utterance determination part that determines a first utterance provided in a pre-stored scenario and a second utterance explicitly responding to the second user utterance;
a presentation part that presents the first utterance determined by the utterance determination part in response to the first user utterance and the second utterance determined by the utterance determination part; and
a dialogue control part that performs control at least including:
a first dialogue flow which is a dialogue consisted of receiving the first user utterance performed by the user and determining the first utterance presented by the presentation part at least one time respectively; and
a second dialogue flow which is a dialogue consisted of receiving the second user utterance performed by the user and determining the second utterance presented by the presentation part at least one time respectively,
wherein the control includes at least one of:
executing the dialogue of the first dialogue flow and the dialogue of the second dialogue flow sequentially; and
executing the dialogue of the second dialogue flow and the dialogue of the first dialogue flow sequentially,
wherein
when the first dialogue flow is executed immediately after the second dialogue flow, selection criteria for selecting one scenario from among a plurality of pre-stored scenarios as a scenario of the first dialogue flow comprise criteria based on utterance contents of the second dialogue flow,
the plurality of pre-stored scenarios are stored with information indicating likelihood of selection of each scenario associated with each scenario, and
the selection criteria are criteria according to which a selection is performed based on the likelihood when a selection of one scenario from among the plurality of pre-stored scenarios based on utterance contents of the second dialogue flow is judged to be inappropriate.

3. A dialogue apparatus that determines an utterance presented by a dialogue system comprising an input part that receives a first user utterance performed by a user and a second user utterance performed by the user, an utterance determination part that determines a first utterance provided in a pre-stored scenario and a second utterance explicitly responding to the second user utterance, and a presentation part that presents the first utterance determined by the utterance determination part in response to the first user utterance and the second utterance determined by the utterance determination part, the dialogue apparatus comprising a dialogue control part that performs control at least including:
a first dialogue flow which is a dialogue consisted of receiving the first user utterance performed by the user and determining the first utterance presented by the presentation part at least one time respectively; and
a second dialogue flow which is a dialogue consisted of receiving the second user utterance performed by the user and determining the second utterance presented by the presentation part at least one time respectively,
wherein the control includes at least one of:
executing the dialogue of the first dialogue flow and the dialogue of the second dialogue flow sequentially; and
executing the dialogue of the second dialogue flow and the dialogue of the first dialogue flow sequentially,
wherein
when the first dialogue flow is executed immediately after the second dialogue flow, selection criteria for selecting one scenario from among a plurality of pre-stored scenarios as a scenario of the first dialogue flow comprise criteria based on utterance contents of the second dialogue flow,
the plurality of pre-stored scenarios are stored with information indicating likelihood of selection of each scenario associated with each scenario, and
the selection criteria are criteria according to which a selection is performed based on the likelihood when a selection of one scenario from among the plurality of pre-stored scenarios based on utterance contents of the second dialogue flow is judged to be inappropriate.

4. A non-transitory computer readable recording medium including computer executable instructions that make a dialogue system perform a dialogue method, wherein the dialogue system performs a dialogue with a user, the dialogue method comprising:
a first utterance receiving step in which an input part receives a first user utterance which is an utterance performed by the user;
a first presentation step in which a presentation part presents an utterance provided in a pre-stored scenario, wherein the utterance provided in the pre-stored scenario is presented in response to the first user utterance;
a second utterance receiving step in which an input part receives a second user utterance which is an utterance performed by the user;
a second presentation step in which the presentation part presents an utterance explicitly responding to the second user utterance; and
a dialogue control step in which a dialogue control part performs control at least including:
a first dialogue flow which is a dialogue consisted of the first utterance receiving step and the first presentation step at least one time respectively; and
a second dialogue flow which is a dialogue consisted of the second utterance receiving step and the second presentation step at least one time respectively,
wherein the control includes at least one of:
executing the dialogue of the first dialogue flow and the dialogue of the second dialogue flow sequentially; and

Assignees

• Nippon Telegraph & Telephone
• Univ Osaka

Inventors

• Sugiyama Hiroaki
• Meguro Toyomi
• Yamato Junji
• Yoshikawa Yuichiro
• Ishiguro Hiroshi

Classifications

• A63H2200/00

  Computerized interactive toys, e.g. dolls · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• A63H3/003

  specially adapted for a particular function not connected with dolls (as electric lighting devices A63H3/006) · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title