Dialogue method, dialogue system, dialogue apparatus and program

Patent metadata

Field	Value
Publication number	US-11222634-B2
Application number	US-201816491442-A
Country	US
Kind code	B2
Filing date	Jan 26, 2018
Priority date	Mar 10, 2017
Publication date	Jan 11, 2022
Grant date	Jan 11, 2022

Abstract

It is an object of the present invention to induce a dialogue to a topic that a dialogue system tries to present. A dialogue system 100 presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user 101. A humanoid robot 50-1 presents the first utterance. A microphone 11-1 receives a user utterance of the user 101 after the first utterance. A humanoid robot 50-2 presents at least one topic-inducing utterance for inducing the topic to the target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance after the user utterance. The humanoid robot 50-1 presents the target utterance after the topic-inducing utterance.

First claim

What is claimed is:

1. A dialogue method executed by a dialogue system that presents a first utterance which is a predetermined utterance sentence and a target utterance which is an utterance sentence predetermined as an utterance sentence related to the first utterance to a user, the method comprising:
a first presentation step in which a presentation part presents the first utterance;
an utterance receiving step in which an input part receives a user utterance of the user after the first utterance;
a second presentation step in which the presentation part presents at least one topic-inducing utterance after the user utterance, where the at least one topic-inducing utterance includes a second utterance to be presented as a next utterance of the user utterance, the second utterance includes a first word and a second word, the first word is associated from any one of words included in an utterance sentence of the user utterance, and the second word is suggestive of any one of words included in the utterance sentence of the target utterance; and
a third presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance.

2. A dialogue method executed by a dialogue system that presents a target utterance related to a user utterance of a user to the user, the method comprising:
an utterance receiving step in which an input part receives the user utterance;
a first presentation step in which a presentation part presents at least one topic-inducing utterance after the user utterance, where the at least one topic-inducing utterance includes a second utterance to be presented as a next utterance of the user utterance, the second utterance includes a first word and a second word, the first word is associated from any one of words included in an utterance sentence of the user utterance, and the second word is suggestive of any one of words included in the utterance sentence of the target utterance; and
a second presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance.

3. A dialogue method executed by a dialogue system that presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user, the method comprising:
a first presentation step in which a presentation part presents the first utterance;
an utterance receiving step in which an input part receives a user utterance of the user after the first utterance;
a second presentation step in which the presentation part presents at least one topic-inducing utterance after the user utterance to induce a topic to a target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance; and
a third presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance,
wherein when recognition of the user utterance fails, in the second presentation step,
after the user utterance, a first personality which is a personality presenting the first utterance presents a first topic-inducing utterance which is an utterance having a same meaning as the first utterance to a second personality which is a personality other than the first personality, and
after the first topic-inducing utterance, the second personality presents a second topic-inducing utterance which is an utterance based on the first topic-inducing utterance and the utterance sentence of the target utterance.

4. A dialogue method executed by a dialogue system that presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user, the method comprising:
a first presentation step in which a presentation part presents the first utterance;
an utterance receiving step in which an input part receives a user utterance of the user after the first utterance;
a second presentation step in which the presentation part presents at least one topic-inducing utterance after the user utterance to induce a topic to a target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance; and
a third presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance;
wherein when recognition of the user utterance fails, in the second presentation step,
after the user utterance, a second personality which is a personality other than a personality presenting the first utterance presents a first topic-inducing utterance which is an utterance related to the first utterance but having contents different from contents of the first utterance, and
after the at least one topic-inducing utterance, a plurality of personalities present a plurality of topic-inducing utterances.

5. A dialogue method executed by a dialogue system that presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user, the method comprising:
a first presentation step in which a presentation part presents the first utterance;
an utterance receiving step in which an input part receives a user utterance of the user after the first utterance;
a second presentation step in which the presentation part presents at least one topic-inducing utterance after the user utterance to induce a topic to a target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance; and
a third presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance,
wherein when recognition of the user utterance fails, in the second presentation step,
after the user utterance, a second personality which is a personality other than the personality presenting the first utterance presents a topic-inducing utterance which is an utterance made in response to the first utterance.

6. A dialogue method executed by a dialogue system that presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user, the method comprising:
a first presentation step in which a presentation part presents the first utterance;
an utterance receiving step in which an input part receives a user utterance of the user after the first utterance;
a second presentation step in which the presentation part presents at least one topic-inducing utterance after the user utterance to induce a topic to a target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance; and
a third presentation step in which the presentation part presents the target utterance after the at least one topic-inducing utterance,
wherein when the target utterance does not cause any uncomfortable feeling as an utterance receiving a positive utterance made in response to the first utterance and when positive intention is detected from a recognition result of the user utterance, or
when the target utterance does not cause any uncomfortable feeling as the utterance receiving a negative utterance made in response to the first utterance and when negative intention is detected from the recognition result of the user utterance,
the at least one topic-inducing utterance includes an utterance following the user utterance by a personality A which is a certain personality and
an utterance not following the user utterance by a personality B which is a personality other than the personality A.

7. A dialogue method executed by a dialogue system that presents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user, the method comprising:
a first presentat

Assignees

• Nippon Telegraph & Telephone
• Univ Osaka

Inventors

• Sugiyama Hiroaki
• Narimatsu Hiromi
• Yoshikawa Yuichiro
• Iio Takamasa
• Arimoto Tsunehiro
• Ishiguro Hiroshi

Classifications

• G10L15/22 Primary

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

• G06F3/16

  Sound input; Sound output (speech processing G10L) · CPC title

• G10L15/183

  using context dependencies, e.g. language models · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title