Dialogue method, dialogue system, dialogue apparatus and program

Patent metadata

Field	Value
Publication number	US-11354517-B2
Application number	US-201816491301-A
Country	US
Kind code	B2
Filing date	Jan 26, 2018
Priority date	Mar 10, 2017
Publication date	Jun 7, 2022
Grant date	Jun 7, 2022

Abstract

It is an object of the present invention to prevent inattentive listening to a dialogue of an agent without taking it seriously and to make it easier to understand the dialogue with the agent. A dialogue system 100 conducts a dialogue with a user 101. A humanoid robot 50-1 presents a leap-in-logic utterance, which is an utterance, of which a logical structure is partially missing. The user 101 expresses a confirmation action which is an action confirming the missing information in the leap-in-logic utterance. The humanoid robot 50-1 presents a supplementary utterance which is an utterance describing the missing information.

First claim

What is claimed is:

1. A dialogue method executed by a dialogue system that conducts a dialogue with a user, the method comprising:
an utterance decision step in which, from contents of an utterance of a sentence structure made up of a premise, an interpretation and a conclusion decided by a predetermined procedure, an utterance decision part of the dialogue system generates a leap-in-logic utterance which is an utterance missing partially information of the premise, the interpretation and the conclusion in the sentence structure of the contents of the utterance;
an utterance presentation step in which a presentation part of the dialogue system presents the leap-in-logic utterance;
a confirmation receiving step in which an input part of the dialogue system receives a user action after the leap-in-logic utterance is presented; and
a supplementary presentation step in which where the user action is a confirmation action which is an action to confirm information missing in the leap-in-logic utterance, the presentation part of the dialogue system presents a supplementary utterance which is an utterance describing the missing information.

2. The dialogue method according to claim 1 , further comprising:
a confirmation presentation step in which when the user action is not a confirmation action, the presentation part of the dialogue system presents an utterance confirming information missing in the leap-in-logic utterance.

3. The dialogue method according to claim 1 , wherein the leap-in-logic utterance is an utterance which is an utterance with a second topic which is a topic less relevant to the topic of the dialogue made before the leap-in-logic utterance and in which at least one of words representing the second topic is not included.

4. The dialogue method according to claim 1 , wherein the leap-in-logic utterance is an utterance with a topic less relevant to the topic of the dialogue made before the leap-in-logic utterance and which is an utterance, at a beginning of which a topic transition word indicating that a topic is changed is added.

5. The dialogue method according to claim 1 , wherein the supplementary utterance is an utterance including a question with contents with which the user can easily agree regarding the missing information.

6. A non-transitory computer-readable recording medium having a program recorded thereon for causing a computer to execute each step of the dialogue method according to claim 1 .

7. A dialogue system that conducts a dialogue with a user, the dialogue system comprising processing circuitry configured to:
decide contents of an utterance of a sentence structure made up of a premise, an interpretation and a conclusion by a predetermined procedure;
generate a leap-in-logic utterance which is an utterance missing partially information of the premise, the interpretation and the conclusion in the sentence structure of the contents of the utterance;
present the leap-in-logic utterance;
decide a supplementary utterance which is an utterance describing information missing in the leap-in-logic utterance;
present the leap-in-logic utterance;
receive a user action after the leap-in-logic utterance is presented; and
present the supplementary utterance where the user action is a confirmation action which is an action for confirming the information missing in the leap-in-logic utterance.

8. A dialogue apparatus that decides an utterance presented by a dialogue system comprising at least a presentation part that presents an utterance and an input part receives a user action, the dialogue apparatus comprising processing circuitry configured to:
decide contents of an utterance of a sentence structure made up of a premise, an interpretation and a conclusion by a predetermined procedure;
generate a leap-in-logic utterance which is an utterance missing partially information of the premise, the interpretation and the conclusion in the sentence structure of the contents of the utterance;
and
decide a supplementary utterance which is an utterance describing information missing in the leap-in-logic utterance, where the supplementary utterance be presented where the user action presented after the leap-in-logic utterance is an action for confirming the information missing in the leap-in-logic utterance.

9. A non-transitory computer-readable recording medium having a program recorded thereon for causing a computer to function as the dialogue apparatus according to claim 8 .

Assignees

• Nippon Telegraph & Telephone
• Univ Osaka

Inventors

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

Classifications

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G10L15/22

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

• G06F3/011

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title