Communication device, communication robot and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-2018366121-A1
Application number	US-201816002506-A
Country	US
Kind code	A1
Filing date	Jun 7, 2018
Priority date	Jun 14, 2017
Publication date	Dec 20, 2018
Grant date	—

Abstract

A communication device including: an utterance acquisition part configured to acquire an utterance of a user to a character; an information acquisition part configured to acquire information different from the utterance; a voice generation part configured to generate a response voice to be emitted by the character based on a content of the utterance acquired by the utterance acquisition part; and an expression generation part configured to generate a response expression to be expressed by a face portion of the character based on the content of the utterance acquired by the utterance acquisition part, wherein when the information is acquired from the information acquisition part, the expression generation part generates the response expression using the information together with the content of the utterance, the response expression generated when the information is acquired being different from a response expression generated when the information is not acquired.

First claim

What is claimed is:

1 . A communication device that allows a character to talk with a user, the communication device comprising:
an utterance acquisition part configured to acquire an utterance of the user to the character; an information acquisition part configured to acquire information different from the utterance; a voice generation part configured to generate a response voice to be emitted by the character based on a content of the utterance acquired by the utterance acquisition part; and an expression generation part configured to generate a response expression to be expressed by a face portion of the character based on the content of the utterance acquired by the utterance acquisition part, wherein when the information is acquired from the information acquisition part, the expression generation part generates the response expression using the information together with the content of the utterance, the response expression generated when the information is acquired being different from a response expression generated when the information is not acquired.

2 . The communication device according to claim 1 , further comprising:
a database configured to store a plurality of the response expressions associated with a plurality of emotions, respectively, wherein the expression generation part selects, from the database, the response expression associated with a third emotion that is determined according to a combination of a first emotion and a second emotion, the first emotion being estimated based on the content of the utterance and the second emotion being estimated based on the information acquired by the information acquisition part.

3 . The communication device according to claim 2 , wherein:
in the database, the plurality of emotions is associated with the plurality of the response expressions, respectively, based on a Russell's circumplex model; and the expression generation part determines the third emotion based on a sum of a first vector corresponding to the first emotion in the Russell's circumplex model and a second vector corresponding to the second emotion in the Russell's circumplex model.

4 . The communication device according to claim 2 , wherein the expression generation part selects, from the database, the response expression corresponding to a fourth emotion that approximates the third emotion in a predetermined range.

5 . The communication device according to claim 1 , wherein when generating two response expressions consecutively, the expression generation part generates at least one interpolation response expression between the two response expressions, the at least one interpolation response expression interpolating the two response expressions.

6 . The communication device according to claim 1 , wherein the information acquisition part includes an imaging part configured to capture an image of the user.

7 . The communication device according to claim 1 , wherein the information acquisition part includes a biometric sensor configured to acquire biological information of the user.

8 . The communication device according to claim 1 , wherein the information acquisition part includes an environmental sensor configured to acquire environmental information of a surrounding environment of the communication device.

9 . The communication device according to claim 1 , further comprising:
a state acquisition part configured to acquire an internal state of a character device that embodies the character, wherein the expression generation part generates the response expression based on the internal state acquired by the state acquisition part in addition to the content of the utterance and the information.

10 . A communication robot, comprising:
the communication device according to claim 1 ; and the face portion configured to express the response expression generated by the expression generation part.

11 . A non-transitory computer-readable storage medium, comprising:
a memory part configured to store a communication control program to be executed by a computer of a communication device that allows a character to talk with a user, wherein when the communication control program is executed by the computer, the computer executes the following steps of:
an utterance acquisition step of acquiring an utterance of the user to the character;
an information acquisition step of acquiring information different from the utterance;
a voice generation step of generating a response voice to be emitted by the character based on a content of the utterance acquired in the utterance acquisition step; and
an expression generation step of generating a response expression to be expressed by a face portion of the character based on the content of the utterance acquired in the utterance acquisition step, and
wherein in the expression generation step, when the information is acquired, the response expression is generated using the information together with the content of the utterance, the response expression generated when the information is acquired being different from a response expression generated when the information is not acquired.

Assignees

• Toyota Motor Co Ltd

Inventors

• Funazukuri Mina
• Yoshizawa Shintaro
• Kaku Wataru
• Yamada Hitoshi

Classifications

• G10L25/63 Primary

  for estimating an emotional state · CPC title

• G06F2203/011

  Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns · CPC title

• G10L15/22 Primary

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

• B25J13/003

  by means of an audio-responsive input (audible safety signals B25J19/061) · CPC title

• G06N3/008

  based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour · CPC title