Interactive system, terminal, method of controlling dialog, and program for causing computer to function as interactive system

Patent metadata

Field	Value
Publication number	US-10657960-B2
Application number	US-201615761010-A
Country	US
Kind code	B2
Filing date	Jul 22, 2016
Priority date	Sep 24, 2015
Publication date	May 19, 2020
Grant date	May 19, 2020

Abstract

A dialog content is generated using information that is unique to a user and information that is not unique. The processing executed by a dialog system includes a step of identifying a person based on a dialog with a user, a step of acquiring personal information, a step of analyzing the dialog, a step of extracting an event, a step of searching for a local episode and a global episode based on the personal information and the event, a step of generating dialog data using the search result, a step of outputting a dialog, and a step of accepting user evaluation.

First claim

The invention claimed is:

1. A dialog system comprising:
an episode storage unit for storing episodes;
a personal information storage unit for storing user information;
a person identifying unit for identifying a user having a dialog with the dialog system based on a result of a voice recognition process and the user information stored in the personal information storage unit;
an extraction unit for extracting one or more events related to the dialog from the dialog with the user and extracting an episode related to the extracted one or more events from the episode storage unit;
an episode evaluation unit for making an evaluation of the extracted episode, the evaluation being performed in accordance with a predefined criterion;
a generation unit for generating a dialog content suitable for the identified user, based on the extracted episode, personal information of the identified user, and a result of the evaluation; and
an output unit for outputting the generated dialog content.

2. The dialog system according to claim 1 , wherein
the episode storage unit includes
a global episode storage unit for storing global events and
a local episode storage unit for storing local events,
the extraction unit extracts a global episode and a local episode related to the extracted one or more events, and
the generation unit generates a dialog content suitable for the user, based on at least one of the global episode and the local episode and personal information of the identified user, based on the result of the evaluation.

3. The dialog system according to claim 1 , further comprising an evaluation acquisition unit for accepting input of user evaluation for the dialog content output by the output unit,
wherein the episode storage unit is configured to learn the episodes based on the evaluation.

4. The dialog system according to claim 1 , wherein the episodes include at least one of voice, music, video, and text.

5. The dialog system according to claim 1 , wherein
the output unit further includes a terminal having a communication function, and
the generation unit is configured to generate a dialog content suitable for the user, additionally based on the kind of the terminal.

6. The dialog system according to claim 5 , wherein
the terminal includes a device performing operation under an instruction, and
the generation unit generates a dialog content having an instruction to control operation of the device.

7. A terminal configured to connect to the dialog system of claim 1 , comprising:
a storage unit for storing terminal information that identifies the terminal;
a transmission unit for transmitting the terminal information to the dialog system; and
a control unit for controlling operation in accordance with a dialog content output from the dialog system.

8. A method of controlling a dialog by a computer, comprising:
preparing episodes;
preparing user information;
identifying a user having a dialog with a dialog system, based on a result of voice recognition and the user information;
extracting one or more events related to the dialog from the dialog with the user and extracting an episode related to the extracted one or more events;
making an evaluation of the extracted episode, the evaluation being performed in accordance with a predefined criterion;
generating a dialog content suitable for the identified user, based on the extracted episode, personal information of the identified user, and a result of the evaluation; and
outputting the generated dialog content.

9. A non-transitory computer-readable medium comprising program instructions for causing a computer to control a dialog,
the instructions causing the computer to execute:
preparing episodes;
preparing user information;
identifying a user having a dialog with a dialog system, based on a result of voice recognition and the user information;
extracting one or more events related to the dialog from the dialog with the user and extracting an episode related to the extracted one or more events;
making an evaluation of the extracted episode, the evaluation being performed in accordance with a predefined criterion;
generating a dialog content suitable for the identified user, based on the extracted episode, personal information of the identified user, and a result of the evaluation; and
outputting the generated dialog content.

Assignees

• Sharp Kk

Inventors

• Tokunaga Rei
• Ueda Toru

Classifications

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G10L15/22 Primary

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

• G10L2015/226

  using non-speech characteristics · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title