IP Library Granted Patent US 11,676,588
Granted Patent B2
US 11,676,588 · App. 16/955,778 · Granted Jun 13, 2023

Dialogue control system, dialogue control method, and program

Inventor: Masayuki Chatani (Tokyo, JP)
Assignee: RAKUTEN GROUP, INC.
G10L15/22G06Q30/0631G10L15/30G06N20/00G10L2015/223
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,676,588
App. No.
16/955,778
Granted
Jun 13, 2023
Kind
B2
Abstract

A dialogue control system, comprising at least one processor configured to: acquire remark information about a remark of a user; control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and output the reply information generated by at least one of a plurality of dialogue generators, wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and wherein each of the plurality of dialogue generators is configured to generate new reply information based on the reply information that has been generated and output by another of the plurality of dialogue generators.

Claims (40)

1. A dialogue control system, comprising at least one processor configured to:

acquire remark information about a remark of a user;

control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and

output the reply information generated by at least one of a plurality of dialogue generators,

wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and

wherein each of the plurality of dialogue generators is configured to generate new reply information based on output reply information that has been generated and output by another of the plurality of dialogue generators;

wherein the reply information includes probability information about a probability of details of a reply,

wherein the at least one processor determines the reply information to be output, based on the probability information included in the reply information generated by each of the plurality of dialogue generators, and

wherein each of the plurality of dialogue generators is configured to update the probability information when the remark information is acquired as the dialogue progresses.

2. The dialogue control system according to claim 1 , wherein each of the plurality of dialogue generators is configured to generate the new reply information based further on the remark information about a remark made in response to a reply that is indicated by the reply information.

3. The dialogue control system according to claim 1 , wherein each of the plurality of dialogue generators is configured to determine whether to generate the new reply information without waiting for a reaction of the user, based on the probability information included in the reply information that has been generated by another of the plurality of dialogue generators and that has been output.

4. A dialogue control system, comprising at least one processor configured to:

acquire remark information about a remark of a user;

control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and

output the reply information generated by at least one of a plurality of dialogue generators,

wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and

wherein each of the plurality of dialogue generators is configured to generate new reply information based on output reply information that has been generated and output by another of the plurality of dialogue generators,

wherein the at least one processor is configured to:

determine that the dialogue has started when a predetermined start condition is fulfilled; and

determine that the dialogue has ended when a predetermined end condition is fulfilled,

wherein each of the plurality of dialogue generators is configured to generate the new reply information based on the output reply information that has been generated by another of the plurality of dialogue generators in a period of any length between a point in time determined as a start of the dialogue and a point in time determined as an end of the dialogue.

5. The dialogue control system according to claim 1 , wherein each of the plurality of dialogue generators is configured to generate the new reply information based on a relation between each of the plurality of dialogue generators and another of the plurality of dialogue generators that has generated and output the reply information.

6. A dialogue control system, comprising at least one processor configured to:

acquire remark information about a remark of a user;

control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and

output the reply information generated by at least one of a plurality of dialogue generators,

wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and

wherein each of the plurality of dialogue generators is configured to generate new reply information based on output reply information that has been generated and output by another of the plurality of dialogue generators,

wherein each of the plurality of dialogue generators is associated with a database about merchandise or a service, and

wherein each of the plurality of dialogue generators is configured to generate the new reply information for suggesting, to the user, the merchandise or service different from the merchandise or service of another of the plurality of dialogue generators, based on the database associated with each of the plurality of dialogue generators.

7. The dialogue control system according to claim 6 , wherein each of the plurality of dialogue generators is configured to generate the new reply information for suggesting, to the user, the merchandise or service related to the merchandise or the service that has been suggested by another of the plurality of dialogue generators.

8. A dialogue control system, comprising at least one processor configured to:

acquire remark information about a remark of a user;

control a plurality of dialogue generators each for generating, when the remark information is acquired, reply information about a reply to be made in response to the remark indicated by the remark information; and

output the reply information generated by at least one of a plurality of dialogue generators,

wherein the acquisition of the remark information and the output of the reply information are repeated so that a dialogue progresses, and

wherein each of the plurality of dialogue generators is configured to generate new reply information based on output reply information that has been generated and output by another of the plurality of dialogue generators,

wherein the at least one processor executes processing for providing a combination of suggested pieces of merchandise or a combination of suggested services to the user, based on the remark information about a remark made after the combination of suggested pieces of merchandise or the the combination of suggested services is suggested to the user by each of the plurality of dialogue generators.

9. The dialogue control system according to claim 1 , wherein the at least one processor is configured to acquire the remark information based on a speech of the user that has been detected by an audio input device.

10. The dialogue control system according to claim 1 , wherein the output reply information indicates a first merchandise on an internet and the new reply information indicates a second merchandise that is recommended along with the first merchandise.

Assignments (2)
CHANGE OF NAME Recorded Jul 13, 2021
From: RAKUTEN, INC.
To: RAKUTEN GROUP, INC.
Reel/Frame 056845/0831 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 21, 2020
From: CHATANI, MASAYUKI
To: RAKUTEN, INC.
Reel/Frame 052995/0654 →
Continuity (1)
Related Publication 20200372912A1 · Nov 26, 2020