IP Library › Granted Patent US 11,526,720
Granted Patent B2
US 11,526,720 · App. 16/220,457 · Granted Dec 13, 2022

Artificial intelligence system for supporting communication

Inventor: Kazutaka Yonekura (Tokyo, JP)
Assignee: ALT INC.
G06N3/006G06F16/337G06F16/583G06F16/90332G06F16/951G06F16/9535G06N3/00G06N20/00G06Q50/01
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 11,526,720
App. No.
16/220,457
Granted
Dec 13, 2022
Kind
B2
Abstract

An artificial intelligence system includes a first information processing module generating data related to a language based on social data of a first user registered in one or a plurality of social network services, and a second information processing module generating data related to an image based on social data of the first user registered in one or a plurality of social network services. The first information processing module and the second information processing module generate a virtual first user on a computer with respect to the first user.

Claims (19)

1. An artificial intelligence system comprising:

a first processor configured to generate data related to a language based on social data of a first user registered in one or a plurality of social network services;

a second processor configured to generate data related to an image based on social data of the first user registered in one or a plurality of social network services;

a first memory configured to store social data of the first user and social data of an other user registered in the one or the plurality of social network services; and

a second memory configured to store a personalization model, a generalization model, and general image data obtained by crawling the internet,

wherein the second processor includes a third processor configured to generate the personalization model suitable to the first user by machine learning based on social data of the first user, and a fourth processor configured to obtain social data of the other user as learning data and generate the generalization model modelled by machine learning,

wherein the first processor and the second processor are configured to generate a virtual first user on a computer with respect to the first user.

2. The artificial intelligence system according to claim 1 , wherein the first memory includes a first sub-memory configured to store social data of the first user, a second sub-memory configured to store social data of the other user, and a third sub-memory configured to store data obtained by the first processor crawling the internet.

3. The artificial intelligence system according to claim 2 , wherein the first processor is configured to deduce and generate an appropriate response to a question from among data stored in the first memory by reading out at least a part of data stored in the first memory.

4. The artificial intelligence system according to claim 1 , wherein the second processor is configured to read out data stored in the second memory and create an image conceptualized by the first virtual user with respect to a thing or an object.

5. The artificial intelligence system according to claim 3 , further comprising a third memory configured to group together similar questions as similar questions and correlate and store the similar questions with responses to the similar questions,

wherein the first processor is configured to select a response to a question from the third memory.

6. The artificial intelligence system according to claim 5 , wherein the third memory includes a fourth memory configured to group together and store similar question content, and a fifth memory configured to store responses to the similar questions.

7. The artificial intelligence system according to claim 5 , wherein the third memory has a hierarchy including a fourth sub-memory configured to store data obtained by classifying a question and a response from among social data of the first user, a fifth sub-memory configured to store data obtained by classifying a question and a response from among social data of a plurality of users, and a sixth sub-memory configured to store data obtained by classifying a question and a response from among text data.

8. The artificial intelligence system according to claim 1 , wherein the second processor is configured to generate the personalization model and the generalization model by deep learning.

9. The artificial intelligence system according to claim 1 , wherein the virtual first user generated on the computer by the first processor and the second processor is configured to have a conversation with the first user and other users apart from the first user.

10. The artificial intelligence system according to claim 9 , further comprising a fifth processor configured to receive an evaluation of a content of a response of the virtual first user.

11. The artificial intelligence system according to claim 10 , wherein the fifth processor is configured to notify the first user of an evaluation result of the content of the response of the virtual first user.

12. The artificial intelligence system according to claim 11 , further comprising a sixth processor configured to edit the content of the response of the virtual first user when the first user receives a notification from the fifth processor, and a seventh processor configured to update the content of the response of the virtual first user based on the content edited by the sixth processor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 14, 2018
From: YONEKURA, KAZUTAKA
To: ALT INC.
Reel/Frame 047778/0289 →
Priority Claims (1)
JP JP2016-119697 · Jun 16, 2016 · national
Continuity (2)
Continuation PCTJP2017022185 · Jun 15, 2017
Related Publication 20190122093A1 · Apr 25, 2019
Cited By (2)
US 12,488,012 US 12,608,568