IP Library Granted Patent US 12694152
Granted Patent B2
US 12694152 · App. 18/932,641 · Granted Jul 28, 2026

Information processing system, information processing method, and non-transitory computer readable storage medium

Inventors: Minh The Nguyen (Tokyo, JP); Tu Tuan Tran (Tokyo, JP); Thuan Duc Ngo (Tokyo, JP)
Assignee: RAKUTEN GROUP, INC.
G06F21/6254
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 12694152
App. No.
18/932,641
Granted
Jul 28, 2026
Kind
B2
Abstract

Provided is an information processing system configured to: acquire an inquiry including one or more pieces of privacy information based on input from a user; replace each of the one or more pieces of privacy information included in the inquiry with masked information different from the one or more pieces of privacy information; request a language model to create an answer to the inquiry in which the privacy information has been replaced, and acquire the answer from the language model; replace the masked information included in the acquired answer with the privacy information which has been replaced with the masked information in the inquiry; and transmit information based on the answer in which the masked information has been replaced to the user.

Claims (40)

1 . An information processing system, comprising:

at least one processor; and

at least one memory device storing instructions which, when executed by the at least one processor, cause the at least one processor to:

acquire an inquiry including one or more pieces of privacy information based on input from a user;

identify each of the one or more pieces of privacy information included in the inquiry;

identify a type of privacy information for each of the one or more pieces of privacy information, using either morphological analysis or based on an output obtained when the inquiry is input to a machine learning model;

replace each of the one or more pieces of privacy information included in the inquiry with masked information different from the one or more pieces of privacy information;

request a language model to create an answer to the inquiry in which each of the one or more pieces of privacy information has been replaced, and acquire the answer from the language model;

replace the masked information included in the acquired answer with each of the one or more pieces of privacy information which has been replaced with the masked information in the inquiry; and

transmit information based on the answer in which the masked information has been replaced to the user.

2 . The information processing system according to claim 1 , wherein the plurality of instructions cause the at least one processor to replace each of the one or more pieces of privacy information included in the inquiry with masked information corresponding to the type of each of the one or more pieces of privacy information.

3 . The information processing system according to claim 2 , wherein the type of the one or more pieces of privacy information includes at least a part of a name, an age, a gender, and a medical history.

4 . The information processing system according to claim 1 , wherein the plurality of instructions cause the at least one processor to store each of the one or more pieces of privacy information in a database in association with the masked information which has replaced a corresponding one of the one or more pieces of privacy information,

wherein the plurality of instructions cause the at least one processor to replace, when the answer includes masked information associated with any of the one or more pieces of privacy information, the masked information with a corresponding one of the one or more pieces of privacy information associated with the masked information.

5 . The information processing system according to claim 1 , wherein the plurality of instructions cause the at least one processor to:

select an age range to which an age of the user belongs from a plurality of age ranges determined in advance when the inquiry includes the age of the user; and

select one of a plurality of ages within the selected age range as a masked age for the age of the user,

wherein the plurality of instructions cause the at least one processor to replace the age of the user included in the inquiry with the masked age for the age of the user.

6 . The information processing system according to claim 5 , wherein the plurality of instructions cause the at least one processor to randomly select one of the plurality of ages within the selected age range as the masked age for the age of the user.

7 . The information processing system according to claim 5 , wherein the plurality of instructions cause the at least one processor to acquire answer basis information based on at least a part of the one or more pieces of privacy information, the answer basis information being any of a plurality of pieces of answer basis information relating to an age range to which the age of the user belongs,

wherein the plurality of instructions cause the at least one processor to request, based on the acquired answer basis information, a language model to create an answer to a question in which each of the one or more pieces of privacy information has been replaced, and acquire the answer from the language model.

8 . The information processing system according to claim 1 , wherein the plurality of instructions cause the at least one processor to replace only the each of the one or more pieces of privacy information included in the inquiry with masked information different from the one or more pieces of privacy information.

9 . The information processing system according to claim 1 ,

wherein the answer comprises a recommendation for an insurance product.

10 . An information processing method, comprising:

acquiring, with at least one processor operating with a memory device in a system, an inquiry including one or more pieces of privacy information based on input from a user;

identifying each of the one or more pieces of privacy information included in the inquiry;

identifying a type of privacy information for each of the one or more pieces of privacy information, using either morphological analysis or based on an output obtained when the inquiry is input to a machine learning model;

replacing, with the at least one processor operating with the memory device in the system, each of the one or more pieces of privacy information included in the inquiry with masked information different from the one or more pieces of privacy information;

requesting, with the at least one processor operating with the memory device in the system, a language model to create an answer to the inquiry in which each of the one or more pieces of privacy information has been replaced, and acquiring the answer from the language model;

replacing, with the at least one processor operating with the memory device in the system, the masked information included in the acquired answer with each of the one or more pieces of privacy information which has been replaced with the masked information in the inquiry; and

transmitting, with the at least one processor operating with the memory device in the system, information based on the answer in which the masked information has been replaced to the user.

11 . A non-transitory computer readable storage medium storing a plurality of instructions, wherein when executed by at least one processor, the plurality of instructions cause the at least one processor to:

acquire an inquiry including one or more pieces of privacy information based on input from a user;

identify each of the one or more pieces of privacy information included in the inquiry;

identify a type of privacy information for each of the one or more pieces of privacy information, using either morphological analysis or based on an output obtained when the inquiry is input to a machine learning model;

replace each of the one or more pieces of privacy information included in the inquiry with masked information different from the one or more pieces of privacy information;

request a language model to create an answer to the inquiry in which each of the one or more pieces of privacy information has been replaced, and acquire the answer from the language model;

replace the masked information included in the acquired answer with each of the one or more pieces of privacy information which has been replaced with the masked information in the inquiry; and

transmit information based on the answer in which the masked information has been replaced to the user.