Granted Patent B2

US 12,406,260 · App. 17/596,419 · Granted Sep 2, 2025

Inventors: Kyosuke Tomoda (Tokyo, JP); Shuhei Ito (Tokyo, JP)

Assignee: RAKUTEN GROUP, INC.

G06Q20/4016G06Q20/3226G06Q20/3274

Abstract

Claims (80)

1. A fraud detection system using a machine learning model for executing predetermined processing when a detection target is detected by using a detection device, the fraud detection system comprising at least one processor configured to:

determine, before the detection target is detected, whether a predetermined action has been performed by a user having a user terminal;

execute, when it is determined that the predetermined action has been performed, fraud detection on the user based on identification information stored in the user terminal, said fraud detection being executed by the machine learning model;

execute, when the detection target is detected, the predetermined processing based on an execution result of the fraud detection;

wherein the detection target is a code displayed on the user terminal,

wherein the detection device is used to detect the code, and is external to the user terminal,

wherein the predetermined action is a display action for displaying the code on the user terminal,

wherein the at least one processor is configured to determine, before the code is detected, whether the display action has been performed,

wherein, when it is determined that the display action has been performed, the at least one processor is configured to execute the fraud detection based on the identification information,

wherein, when the code is detected, the at least one processor is configured to execute the predetermined processing based on the execution result of the fraud detection;

wherein the machine learning model outputs a probability of the code being used by the user;

wherein the machine learning model outputs a fraud detection result, in real time, using the probability as an input;

wherein when fraud is detected, the user is not permitted to enter a facility; and

wherein when fraud is not detected, the user is permitted to enter the facility by opening an entrance gate to the facility.

2. The fraud detection system according to claim 1 , wherein the at least one processor is configured to calculate, based on a predetermined calculation method, a probability that the code displayed on the user terminal is to be used by the user, and

wherein, when it is determined that the display action has been performed, the at least one processor is configured to execute the fraud detection based on the probability.

3. The fraud detection system according to claim 1 ,

wherein the detection device is arranged at a predetermined location,

wherein the at least one processor is configured to:

determine whether the user is at or near the predetermined location;

permit display of the code on the user terminal when it is determined that the user is at or near the predetermined location, and

execute the fraud detection when it is determined that the display action has been performed and when the display of the code is permitted.

4. The fraud detection system according to claim 1 , wherein the at least one processor is configured to permit display of the code on the user terminal when fraud by the user is not confirmed based on the execution result of the fraud detection, and

wherein the at least one processor is configured to execute the fraud detection when it is determined that the display action has been performed.

5. The fraud detection system according to claim 1 ,

wherein the detection device is arranged at a predetermined location,

wherein the at least one processor is configured to determine whether the user is at or near the predetermined location, and

wherein the at least one processor is configured to execute the fraud detection when it is determined that the display action has been performed and it is determined that the user is at or near the predetermined location.

6. The fraud detection system according to claim 1 , wherein the at least one processor is configured to determine whether an orientation or an attitude of the user terminal is a predetermined orientation or a predetermined attitude for causing the detection device to detect the code, and

wherein the at least one processor is configured to execute the fraud detection when it is determined that the display action has been performed and it is determined that the user terminal is in the predetermined orientation or the predetermined attitude.

7. The fraud detection system according to claim 1 , wherein the at least one processor is configured to update the identification information stored in the user terminal when a predetermined update condition is satisfied, and

wherein the at least one processor is configured to execute the fraud detection when the identification information has been updated and it is determined that the predetermined action has been performed.

8. The fraud detection system according to claim 1 , wherein the at least one processor is configured to determine a validity of the fraud detection executed in the past based on a predetermined determination condition, and

wherein the at least one processor is configured to execute the predetermined processing based on the execution result of the fraud detection and a determination result of the validity of the fraud detection.

9. The fraud detection system according to claim 8 ,

wherein the predetermined determination condition is a condition relating to an elapsed time since the fraud detection has been executed in the past, and

wherein the at least one processor is configured to determine the validity based on the elapsed time.

10. The fraud detection system according to claim 8 ,

wherein the predetermined determination condition is a condition relating to a movement distance by the user since the fraud detection has been executed in the past, and

wherein the at least one processor is configured to determine the validity based on the movement distance.

11. The fraud detection system according to claim 8 ,

wherein the detection device is arranged at a predetermined location,

wherein the predetermined determination condition is a condition relating to a distance between the predetermined location and a position of the user terminal at a time when the predetermined action is performed, and

wherein the at least one processor is configured to determine the validity based on the distance.

12. The fraud detection system according to claim 1 ,

wherein the detection target is a code external to the user terminal,

wherein the detection device is used to detect the code, and is included in the user terminal,

wherein the predetermined action is a start action for starting the detection device of the user terminal,

wherein the at least one processor is configured to determine, before the code is detected, whether the start action has been performed,

wherein, when it is determined that the start action has been performed, the at least one processor is configured to execute the fraud detection based on the identification information, and

wherein, when the code is detected, the at least one processor is configured to execute the predetermined processing based on the execution result of the fraud detection.

13. The fraud detection system according to claim 1 ,

wherein the predetermined processing is payment processing, and

wherein, when the detection target is detected, the at least one processor is configured to execute the payment processing based on the execution result of the fraud detection and payment information on the user.

14. A fraud detection method using a machine learning model for executing predetermined processing when a detection target is detected by using a detection device, the fraud detection method comprising:

determining, before the detection target is detected, whether a predetermined action has been performed by a user having a user terminal;

executing, when it is determined that the predetermined action has been performed, fraud detection on the user based on identification information stored in the user terminal, said fraud detection being executed by the machine learning model;

executing, when the detection target is detected, the predetermined processing based on an execution result of the fraud detection;

wherein the detection target is a code displayed on the user terminal,

wherein the detection device is used to detect the code, and is external to the user terminal,

wherein the predetermined action is a display action for displaying the code on the user terminal,

wherein the at least one processor is configured to determine, before the code is detected, whether the display action has been performed,

wherein, when it is determined that the display action has been performed, executing the fraud detection based on the identification information,

wherein, when the code is detected, executing the predetermined processing based on the execution result of the fraud detection;

wherein the machine learning model outputs a probability of the code being used by the user;

wherein the machine learning model outputs a fraud detection result, in real time, using the probability as an input;

wherein when fraud is detected, the user is not permitted to enter a facility; and

wherein when fraud is not detected, the user is permitted to enter the facility by opening an entrance gate to the facility.

15. A non-transitory computer-readable information storage medium for storing a program for causing a computer to execute using a machine learning model, when it is determined that a predetermined action has been performed by a user having a user terminal before a detection target is detected by using a detection device in order to execute predetermined processing, fraud detection on the user based on identification information stored in the user terminal, said fraud detection being executed by the machine learning model;

wherein the detection target is a code displayed on the user terminal,

wherein the detection device is used to detect the code, and is external to the user terminal,

wherein the predetermined action is a display action for displaying the code on the user terminal,

wherein the computer is configured to determine, before the code is detected, whether the display action has been performed,

wherein, when it is determined that the display action has been performed, the computer is configured to execute the fraud detection based on the identification information,

wherein, when the code is detected, the at least one processor is configured to execute the predetermined processing based on the execution result of the fraud detection;

wherein the machine learning model outputs a probability of the code being used by the user;

wherein the machine learning model outputs a fraud detection result, in real time, using the probability as an input;

wherein when fraud is detected, the user is not permitted to enter a facility; and

wherein when fraud is not detected, the user is permitted to enter the facility by opening an entrance gate to the facility.

16. The fraud detection system according to claim 1 , wherein the machine learning model outputs the probability of the code being used by the user based on at least one of a position information on the user terminal, a date or time when the display action is performed, a distance from the user terminal to a facility, or a usage history of the user.

Assignments (1)

Continuity (1)

References Cited (29)