IP Library Granted Patent US 12,373,530
Granted Patent B2
US 12,373,530 · App. 18/519,076 · Granted Jul 29, 2025

Method for authenticating user for eKYC automation

Inventors: Sungho Son (Seoul, KR); Juri Seo (Namyangju-si, KR)
Assignee: Fullstack Inc.
G06F21/32G06V30/10
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 12,373,530
App. No.
18/519,076
Granted
Jul 29, 2025
Kind
B2
Abstract

A method for authenticating a user, which is performed by at least one processor, includes obtaining an image an identity (ID) card, assigning a parameter score to at least one parameter included in the image of the ID card, assigning an accuracy score to the at least one parameter extracted through character recognition, based on the image of the ID card, setting a first weight for the parameter score and a second weight for the accuracy score, setting a weight related to a priority for the at least one parameter, and calculating an authentication score based on the parameter score, the accuracy score, the first weight, the second weight, and the weight related to the priority.

Claims (37)

1. A method for authenticating a user, which is performed by

at least one processor, the method comprising:

obtaining an image of an identity (ID) card;

assigning a parameter score to at least one parameter included in the image of the ID card;

assigning an accuracy score to the at least one parameter extracted through character recognition, based on the image of the ID card;

setting a first weight for the parameter score and a second weight for the accuracy score; setting a weight related to a priority for the at least one parameter; and calculating an authentication score based on the parameter score, the accuracy score, the first weight, the second weight, and the weight related to the priority; and

wherein the assigning of the parameter score includes: comparing a result extracted through the character recognition based on the image of the ID card with the at least one parameter;

assigning a first value to the parameter score when a parameter included in the at least one parameter is included in the extracted result and a second value to the parameter score when the parameter included in the at least one parameter is not included in the extracted result; and

further comprising: obtaining a user input value for the at least one parameter, wherein the assigning of the parameter score includes:

comparing the extracted result with the user input value with respect to the at least one parameter; multiplying the parameter score by a third value when the extracted result is equal to the user input value and the parameter score by a fourth value when the extracted result is different from the user input value.

2. The method of claim 1 , wherein the assigning of the accuracy score includes: setting a reliability score for the character recognition for the at least one parameter as the accuracy score; and setting an average of a plurality of reliability scores as a reliability score for one parameter when the plurality of reliability scores are provided for the one parameter.

3. The method of claim 1 , wherein the first weight is higher than the second weight.

4. The method of claim 1 , wherein the setting of the weight related to the priority includes: classifying parameters included in the at least one parameter into a first group related to user authentication and a second group related to verification of the ID card; setting a first group weight for the first group and a second group weight for the second group; setting a weight for each of parameters included in the first group, such that a sum of the weights of the parameters included in the first group is equal to the first group weight; and setting a weight for each of parameters included in the second group, such that a sum of the weights of the parameters included in second first group is equal to the second group weight.

5. The method of claim 4 , wherein the first group weight is greater than the second group weight, and wherein a weight of one parameter included in the second group is set to be equal to or less than a threshold value.

6. The method of claim 4 , wherein the weight of each parameter included in the first group is set as a value that the first group weight divided by the number of parameters included in the first group.

7. The method of claim 1 , wherein the at least one parameter includes: at least one of a name, a date of birth, an ID card number, an ID type, an expiration date, an issue date, a gender, and a nationality.

8. The method of claim 4 , wherein the first weight, the second weight, the first group weight, and the second group weight are set through an artificial intelligence (AI) model.

9. The method of claim 1 , further comprising: authenticating an identify of a user corresponding to the image of the ID card, when the authentication score is equal to or greater than an authentication reference value.

10. A non-transitory computer program recorded in a computer-readable medium to execute the method for authenticating a user, which is performed by at least one processor, the method comprising:

obtaining an image of an identity (ID) card; assigning a parameter score to at least one parameter included in the image of the ID card;

assigning an accuracy score to the at least one parameter extracted through character recognition, based on the image of the ID card;

setting a first weight for the parameter score and a second weight for the accuracy score; setting a weight related to a priority for the at least one parameter; and

calculating an authentication score based on the parameter score, the accuracy score, the first weight, the second weight, and the weight related to the priority; and

wherein the assigning of the parameter score includes:

comparing a result extracted through the character recognition based on the image of the ID card with the at least one parameter; assigning a first value to the parameter score when a parameter included in the at least one parameter is included in the extracted result and a second value to the parameter score when the parameter included in the at least one parameter is not included in the extracted result; and further comprising:

obtaining a user input value for the at least one parameter, wherein the assigning of the parameter score includes: comparing the extracted result with the user input value with respect to the at least one parameter;

multiplying the parameter score by a third value when the extracted result is equal to the user input value and the parameter score by a fourth value when the extracted result is different from the user input value.

11. A method for authenticating a user, which is performed by at least one processor, the method comprising:

obtaining an image of an identity (ID) card;

assigning a parameter score to at least one parameter included in the image of the ID card; assigning an accuracy score to the at least one parameter extracted through character recognition, based on the image of the ID card;

setting a first weight for the parameter score and a second weight for the accuracy score; setting a weight related to a priority for the at least one parameter; and

calculating an authentication score based on the parameter score, the accuracy score, the first weight, the second weight, and the weight related to the priority; and

wherein the assigning of the parameter score includes: comparing a result extracted through the character recognition based on the image of the ID card with the at least one parameter;

assigning a first value to the parameter score when a parameter included in the at least one parameter is included in the extracted result and a second value to the parameter score when the parameter included in the at least one parameter is not included in the extracted result; and

wherein the assigning of the parameter score includes:

multiplying the parameter score by a first multiple value when the parameter included in the at least one parameter is related to verification by the government and the parameter score by a second multiple value smaller than the first multiple value when the parameter is related to a bar code or a region to be read by a machine; and

setting a reference value as the parameter score when the parameter score is greater than the reference value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 27, 2023
From: SON, SUNGHO; SEO, JURI
To: FULLSTACK INC.
Reel/Frame 065661/0305 →
Priority Claims (1)
KR 10-2023-0156193 · Nov 13, 2023 · national
Continuity (1)
Related Publication 20250156512A1 · May 15, 2025
References Cited (18)
US 9798871B2 · Suh · 2017 [cited by examiner]
US 10772675B2 · Whitcher · 2020 [cited by examiner]
US 11139976B2 · Khan · 2021 [cited by examiner]
US 11303631B1 · Alexanian · 2022 [cited by examiner]
US 11681817B2 · Kadiyala · 2023 [cited by examiner]
US 11888849B1 · Slowiak · 2024 [cited by examiner]
US 11924200B1 · Bergano · 2024 [cited by examiner]
US 20190251239A1 · Kim · 2019 [cited by examiner]
US 20210124919A1 · Balakrishnan · 2021 [cited by examiner]
US 20210273804A1 · Khan · 2021 [cited by examiner]
US 20210365292A1 · K S · 2021 [cited by examiner]
US 20230026228A1 · Robinson-Morgan · 2023 [cited by examiner]
KR 102303754B1 · 2021 [cited by applicant]
KR 102363940B1 · 2022 [cited by applicant]
KR 1020220032146A · 2022 [cited by applicant]
KR 1020220086998A · 2022 [cited by applicant]
KR 102408528B1 · 2022 [cited by applicant]
KR 102410588B1 · 2022 [cited by applicant]