US 11,741,691 B2
Distributed learning method, server and application using identification card recognition model, and identification card recognition method using the same
Ho Yeol Choi, Seongnam-si (KR)
Assigned to KakaoBank Corp., Seongnam-si (KR)
Appl. No. 17/637,904
Filed by KakaoBank Corp., Seongnam-si (KR)
PCT Filed Aug. 20, 2020, PCT No. PCT/KR2020/011112
§ 371(c)(1), (2) Date Feb. 24, 2022,
PCT Pub. No. WO2021/040318, PCT Pub. Date Mar. 4, 2021.
Claims priority of application No. 10-2019-0107628 (KR), filed on Aug. 30, 2019.
Prior Publication US 2022/0270355 A1, Aug. 25, 2022
Int. Cl. G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 30/42 (2022.01)
CPC G06V 10/7747 (2022.01) [G06V 10/82 (2022.01); G06V 30/42 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A distributed learning method of a server managing an ID card recognition model, the distributed learning method comprising:
releasing an ID card recognition model performing at least one convolution operation on an ID card image captured in a user terminal so that the user terminal uses the ID card recognition model;
receiving update information of the ID card recognition model generated according to an ID card recognition result of the released ID card recognition model;
verifying validity by comparing the update information received from the user terminal with a predetermined reference and updating the ID card recognition model using the verified update information; and
re-releasing the updated ID card recognition model to the user terminal,
wherein the receiving the update information of the ID card recognition model comprises:
receiving weight change information of a layer performing the convolution operation as the update information by comparing an output value of the ID card recognition model with the user response, and
wherein the updating the ID card recognition model comprises:
updating the ID card recognition model using the received update information according to a release period of the released or re-released ID card recognition model.