Kakaobank Corp.

Hyeon Seung Kim

Tae Wan Kim

Jong Sun Yoo

Ho Yeol Choi

Tae Ki Ha

Dohyoung Keedi Kim

Yong Uk Kim

Jang Hyun Han

Doo Hwan Im

Sung Hwan Cho

Eun Jin Song

Jung Ho Bae

Kyung Doo Moon

The described technology relates to a method for detecting abnormal transaction data between computing devices in a communication network using valid transaction patterns and a server for performing the same. In one aspect, the method includes receiving, at a data collection processor, from an institution server computer, a plurality of pieces of transaction data communicated between two or more of the plurality of user devices, and determining, at a data processor, at least one piece of valid transaction data from the plurality of pieces of transaction data. The method may also include generating, at the data collection processor, a valid transaction pattern based on the determined valid transaction data. The method may further include detecting, at an abnormal transaction detection processor, an existence of an abnormal transaction data between two or more of the plurality of user devices based on the generated valid transaction pattern.

Method and system for detecting abnormal transaction between computing devices in a communication network using valid transaction pattern

The disclosure relates to a method for providing a scraping-based service. The method for providing a scraping-based service includes: requesting and receiving at least one of scraping rule information defining a series of tasks for obtaining external data; collecting the external data by executing tasks according to the received rule information; and providing service information to a user using the collected external data. According to the disclosure, by providing a scraping service through a client terminal and a remote server in a distributed manner, it is possible to increase efficiency of a scraping task and actively cope with changes in a scraping target.

Method for providing scraping-based service and application for executing the same

A method for recognizing an identification (ID) card of a user terminal using deep learning includes extracting an outline region of the ID card included in an input image using a first neural network model, modifying the ID card image of the image to a reference form using at least a partial value of the extracted outline region, and determining whether the modified ID card image is valid and recognizing text information in the valid ID card image. A recognition rate of the ID card may be increased by modifying an ID card image into a reference form using a trained neural network model.

Method and apparatus for recognizing ID card

Growing community of inventors

Seongnam-si, South Korea

Hyeon Seung Kim