KR-20260065372-A - Abnormal transaction detection method linked to CCTV

Abstract

The present invention relates to an abnormal transaction detection system linked with a CCTV. An abnormal transaction detection method according to one embodiment of the present invention comprises: an image acquisition step in which at least one CCTV is provided in each of at least one offline store and captures and transmits a real-time image within the store; a payment history inquiry step through linkage with payment history; an object detection step in which a person is detected in an image; an image analysis step in which time information of a person is detected is generated; a mapping step in which time information of a person is detected in an image is mapped to time information of a payment history; a mapping result analysis step; and an abnormal transaction detection step in which an abnormal transaction is detected according to the analysis result.

Inventors

• 봉지수

Assignees

• 봉지수

Dates

Publication Date

20260508

Application Date

20241101

Claims (1)

1. An image acquisition step for acquiring real-time images of the store captured by CCTV; Payment history lookup step based on order information purchased by the consumer; Object detection step for generating location information including coordinate values of objects recognized as people; An image analysis step in which the server analyzes the real-time image to obtain the location and detected time information of a person detected; and a mapping step for mapping the detected location and time information and the time information of the payment history retrieved in the payment history inquiry step; A mapping result analysis step that analyzes whether there is information mapped within an error range by comparing the visual information of a person detected in the above image with the visual information of the payment history; An abnormal transaction detection method linked with CCTV, generated through an abnormal transaction detection step that transmits a notification when visual information of the detected image or visual information of the payment history is detected outside the error range according to the analyzed mapping result.

Description

Abnormal transaction detection method linked to CCTV The present invention relates to an abnormal transaction detection technology, and more specifically, to an abnormal transaction detection method linked with CCTV. Video analysis technology has significantly improved in recent years due to advancements in artificial intelligence and machine learning. These technologies are opening up the possibility of detecting abnormal behavior by recognizing and analyzing human actions in CCTV footage. However, since many systems still fail to go beyond simple motion detection or pattern recognition, there are limitations in actually identifying abnormal transactions. FIG. 1 is a schematic flowchart illustrating a store and customer management system through abnormal transaction detection in a store according to the present invention. Hereinafter, the structure and operation of an embodiment of the present invention will be described in detail with reference to the attached drawings. However, the present invention is not intended to be limited to a specific disclosed form, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention. In this application, terms such as "comprising" or "having" are intended to specify the existence of the features, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, steps, actions, components, parts, or combinations thereof. That is, throughout the specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but rather may include additional components. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application. Hereinafter, repetitive descriptions and specific descriptions of known functions and configurations that could unnecessarily obscure the essence of the invention are omitted to ensure that the essence of the invention is not obscured. Embodiments of the invention are provided to more fully explain the invention to those with average knowledge in the art. Accordingly, the shapes and sizes of elements in the drawings may be exaggerated for clearer explanation. FIG. 1 is a schematic flowchart illustrating a store and customer management system through abnormal transaction detection in a store according to the present invention. The drawing illustrates a store and customer management system through abnormal transaction detection in a store, comprising a real-time analysis server that detects abnormal transactions by analyzing the situation inside the store in real time, the module for acquiring real-time images and an image object detection and analysis module within the store captured by a CCTV operating in the store, a payment history inquiry module linked to a payment terminal, a module for mapping the time of an image where a person is detected with the time of payment history, a mapping result analysis module, and an abnormal transaction detection module. The method according to the present invention is characterized by being generated through an image acquisition step of acquiring a real-time image of a store captured by a CCTV, a payment history inquiry step based on order information purchased by a consumer, an object detection step of generating location information including coordinate values of objects recognized as people, an image analysis step in which the server analyzes the real-time image to acquire the location of a detected person and the detected time information, a mapping step of mapping the detected location and time information with the time information of the payment history inquiry step, a mapping result analysis step of analyzing whether there is information mapped within an error range by comparing the time information of the detected person in the image with the time information of the payment history, and an abnormal transaction detection step of transmitting an alert when the time information of the detected image or the time information of the payment history that deviates from the error range is detected according to the analyzed mapping result. Meanwhile, the present invention is not limited to the described embodiments, and it is possible to use it by changing the application area. It is obvious to those skilled in the art that various modifications and variations can be made