KR-102963928-B1 - PIPELINE TYPE DETECTION LOGIC CONFIGURATION METHOD

KR102963928B1KR 102963928 B1KR102963928 B1KR 102963928B1KR-102963928-B1

Abstract

An embodiment of the present invention provides a pipeline-type detection logic setting method that allows an operator to easily set up detection logic. The pipeline-type detection logic setting method according to an embodiment of the present invention comprises: receiving input for detection components including a detection target, a region of interest for detecting the detection target, an anomaly detection condition for detecting the detection target, and an output method for outputting detection information when the anomaly detection condition is satisfied; displaying blocks corresponding to the detection components in a main setting area; receiving input regarding setting information for the detection components and connection relationships between the blocks through the blocks; generating detection logic according to the setting information and connection relationships between the blocks; and monitoring the detection target according to the detection logic.

Inventors

민보경

Assignees

아이디비 주식회사

Dates

Publication Date: 20260512
Application Date: 20250121
Priority Date: 20240822

Claims (12)

In a method for configuring detection logic in which detection components constituting the detection logic are connected in a pipelined manner, A processor of a computing device receives, through an input/output interface device, a drag input that moves a detection component selected from a list of detection components displayed in an auxiliary setting area of a user interface to a main setting area of the user interface after clicking or touching the component, wherein the detection components include a detection target, an anomaly detection condition for determining whether there is an anomaly from the detection target, and an output method for outputting anomaly detection information when the anomaly detection condition is satisfied; The above processor displays blocks corresponding to the detection components through a display in the main setting area, wherein the blocks include a first block corresponding to the detection target, a second block corresponding to the anomaly detection condition, and a third block corresponding to the output method; The above processor receives setting information for the detection components through a touch or click on the blocks displayed in the main setting area, and receives the connection relationship between the blocks through the input/output interface device through a drag input that connects to a connection point of another block after a click or touch on a connection point of a specific block among the blocks, wherein when a click or touch occurs on the first block, an area of interest to detect the detection target is set through the area of interest setting area of the user interface, and a fourth block corresponding to the area of interest is displayed in the main setting area; The step of the processor generating detection logic corresponding to the detection target, the region of interest, the anomaly detection condition, and the output method according to the connection relationship between the setting information and the blocks; and A pipeline-type detection logic setting method comprising the step of the processor monitoring whether the detection target in the area of interest satisfies the anomaly detection condition according to the detection logic, and outputting the anomaly detection information when the anomaly detection condition is satisfied.
delete
In paragraph 1, The above detection target is a pipelined detection logic setting method including a detection target object or a detection target behavior.
In paragraph 3, A pipeline-type detection logic setting method in which the above-mentioned detection target object includes at least one of a person, vehicle, equipment, environment, smoke, animal, or measuring gauge.
In paragraph 3, The above-mentioned detection target behavior is a pipeline-type detection logic setting method that includes at least one of dangerous behavior or prohibited behavior.
In paragraph 1, The step of receiving configuration information for the above detection components is, A step of selecting at least one camera to acquire an image among the plurality of cameras through the interest region setting area upon clicking or touching the first block; When an image captured by the at least one camera is displayed in the interest region setting area, a step of receiving points corresponding to the outline of the interest region in the image captured by the at least one camera through the interest region setting area; and A pipeline-type detection logic setting method comprising the step of establishing a region of interest by connecting the points in the above image.
In paragraph 1, The above anomaly detection condition is a pipeline-type detection logic setting method including at least one of the detection count of the detection target or the detection time of the detection target.
In paragraph 1, The above output method is a pipeline-type detection logic setting method comprising at least one of transmitting detection information, storing detection information, controlling equipment, controlling output devices, or transmitting mobile messages.
In paragraph 1, The above detection component is a pipeline-type detection logic setting method that further includes measurement information by a sensor.
In Paragraph 9, A pipeline-type detection logic setting method including whether the anomaly detection condition for the above measurement information exceeds a threshold for the measurement data by the sensor.
In Paragraph 9, The anomaly detection condition for the above measurement information includes an anomaly model for the measurement data by the sensor and learning information for the anomaly model, and The above learning information is a method for setting pipelined detection logic including a learning period and a threshold.
In Paragraph 9, The above anomaly detection condition is a pipeline-type detection logic setting method in which the detection target is detected in the region of interest of an image captured by a camera and the measurement information by the sensor is combined.

Description

Pipeline Type Detection Logic Configuration Method The present invention relates to a method for setting pipeline-type detection logic to detect whether an anomaly has occurred at a specific location. In manufacturing plants, production processes are carried out by dozens to hundreds of pieces of equipment, and plant managers must record and manage data for each piece of equipment to ensure that products are produced according to objectives. With the recent advancements in data processing and communication technologies, smart factory technology is being introduced to manage manufacturing processes by aggregating data from sensors equipped on each piece of equipment. Smart factories can increase production efficiency and also prevent safety accidents in manufacturing plants. To prevent safety accidents in manufacturing plants, measurement data collected by various sensors installed in the plant and video data captured by cameras can be utilized. Managers can use these various measurement and video data to monitor for hazardous situations or the occurrence of accidents within the manufacturing plant. With the recent advancement of artificial intelligence technology, solutions are being introduced to automatically monitor for hazardous situations or accidents and execute response measures. Managers must configure the solution's detection logic to detect hazardous situations or accidents in accordance with the manufacturing plant's situation and needs. However, it is often difficult for ordinary workers, who lack knowledge of individual solution configuration methods or programming, to set up this detection logic. Figure 1 illustrates the schematic configuration of a system for anomaly detection. FIG. 2 illustrates the configuration of a computing device that performs a detection logic setting method according to the present invention. FIG. 3 is a flowchart illustrating a detection logic setting method according to the present invention. Figure 4 illustrates an example of an interface for setting detection logic. Figure 5 illustrates another example of an interface for setting detection logic. Figure 6 illustrates an example of a case where an abnormal situation is reported via a chatbot based on the abnormal detection results. Figure 7 illustrates an example of a scenario for providing danger area access and warning services. Figure 8 illustrates an example of a scenario for providing a rescue request service through sound. Figure 9 illustrates an example of a scenario for detecting a fire at a construction site using a sensor and a camera together. Figure 10 illustrates an example of a scenario for detecting the collapse of a barrier at a construction site using a sensor. Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. The present invention may be embodied in various different forms and is not limited to the embodiments described herein. To clearly explain the present invention, parts unrelated to the explanation have been omitted, and the same reference numerals are used for identical or similar components throughout the specification. In addition, in various embodiments, components having the same configuration are described using the same reference numerals only in the representative embodiment, and in other embodiments, only configurations different from the representative embodiment are described. Throughout the specification, when a part is described as being "connected (or combined)" with another part, this includes not only cases where they are "directly connected (or combined)" but also cases where they are "indirectly connected (or combined)" with other members in between. Furthermore, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. 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, a method for setting detection logic according to the present invention is described. The method for setting detection logic according to the present invention can be executed through a software program for anomaly detection in an environment such as a manufacturing plant or a public place. The software program can be executed by a computing device (e.g., a desktop computer, a laptop computer, a tablet PC, or a smartphone). In this document, the place where anomaly detection is performed may