KR102672273B1 - The method of fire prevention in traditional market - Google Patents

Abstract

The present invention relates to a fire prevention method in a traditional market that is installed in a traditional market and monitors human objects entering after closing or takes safety measures in the event of a fire flame. More specifically, the present invention relates to a fire prevention method in a traditional market installed in a traditional market. A surveillance step of filming the inside of a traditional market through at least one camera; In the processing unit connected to the camera, when it is determined through the monitoring step that the object wanders for more than a set time or a fire flame is detected in the same place or a specific place, location information about the same place or a specific place is generated and at least one Robot preparation step for transmitting to a representative robot; A robot dispatch step in which the robot moves to the same place or a specific place based on the received location information; and a robot response step of taking response measures against the object or the fire flame through the robot that has moved to the same place or a specific place.

Description

Fire prevention method in traditional markets{THE METHOD OF FIRE PREVENTION IN TRADITIONAL MARKET}

The present invention relates to a fire prevention method in a traditional market, and in particular, a fire prevention method in a traditional market installed in a traditional market to monitor objects such as people entering after closing or to take safety measures in the event of a fire spark. It's about.

Traditional markets are precious places that preserve our culture and traditions, and are lively places where numerous merchants and consumers come and go. However, traditional markets face an environment in which it is difficult to conduct fire prevention and surveillance at night. Because night markets are sparsely populated or almost empty of people, early detection and response may be delayed in the event of a fire, which poses the risk that it could escalate into a large-scale fire.

Additionally, because traditional markets are densely populated areas, there may be cases where suspicious people enter the market and commit malicious acts such as arson. To date, it has been difficult to respond to these issues due to the lack of security-related measures inside traditional markets, and problems are being raised that fire prevention and response are even more difficult due to irregular structures and outdated facilities.

Therefore, there is a need to develop an automated system to solve these problems and effectively prevent and respond to fires in traditional markets.

(0001) Domestic Patent Publication No. 10-0787971

The technical problem that the present invention seeks to solve is to effectively detect and respond to fires in a nighttime environment, and to take rapid and accurate safety measures for potentially dangerous situations using artificial intelligence and robot technology, The goal is to provide fire prevention methods in traditional markets that can solve the challenges of fire prevention and safety management.

Another technical problem that the present invention aims to solve is to solve problems with fire prevention and safety management at night in traditional traditional markets, and to ensure the safety of consumers and merchants by enabling a quick and accurate response in the event of a fire. The goal is to provide fire prevention methods in the market.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

The present inventor's fire prevention method in a traditional market to achieve the above technical problem is a fire prevention method in a traditional market that is installed in a traditional market and monitors objects, such as people entering after closing, or takes safety measures in the event of a fire flame. Regarding, a surveillance step of filming the inside of a traditional market through at least one camera placed in the traditional market; In the processing unit connected to the camera, when it is determined through the monitoring step that the object wanders for more than a set time or a fire flame is detected in the same place or a specific place, location information about the same place or a specific place is generated and at least one Robot preparation step for transmitting to a representative robot; A robot dispatch step in which the robot moves to the same place or a specific place based on the received location information; and a robot response step of taking response measures against the object or the fire flame through the robot that has moved to the same location or a specific location.

In addition, if it is determined through the monitoring step that the object has wandered in the same place or a specific place for more than a set time, the robot generates a warning signal for the object in the robot response step.

In addition, the method further includes a robot photographing step of photographing the object through a camera installed on the robot.

In addition, if it is determined that a fire flame has occurred inside the traditional market through the monitoring step, in the robot response step, the robot is characterized in that it sprays fire extinguishing fluid to the place where the fire flame occurred.

In addition, if it is determined that a fire flame has occurred inside a traditional market through the monitoring step, a fire reporting step is further performed in which the processing unit connected to the camera generates location information about the same place or a specific place and transmits it to the relevant organization. It is characterized by including.

In addition, when the object moves to another location within the traditional market, the location information is updated and the updated location information is retransmitted to the robot.

In addition, when there are multiple identical locations or specific locations, in the robot dispatch step, at least one robot moves to the multiple identical locations or specific locations according to the set order.

In addition, the processing unit is connected to a server, and the server stores a large number of fire occurrence images and wandering image data of objects associated with abnormal behavior, and includes a deep learning model for learning a large number of stored image data. do.

The above aspects of the present invention are only some of the preferred embodiments of the present invention, and various embodiments reflecting the technical features of the present invention will be described in detail below by those skilled in the art. It can be derived and understood based on.

The present invention described above has the following effects.

First, the present invention can perform accurate and rapid fire detection operations by overcoming the difficulties of detecting fires in night markets, especially after closing. For example, deep learning and computer vision technology can be used to detect abnormal behavior of objects, and when abnormal behavior is discovered, a robot can be automatically dispatched to take immediate response measures.

Additionally, if a person is found wandering around a certain location or a specific location for a certain period of time, safety measures can be taken before an accident such as a fire occurs, so accidents can be prevented in advance.

In addition, by responding immediately in the event of a fire, it is possible to prevent a large-scale fire from occurring. Initial fire extinguishing work can be performed through a robot, and information on the location of the fire can be quickly transmitted to the relevant organizations to respond quickly.

In addition, before a suspicious person enters a traditional market and commits a malicious act, the robot detects abnormal human behavior and, if necessary, generates a warning signal to warn the suspicious person, thereby increasing the safety of the traditional market and Safety measures can be taken before an incident occurs.

In addition, the present invention overcomes the limitations of the surveillance system due to lack of manpower by building an automated system by combining artificial intelligence and robot technology, and enables efficient and accurate monitoring and response.

In addition, by effectively performing fire prevention and safety management in traditional markets, the safety of traditional markets can be increased and the safety of consumers and merchants can be guaranteed, thereby improving the image of traditional markets and promoting stable operation.

The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a system configuration diagram according to an embodiment for carrying out the fire prevention method of a traditional traditional market of the present invention;
Figure 2 is a configuration diagram according to an embodiment of the fire prevention method of a traditional market of the present invention.

Hereinafter, some embodiments of the present invention will be described in detail through illustrative drawings. When adding reference numerals to components in each drawing, it should be noted that identical components are given the same reference numerals as much as possible even if they are shown in different drawings. Additionally, when describing embodiments of the present invention, if detailed descriptions of related known configurations or functions are judged to impede understanding of the embodiments of the present invention, the detailed descriptions will be omitted.

Additionally, when describing the components of embodiments of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are only used to distinguish the component from other components, and the nature, order, or order of the component is not limited by the term. When a component is described as being "connected," "coupled," or "connected" to another component, that component may be directly connected or connected to that other component, but there is no "interconnection" between each component. It should be understood that they may be “connected,” “coupled,” or “connected.”

Figure 1 is a system configuration diagram according to an embodiment of the present inventor's fire prevention method for a traditional traditional market, and Figure 2 is a configuration diagram according to an embodiment of the fire prevention method of a traditional traditional market according to the present invention.

The present inventor's fire prevention method in a traditional market is installed in a traditional market to monitor human objects entering after closing or to take safety measures in the event of a fire flame. To this end, the system shown in FIG. 1 is applied. You can proceed as shown in Figure 2.

The fire prevention method in a traditional market according to the present invention includes a monitoring step (S10), a robot preparation step (S20), a location information update step (S30), a robot dispatch step (S40), a robot response step (S50), and a robot shooting step. It may be configured to include a step (S60) and a fire reporting step (S70). Of course, it can be basically configured to include only the monitoring step (S10), the robot preparation step (S20), the robot dispatch step (S40), and the robot response step (S50). However, for convenience of explanation, they will be explained sequentially.

First, the surveillance step (S10) is a step that performs the function of preventing fire and detecting abnormal behavior by filming the inside of a traditional market.

In the monitoring step (S10), the interior of a traditional market can be photographed using at least one camera (10). At this time, filming in a traditional market may occur immediately after it closes or when there are few people around.

The camera 10 can perform the function of collecting data for fire prevention and response by filming the inside of a traditional traditional market. For this purpose, various types of cameras can be used, and multiple cameras can be deployed to film the entire market except the inside of the store or restroom.

For example, infrared (IR) cameras can be used for fire detection in night environments. Infrared cameras can detect heat to identify heat sources (flames, fires) and detect abnormal temperature changes.

Additionally, the camera 10 can be connected to the processing unit 20 and the server 30 and use a network camera to transmit data. Network cameras can transmit video data in real time over the Internet or local network.

Additionally, high-resolution cameras can be used for detailed object detection and recognition. High-resolution cameras can capture video details with high quality, making them useful for accurately analyzing abnormal behavior of objects.

In addition, pan/tilt/zoom (PTZ) cameras and video compression technologies can be used, and the camera 10 can collect data for fire prevention inside traditional markets by utilizing various types of technologies as above. there is.

Next, the processing unit 20 connected to the camera 10 may perform the role of analyzing and processing image data collected from the camera. This allows fire-related objects and abnormal behavior to be identified and required data to be extracted.

The processing unit 20 may include the following components.

First, an image processing unit may be included. The image processing unit may analyze image data collected from the camera 10 and detect abnormal behavior of objects, fire-related situations, etc. To this end, deep learning algorithms and computer vision technology can be used to perform tasks such as object detection, tracking, and classification.

Additionally, deep learning models for object detection and classification may be included. For example, models such as YOLO (You Only Look Once), SSD (Single Shot Multibox Detector), and Faster R-CNN (Region-based Convolutional Neural Networks) can be used to detect and classify fire-related objects.

Additionally, deep learning models to detect abnormal behavior may also be included. For example, a recurrent neural network such as LSTM (Long Short-Term Memory) can be used to learn movement patterns for a specific time and identify abnormal behavior.

Additionally, a function may be included to compress and save the analyzed data (video) or transmit it to a server. Bandwidth and storage space can be managed efficiently by using compression technology that reduces the size of video data.

Additionally, a network communication module can be provided to manage data communication between the camera 10 and the server 30. Video data can be transmitted in real time through a network communication module and necessary information can be received from the server 30.

Additionally, by analyzing video data, information necessary for fire prevention and response can be extracted and stored. The analyzed data can be used in the robot preparation stage (S20) and the robot dispatch stage (S40).

The processing unit 20 can analyze image data collected from the camera 10 in real time through the various components described above and extract information necessary for fire prevention and response.

The server 30 is connected to the processing unit 20 and can store and manage data analyzed by the processing unit 20. The processing unit 20 may be understood as being included in the server 30 or configured separately. The server 30 may be a central processing unit and may be used to efficiently store and manage data related to fire prevention and abnormal behavior occurring within a traditional market.

Server 30 may include the following components.

First, the server 30 may include a data storage device for storing a large amount of data. You can store data using a hard disk drive (HDD) or a high-performance solid state drive (SSD).

Additionally, data can be managed efficiently using a database management system (DBMS). You can build a database to structure data and run queries for search and analysis.

Additionally, the server 30 can analyze and process data received from the processing unit 20. It can also extract information related to abnormal behavior or fire and generate necessary notifications and warnings.

Additionally, a network communication module may be provided to manage data communication with the processing unit 20. The network communication module ensures stable transmission of data and can receive data from the processing unit 20 in real time.

Additionally, a security system is installed in the server 30 to prevent unauthorized access to data from the outside. To this end, security technologies such as encryption, access control, and firewalls can be used to keep data safe.

Additionally, the server 30 can efficiently manage data and periodically back up data to prevent data loss. You can maintain necessary information by setting data retention periods and policies.

Additionally, it may include the ability to share and transmit data with other systems as needed.

In addition, the processing unit 20 is connected to the server 30, and the server 30 stores a large number of fire occurrence images and wandering image data of objects linked to abnormal behavior, and deep learning is used to learn a large number of stored image data. Models may be included. Through this, it is possible to quickly determine abnormal situations through fire occurrence situations and wandering images of objects and take prompt action.

The server 30 can stably store and manage data transmitted from the processing unit 20 through the above components and provide information necessary for fire prevention and response.

The robot preparation step (S20) is performed in the processing unit 20 connected to the camera 10, through the monitoring step (S10), when the object wanders in the same place or a specific place for a set time, for example, 10 seconds or more, or is detected in the same place or a specific place. If it is determined that a fire flame is detected, location information for the same location or a specific location is generated and the generated location information is transmitted to at least one robot 40.

The robot preparation step (S20) is a step in which the robot 40 is prepared to respond when abnormal behavior of an object (a person entering the traditional market) or a situation related to a fire is detected.

The processing unit 20 may analyze the image received through the camera 10, that is, the object detection result, to determine whether abnormal behavior of the object or a situation related to a fire has been detected.

Additionally, it is possible to decide whether to operate the robot 40 based on the object detection results. When abnormal behavior of an object or a fire-related situation is detected, it can be determined whether operation of the robot 40 is necessary.

The robot 40 can be activated in the robot preparation step (S20). The robot 40 can be converted to an operable state so that it can respond quickly in the subsequent response stage.

The robot 40 can receive location information of the place where abnormal behavior of an object or a situation related to a fire occurred through the processing unit 20 and the server 30, and the robot 40 can receive the location information based on the received location information. You can move to the location and take action.

When the robot 40 moves according to location information, it can be configured using various robot technologies and functions. The robot 40 has autonomous driving capabilities and can be configured to move to a designated location or move along a path.

In order for the robot 40 to move according to location information, it can be configured as follows.

First, the robot 40 can be equipped with autonomous driving technology that recognizes the surrounding environment using the camera 10 and sensors and determines its own movement path. To this end, computer vision, LiDAR, and ultrasonic sensors can be used to understand the driving environment and configure the vehicle to move safely while avoiding obstacles.

In addition, the robot 40 uses location tracking technology such as GPS (Global Positioning System) to determine its own location in real time, and uses the location information received from the server 30 and its own location information measured. This allows you to confirm the exact location and configure it to move.

Additionally, the robot 40 can implement an algorithm for planning a movement path based on the received location information. You can move efficiently by selecting the optimal route, and the A* algorithm or Dijkstra algorithm can be used for route planning.

Additionally, the robot 40 may be equipped with motion control technology to determine how to move. By adjusting speed, direction, rotation, etc., it can be configured to move to a designated location accurately and safely.

Additionally, the robot 40 may be equipped with a function to avoid an obstacle and select another route when it detects an obstacle while moving. To this end, sensor data can be analyzed to detect obstacles and run avoidance algorithms to prevent collisions.

Additionally, the robot 40 may be equipped with a function to correct position errors while moving. It can be configured to move to the correct location by correcting in real time to prevent position errors from accumulating.

The function of the robot 40 to move according to location information can be implemented through the above-described technologies and functions, through which the robot 40 can move accurately and safely to a designated location and effectively perform fire prevention and response tasks. You can.

The robot 40 can receive work instructions for responding to an abnormal behavior of an object or a fire from the server 30 and perform appropriate work accordingly. Of course, the robot itself can be configured to perform appropriate tasks according to the set program.

The robot 40 can establish a communication environment in which data can be exchanged in real time with the server 30 through the communication module 44.

The location information updating step (S30) is a step in which the robot 40 updates the location information of the object when the object moves to another location within the traditional market and retransmits the updated location information to the robot 40. The location information updating step (S30) may be performed whenever an object moves.

To this end, the robot 40 can be configured to detect an object through the camera 10 and determine the location information of the object. The location of an object can be relative to its initial location or its last known location. Through this, the robot 40 can continuously detect the movement of the object. Movement of an object may mean that location information is periodically updated or new location information is received.

When the movement of an object is detected, the robot 40 can update the location information and move according to the updated location information. In addition, the new location can be calculated by considering the object's movement path and movement speed, and the exact location can be determined by comparing it with the location information received from the server 30.

The robot 40 may be comprised of a plurality of robots, and if necessary, the location information may be retransmitted to other robots 40 so that all robots 40 within a traditional market share the latest location information. Accordingly, when there are multiple locations or specific locations, at least one robot may move according to a set order for each of the multiple locations or specific locations in the robot dispatch step (S40), which will be described later. At this time, it can be configured to move from a long distance.

Additionally, location error can be managed in the location information updating step (S30). To minimize the position error, a correction algorithm can be implemented and the position information can be updated at regular intervals.

Through the above-described location information update step (S30), the robot 40 accurately determines the location of the object, and when the object moves to another location, the location information can be updated in real time to increase the efficiency of the response task. Fire prevention and response systems in the market can operate more accurately and quickly.

The robot dispatch step (S40) is a step in which the robot 40 moves to the same place or a specific place based on the received location information. The same place is a place where an object (person) wanders for more than a certain period of time, and may be one place. A specific location may be a location vulnerable to fire or a location where a fire flame occurs. The same place and a specific place may be the reference places for generating the initial location information, and the location information may vary depending on the movement of the object.

In the robot dispatch step (S40), the robot 40 can plan the optimal path to the target point to be dispatched. At this time, the robot 40 must avoid obstacles and can select a path to reach the departure point in the shortest time.

The robot 40 can move along the planned dispatch route using the autonomous navigation device 41. Autonomous driving devices can use sensor data to sense the surrounding environment while driving and adjust the driving path to ensure safe dispatch.

When the robot 40 reaches the dispatch point, it can report the dispatch completion status to the server 30.

The robot response step (S50) is a step of taking response measures to an object or fire flame through a robot that has moved to the same location or a specific location, and may include the following procedures.

First, the robot 40 can determine whether a response task should be performed when an abnormal behavior of an object or a fire is detected. To this end, preset rules or algorithms can be used to analyze the situation and determine whether a response is necessary.

If it is determined that response work is necessary, the robot 40 can set a response plan. For example, if it is determined through the monitoring step (S10) that a fire spark has occurred due to a short circuit, etc. inside a traditional traditional market, the robot 40 performs the initial fire extinguishing work using the automatic fire extinguishing liquid injection means 42 to extinguish the fire. can do. The automatic fire extinguishing liquid injection means 42 can be understood as a fire extinguisher, and can be configured to be mounted on the robot 40 and automatically spray toward the fire flame. Since the automatic extinguishing liquid injection means itself is a known technology, detailed description thereof will be omitted.

In addition, if it is determined through the monitoring step (S10) that the object has wandered in the same place or a specific place for more than a set time, the robot 40 can generate a warning signal for the object through the warning device 45.

The warning signal may be implemented as a visual display, such as a flashing warning light or a message on a display, and/or an auditory display, such as a warning sound or a voice guidance. The voice prompt says, “You are being filmed and will be reported if you commit any illegal activity!” You can provide guidance, etc. Warning signals like these can alert people (objects) who enter a traditional traditional market and encourage the objects to voluntarily leave the traditional market. Such a warning signal may be issued as the robot 40 follows the object until the object leaves the traditional market. Through this, accidents such as fire can be prevented in advance.

The robot 40 can perform the necessary actions to perform the corresponding task. When interaction with an object is required using the autonomous driving device 41, a response can be performed by executing an appropriate action and checking the result.

The robot 40 can report (transmit) the response task performance status to the server 30, and through this, the server 30 can monitor the response task status of the robot 40 and issue additional instructions if necessary.

When the robot 40 detects a fire, it can report the fire status to the server 30, and through this, it can quickly respond to the fire.

The robot response step (S50) may include a procedure for allowing the robot 40 to perform an appropriate response to an abnormal behavior of an object or a fire.

Meanwhile, the object can be photographed through the robot photographing step (S60). At least one camera 43 may be disposed on the robot 40. The camera 43 disposed on the robot 40 may be used for the movement of the robot 40, that is, autonomous driving, or may be used to detect objects or fire flames and spray the automatic fire extinguishing liquid injection means 42.

The robot photography step (S60) is a step in which, when the robot detects an abnormal behavior of an object or a fire, the robot photographs the situation and records image data. The robot imaging step (S60) may include the following procedures. The robot imaging step (S60) may be performed whenever the robot 40 moves.

The robot 40 can move to the filming target using the autonomous navigation device 41. During the movement process, the robot 40 can sense the surrounding environment and be controlled to avoid obstacles and safely move to the shooting location.

The robot 40 can perform image shooting at the shooting target point. At this time, the camera 43 mounted on the robot 40 can be used to photograph the location and record the captured image data.

Additionally, the captured image data may be transmitted to the server 30 through the communication module 44 connected to the processing unit 20. Through this, the server 30 can check abnormal behavior or fire conditions of objects and take additional measures as necessary.

The robot imaging step (S60) may include a procedure in which the robot 40 checks for abnormal behavior or fire of an object, captures image data, and transmits it to the server 30.

In addition, in the fire reporting step (S70), if it is determined that a fire flame has occurred inside the traditional traditional market through the monitoring step (S10), the processing unit 20 connected to the camera 10 determines the location of the same place or a specific place. Information can be generated and transmitted to relevant organizations. At this time, if the location information is updated, the updated location information can be transmitted to the relevant organization each time it is generated. The fire reporting step (S70) may be performed at the same time as a fire flame occurs.

In other words, if it is determined that a fire spark, that is, a fire, has occurred through the camera, information about this can be automatically transmitted to related organizations, such as fire departments and police stations.

According to the present invention described above, it is possible to solve problems related to fire prevention and response in traditional traditional markets and to ensure the safety of consumers and merchants by enabling a quick and accurate response in the event of a fire.

In the above, even though all the components constituting the embodiment of the present invention have been described as being combined or operated in combination, the present invention is not necessarily limited to this embodiment. That is, as long as it is within the scope of the purpose of the present invention, all of the components may be operated by selectively combining one or more of them. In addition, terms such as “include,” “comprise,” or “have” described above mean that the corresponding component may be present, unless specifically stated to the contrary, and therefore do not exclude other components. Rather, it should be interpreted as being able to include other components. All terms, including technical or scientific terms, unless otherwise defined, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains. Commonly used terms, such as terms defined in a dictionary, should be interpreted as consistent with the contextual meaning of the related technology, and should not be interpreted in an idealized or overly formal sense unless explicitly defined in the present invention.

The above description is merely an illustrative explanation of the technical idea of the present invention, and various modifications and variations will be possible to those skilled in the art without departing from the essential characteristics of the present invention. Accordingly, the embodiments posted in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these examples. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

10: Camera 20: Processing unit
30: Server 40: Robot
41: autonomous driving device 42: automatic fire extinguishing fluid injection means
43: Camera 44: Communication module
45: Warning device
S10: Monitoring step S20: Robot preparation step
S30: Location information update step S40: Robot dispatch step
S50: Robot response step S60: Robot photography step
S70: Fire reporting phase

Claims (8)

This is about a fire prevention method in a traditional market that is installed in a traditional market and detects objects and fire sparks that enter the market after the market closes at night and takes safety measures against them.
A surveillance step of filming the interior of a traditional market through at least one camera placed in the traditional market;
In the processing unit connected to the camera, if it is determined through the monitoring step that the object is wandering in the same place or a specific place for more than a set time or a fire flame is detected, location information about the same place or a specific place is generated and at least one Robot preparation step for transmitting to a representative robot;
A robot dispatch step in which the robot moves to the same place or a specific place based on the received location information; and
A robot response step of taking response measures against the object or the fire flame through the robot that has moved to the same place or a specific place,
If it is determined through the monitoring step that the object has wandered for more than a set time in the same place or a specific place,
In the robot response step, the robot generates a warning signal for the object,
The warning signal includes a flashing warning light and a voice guidance saying, “You are being filmed, and if you commit an illegal act, you may be reported!”
A fire prevention method in a traditional traditional market in which the robot generates the warning signal while following the object until the object goes outside the traditional market. delete According to claim 1,
A method of preventing fire in a traditional market further comprising a robot photographing step of photographing the object through a camera installed on the robot. According to claim 1,
If it is determined that a fire flame has occurred inside the traditional market through the above monitoring steps,
A fire prevention method in a traditional market in which, in the robot response step, the robot sprays fire extinguishing liquid to the place where the fire flame occurs. According to clause 4,
If it is determined that a fire flame has occurred inside the traditional market through the above monitoring steps,
A fire prevention method in a traditional market further comprising a fire reporting step in which a processing unit connected to the camera generates location information for the same place or a specific place and transmits it to a related organization. According to claim 1,
A method of preventing fire in a traditional market further comprising updating location information about the object when it moves to another location within the traditional market, and retransmitting the updated location information to the robot. According to claim 1,
If the same location or specific location is multiple,
In the robot dispatch step, a fire prevention method in a traditional market in which at least one robot moves to a plurality of the same places or specific places according to the set order. The method according to any one of claims 1 and 3 to 7,
The processing unit is connected to the server,
The server stores a large number of fire occurrence images and wandering image data of objects linked to abnormal behavior, and a fire prevention method in a traditional market that includes a deep learning model for learning a large number of stored image data.