KR102271556B1 - Method, device and system for controlling fire monitoring of construction site - Google Patents

Abstract

The present invention relates to a method for controlling fire monitoring at a construction site, which is executed by a device. The method includes: a step of acquiring work information for construction site fire monitoring from an administrator terminal; a step of transmitting the work information to user terminals; a step of acquiring information on work participants to participate in the work from the user terminals; a step of applying the work information and the work participant information to artificial intelligence to output supervisors selected based on work section-specific risk and the proficiency of the work participants and sections in charge assigned to the supervisors; and a step of checking the sections in charge assigned to the supervisors and transmitting guide information on a first section in charge as the section in charge of a first supervisor to a first user terminal. The work information includes a difficulty level set by construction site section and an accident case that has occurred by construction site section. The work participant information includes a monitoring work career and a preferred work field.

Description

Control method, device and system for fire monitoring at construction site {METHOD, DEVICE AND SYSTEM FOR CONTROLLING FIRE MONITORING OF CONSTRUCTION SITE}

The embodiments below relate to a technique for allocating a supervisor for each work zone in order to control fire monitoring at a construction site.

At the construction site, inspectors for fire monitoring at the construction site are working at the site, and inspectors are put into the construction site to monitor compliance with safety and fire regulations according to the checklist for each process and construction.

When inspectors put on the scene monitor fire regulations, they take pictures of safety equipment such as fire extinguishers and facilities with fires with their smartphones or cameras, and use the captured photos to create a report. Inserting it into a document, etc.

However, even at the same construction site, it is difficult to allocate a suitable supervisor for each zone because the target to be checked for each zone is different and the level of risk is also different for each zone.

In particular, since the process is different depending on the type of facility, building, and building at the construction site, it is necessary to check the appropriate fire monitoring target and safety equipment. There is a problem that fire monitoring is not performed accurately because there are many.

Therefore, there is a demand for research and development on a technology that can increase the accuracy of fire monitoring work by selecting supervisors suitable for performing fire monitoring for each work area of a construction site.

According to one embodiment, by applying the work information for fire monitoring at the construction site and the information of the work participants who will participate in the work to artificial intelligence, each of the monitors and the supervisors selected through the risk level for each work area and the skill level of the work participants Its purpose is to provide a control method, apparatus and system for fire monitoring of a construction site that outputs assigned area of responsibility.

Objects of the present invention are not limited to the objects mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, there is provided a method for controlling fire monitoring of a construction site, performed by an apparatus, the method comprising: obtaining work information for fire monitoring of a construction site from a manager terminal; transmitting the job information to user terminals; obtaining information of task participants to participate in the task from the user terminals; applying the work information and the information of the work participants to artificial intelligence, and outputting the supervisors selected through the level of risk for each work area and the skill level of the work participants and the area assigned to each of the supervisors; and checking the area in charge assigned to each of the supervisors, and transmitting guide information for the first area in charge, which is the area in charge of the first supervisor, to the first user terminal, wherein the work information is of the construction site. A control method for monitoring a fire at a construction site is provided, including a difficulty set for each zone and an accident case that occurred for each zone of the construction site, and the information of the work participants includes a monitoring work experience and a preferred work field.

The control method for monitoring a fire at the construction site includes: when a detection signal for wearing the hard hat is received from a detection sensor attached to the hard hat of the first monitor, determining that the first monitor has started work; determining whether the first supervisor has arrived at the first area in charge by obtaining the location information of the first user terminal when it is determined that the first supervisor has started the operation; if it is determined that the first supervisor has arrived at the first covered area, transmitting a check list for the first covered area to the first user terminal; When a first check target that is any one of the check list is selected and the first check target is photographed through a camera attached to the hard hat of the first monitor, image information generated by shooting the first check target obtaining a; And based on the analysis result of the image information, it may further include the step of calculating the risk of fire in the first area in charge.

The control method for monitoring a fire at the construction site may include: when a fire risk for the first area in charge is confirmed to be greater than or equal to a predefined reference value, transmitting a safety equipment confirmation notification message to the first user terminal; When it is confirmed that the first safety equipment is placed in an appropriate position through the manual included in the safety equipment confirmation notification message, the first safety equipment is sent from the first user terminal that has recognized the first safety equipment as an electronic tag. receiving a confirmation result; and confirming whether the first safety equipment is normally disposed and stored in the first responsible area based on the result of checking the first safety equipment.

The control method for monitoring a fire at the construction site includes: acquiring a first measured value measured through an environmental sensor attached to the first safety equipment; when it is determined that the first measured value is out of a predefined reference range, checking an average measured value of the first covered area; and generating a correction value based on a difference between the average measured value and the first measured value, and updating the fire risk level for the first area in charge through the correction value.

The control method for monitoring a fire at the construction site includes: acquiring account information of a first monitor logged into the first user terminal; By applying the account information of the first monitor and the information of the task participants to artificial intelligence, the display order of the first task waiters - the task participants who are not selected as watchers from among the task participants - and the first task waiters outputting the output and transmitting it to the first user terminal; obtaining the location information of the first user terminal, and determining whether the first monitor has entered the waiting area connected to the first area in charge; When it is determined that the first supervisor has entered the waiting area, the display order of the second task waiters - the task participants determined to be in the waiting area among the first task waiters - and the second task waiters are output to transmit to the first user terminal; obtaining, through the account information of the first monitor, whether or not the contact information of the participant who performed the task with the first monitor is stored; When the contact information of the task participant who performed the task with the first monitor is stored, the third task waiters—the second task waiters, the task participant and task participant information who proceeded with the task with the first monitor among the task waiters outputting a display order of the task participants determined to be similar according to a predefined criterion - and the third task waiters, and transmitting the display order to the first user terminal; and if the contact information of the task participant who performed the task with the first monitor is not stored, the fourth task waiters—the task participant and the task participant who performed the task together with the first monitor among the second task waiters The method may further include outputting a display order of task participants whose information is not similar according to a predefined criterion—and the fourth task waiting list, and transmitting it to the first user terminal.

According to one embodiment, by applying the work information for fire monitoring at the construction site and the information of the work participants who will participate in the work to artificial intelligence, each of the monitors and the supervisors selected through the risk level for each work area and the skill level of the work participants By outputting the assigned area in charge, there is an effect that can increase the accuracy of the fire monitoring work by selecting appropriate supervisors for performing fire monitoring for each work area of the construction site.

On the other hand, effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

1 is an exemplary diagram of a configuration of a system according to an embodiment.
2 is a view for explaining an operation for controlling a fire monitoring at a construction site according to an embodiment.
FIG. 3 is a diagram for explaining a process of calculating a risk of fire in a first area in charge according to an exemplary embodiment.
4 is a view for explaining a process of confirming whether safety equipment is normally disposed and stored according to an embodiment.
5 is a diagram for explaining a process of updating a fire risk level using a measurement value measured by an environmental sensor according to an exemplary embodiment.
6 is a view for explaining a process of outputting the task waiters and the display order of the task waiters according to an embodiment.
7 is a diagram for explaining learning of an artificial neural network according to an embodiment.
8 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The terms used in the examples are used for description purposes only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

The embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, wearable devices, and the like.

1 is an exemplary diagram of a configuration of a system according to an embodiment.

A system according to an embodiment may include the device 100 , the manager terminal 110 , and a plurality of user terminals 120 , 130 , 140 , and 150 . The device 100 , the manager terminal 110 , and the plurality of user terminals 120 , 130 , 140 , and 150 may be connected to a network to exchange data through wired/wireless communication. The system can announce the work to be done information, and it is possible to select and assign supervisors who are responsible for each area of the construction site.

The device 100 may be an own server owned by a person or an organization that provides services using the device 100 , may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 100 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The device 100 may include at least one artificial neural network that performs an inference function. The device 100 may be configured to communicate with the manager terminal 110 and the plurality of user terminals 120 , 130 , 140 , and 150 by wire or wireless.

The manager terminal 110 may be a desktop computer, a notebook computer, a tablet, a smart phone, or the like. For example, as shown in FIG. 1 , the manager terminal 110 may be a desktop, and may be employed differently according to embodiments. The manager terminal 110 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The manager terminal 110 may be configured to communicate with the device 100 and the plurality of user terminals 120 , 130 , 140 , and 150 through wired or wireless communication.

The manager terminal 110 uses the device 100 to access a web page operated by a person or organization that provides a service, or an application developed and distributed by a person or organization that provides a service using the device 100 . can be installed. The manager terminal 110 may be linked with the device 100 through a web page or an application.

The manager account 111 logged in to the manager terminal 110 may be maintained in a logged-in state in a web page or an application in the manager terminal 110 . When logged in through the administrator account 111 , the web page or application may include functions for uploading job information, modifying job information, managing job participants, and the like.

The plurality of user terminals 120 , 130 , 140 , 150 may be a desktop computer, a notebook computer, a tablet, a smart phone, or the like. Preferably, as shown in FIG. 1 , the first user terminal 120 , the second user terminal 130 , the third user terminal 140 , and the fourth user terminal 150 may be smartphones, and according to embodiments, may be employed otherwise. The plurality of user terminals 120 , 130 , 140 , and 150 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The plurality of user terminals 120 , 130 , 140 , and 150 may be configured to communicate with the device 100 and the manager terminal 110 by wire or wireless.

The plurality of user terminals 120 , 130 , 140 , and 150 are a person who provides a service using the device 100 , or a person who accesses a web page operated by an organization, or a person who provides a service using the device 100 . Applications developed and distributed by organizations or organizations may be installed. The plurality of user terminals 120 , 130 , 140 , and 150 may interact with the device 100 through a web page or an application.

A user account logged into each of the plurality of user terminals 120, 130, 140, and 150 may be maintained in a logged-in state in a web page or an application. Specifically, the first user account 121 logged in to the first user terminal 120 , the second user account 131 logged in to the second user terminal 130 , and the third logged in to the third user terminal 140 . 3 When the user account 141, the fourth user account 151 logged in to the fourth user terminal 150, etc. are logged in through each user terminal, the web page or application checks work information, checks the area in charge, It may include functions for requesting a work partner between work participants.

The device 100 is a manager account 111 that logs in to a webpage or an application through the manager terminal 110 through wired/wireless communication with the manager terminal 110 and the plurality of user terminals 120 , 130 , 140 , and 150 . ) and a first user account 121, a second user account 131, a third user account 141, and a fourth user account logged in through each of the plurality of user terminals 120, 130, 140, 150 ( 151) and data can be exchanged. The device 100 may notify information about work scheduled to be carried out, and may select and assign supervisors in charge for each area of the construction site.

Meanwhile, for convenience of explanation, only one manager terminal 110 and four user terminals 120, 130, 140, and 150 are illustrated in FIG. 1, but the number of terminals may vary according to embodiments. As long as the processing capacity of the apparatus 100 allows, the number of terminals is not particularly limited.

Hereinafter, embodiments will be described focusing on the operation of the device 100, and the embodiments are not limited by the subject or aspect of communication, and various application examples may be employed.

According to one embodiment, the company operating the device 100 is a company that safely monitors the construction site of the construction company, and observers are put into the construction site to comply with safety and fire regulations according to a predetermined checklist for each process and each construction. You can monitor whether At this time, training of supervisors is required. For example, when about 400 fire guards are put into the construction site, not only monitoring the construction site, but also safety monitoring appropriate for each facility, building, and building because the process is different. You can create guidelines to train supervisors, and send supervisors to conduct safety monitoring on construction sites.

In particular, the device 100 may provide a web page and an application specialized for fire monitoring, and may provide a checklist for checking fire monitoring to the supervisors.

The device 100 may provide a platform and application for increasing the monitoring work efficiency and accuracy of the supervisors, and through this, it is possible to provide a check list necessary for monitoring work, and to provide services such as commuting management, education management, etc. .

The device 100 may analyze accident cases to determine the degree of risk in order to place the supervisors at an appropriate location at the construction site, and may arrange the monitors according to the degree of risk, and deep learning technology may be applied in the process of arranging the supervisors. . A detailed description related thereto will be described later with reference to FIG. 2 .

The device 100 may manage whether to start work based on a sensor attached to the helmet, and monitor the risk of fire in real time based on an image captured by a camera. A detailed description related thereto will be described later with reference to FIG. 3 .

The device 100 may provide a safety equipment confirmation notification based on the risk of fire at the construction site when performing fire monitoring, and the electronic tag method is utilized to determine whether safety prevention such as a fire extinguisher is placed in an appropriate location. It can be used and stored according to the manual for each safety device. A detailed description related thereto will be described later with reference to FIG. 4 .

The device 100 may process various information related to fire to be displayed on the plurality of user terminals 120 , 130 , 140 , and 150 through a measurement value measured through an environmental sensor attached to the safety device, and measure Based on the pattern of values, the fire risk can be determined. A detailed description related thereto will be described later with reference to FIG. 5 .

2 is a view for explaining an operation for controlling a fire monitoring at a construction site according to an embodiment.

First, in step S201 , the device 100 may obtain work information for monitoring a fire at a construction site from the manager terminal 110 .

According to an embodiment, the construction site may mean various sites such as facilities, buildings, and buildings, and the work is put into the construction site and monitored for compliance with fire regulations according to a predetermined checklist for each process and each construction. may mean, and the work information may include basic work information, difficulty set for each zone of the construction site, and accident cases that occurred for each zone of the construction site.

When a button is clicked through a web page or an application in the manager terminal 110 , the device 100 may generate and provide a pop-up window. The pop-up window may be provided to receive basic job information such as job name, job date and time, job location, and job summary from the manager account 111 to be uploaded.

The device 100 may acquire a level of difficulty set for each zone of the construction site. Here, the difficulty level may be determined according to the location of the monitoring area, the type and number of confirmation objects to be checked, and the like. The device 100 may acquire the difficulty level through information input to the manager terminal 110 , and may obtain the difficulty level through information stored in the database. The device 100 may automatically set the difficulty of the corresponding zone through the number of accidents, the number of casualties, and the size of the accident based on the accident cases that occurred for each zone of the construction site.

The device 100 may acquire an accident case that occurred for each zone of the construction site. Here, the accident case may include information on the number of accidents, the number of casualties, and the size of the accident. The device 100 may acquire an accident case through information input to the manager terminal 110 , and may acquire an accident case through information stored in a database.

In step S202 , the device 100 may transmit job information to the plurality of user terminals 120 , 130 , 140 , and 150 .

The device 100 may provide a job information display area to a web page or application to be displayed on each of the plurality of user terminals 120 , 130 , 140 , 150 , and basic information of jobs known through the corresponding area, construction It is possible to display the level of difficulty set for each zone of the site, and accident cases that occurred for each zone of the construction site.

The job information display area may display names, dates, places, outlines, etc. of all known jobs for each zone. The device 100 may display work information registered in a web page or application in a thumbnail manner, and may further display a representative image, a work name, a date, an object to be checked, and the like for each area of the construction site in a table. When the representative image is clicked, the device 100 may provide a job participation application page and a detailed information page of the work area.

In step S203 , the device 100 may obtain information on the task participants to participate in the task from the plurality of user terminals 120 , 130 , 140 , and 150 .

The task participants may be users using the first user account 121 , the second user account 131 , the third user account 141 , the fourth user account 151 , and the like. The information of the job participants may include surveillance work experience and preferred field of work.

In step S204 , the device 100 may apply the job information and the job participants information to AI.

Specifically, the device 100 may include a pre-learned first artificial intelligence (a first artificial neural network). The first artificial neural network receives the work information and the work participants' information, selects the monitors who are judged to be suitable for the work area based on the risk level for each work area and the skill level of the work participants, and assigns a responsible area to each of the selected supervisors can be learned to infer what to do. A specific learning operation of the first artificial neural network will be described later with reference to FIG. 7 .

In step S205 , the device 100 may output the supervisors selected through the level of risk for each work section and the skill level of the work participants and the area assigned to each of the supervisors.

According to an embodiment, the risk level for each work section may be determined through the difficulty and accident cases included in the work information, and the skill level of the work participants may be determined through the monitoring work experience and the preferred work field included in the information of the work participants. .

In step S205 , the device 100 may check the area in charge assigned to each of the supervisors, and transmit guide information on the area in charge to the user terminal used by the supervisor of the area in charge.

For example, when a user using the first user account 121 is selected as a first supervisor for performing a monitoring task for the first area of responsibility and the first supervisor is assigned a first area of responsibility, the device 100 ) may transmit guide information about the first area in charge of the first monitor to the first user terminal 120 .

FIG. 3 is a diagram for explaining a process of calculating a risk of fire occurrence in a first area in charge according to an exemplary embodiment.

First, in step S301 , the device 100 may maintain a standby state for receiving a detection signal.

Specifically, the device 100 may receive a detection signal from a detection sensor attached to the helmet. The detection sensor is installed inside the helmet, detects that the helmet is worn by the user through pressure, may generate a detection signal when the helmet is worn, and transmit the generated detection signal to the device 100 . The detection sensor may directly transmit a detection signal to the device 100, and when the detection sensor and the first user terminal 120 are connected through short-range wireless communication, the detection signal is transmitted to the device ( 100) can be transmitted.

In step S302, the device 100 may determine whether the first monitor has started the operation according to whether the detection signal is received. When the first monitor wears the hard hat and a detection signal for wearing the hard hat is received from the detection sensor attached to the first supervisor's hard hat, the device 100 may determine that the first monitor has started the work.

If it is determined in step S302 that the first monitor does not start the operation, returning to step S301, the device 100 may continue to maintain a standby state for receiving the detection signal.

If it is determined in step S302 that the first monitor has started the operation, in step S303 , the device 100 may acquire location information of the first user terminal 120 . The device 100 may obtain the location information of the first user terminal 120 in real time or periodically, and through the location of the first user terminal 120 , The location may be inferred, and by tracking the location of the first supervisor, it may be confirmed whether the first supervisor has moved to the first area assigned to the supervisor.

In step S304 , the device 100 may determine whether the first supervisor has arrived at the first area in charge through the location information of the first user terminal 120 .

If it is determined in step S304 that the first supervisor has not arrived in the first area in charge, return to step S303, the device 100 continues to acquire the location information of the first user terminal 120, and the location of the first supervisor can be tracked.

If it is determined in step S304 that the first supervisor has arrived at the first coverage area, in step S305 , the device 100 may transmit a check list for the first coverage area to the first user terminal 120 .

The apparatus 100 may store and manage a check list set for each area in charge in a database, and a target to be checked for each area in charge may be set differently. For example, the check list for the first responsible area includes the first confirmation object, the second confirmation object, and the third confirmation object as objects to be checked, and the check list for the second coverage area includes the third confirmation object; The fourth and fifth verification targets may be included as targets to be checked.

According to an embodiment, the check target may mean a facility, equipment, etc. in which a fire occurs, and when a fire risk level is set for each check target, the device 100 is arranged in the order of the high fire risk. You can create a checklist for your area.

In step S306 , the device 100 may receive, from the first user terminal 120 , selection information on the first check target, which is any one of the check list for the first coverage area.

In step S307 , when the photographing of the first object to be checked is performed through the camera attached to the hard hat of the first supervisor, the device 100 may acquire image information generated by the photographing of the first object to be checked.

Specifically, the camera attached to the helmet of the first supervisor and the first user terminal 120 are connected through short-range wireless communication, and a check list for the first area in charge is displayed on the screen of the first user terminal 120 . Then, when the first check target is selected from the check list for the first area in charge, image information generated through a camera attached to the helmet of the first supervisor may be displayed on a part of the screen of the first user terminal 120 . . When the camera attached to the hard hat of the first supervisor illuminates the area with the first confirmation target and the shooting button displayed on a part of the screen of the first user terminal 120 is selected, the camera attached to the hard hat of the first supervisor is the second 1 Shooting can be performed on the area to be checked. The camera attached to the helmet of the first monitor may directly transmit image information generated by the shooting of the first check target to the device 100, and transmit the image information through the first user terminal 120 connected through short-range wireless communication. may be transmitted to the device 100 .

In step S308 , the device 100 may calculate the risk of fire in the first area in charge based on the analysis result of the image information.

Specifically, a plurality of marks (eg, text, figures, etc.) are attached to the periphery of the first confirmation object, and the device 100 obtains image information in which the first confirmation object and the marks are photographed together. By calculating a distance between the first confirmation object and the marks, it may be determined whether the first confirmation object is disposed at a preset position.

When it is determined that the first check target is disposed at a preset position, the device 100 may calculate a fire risk for the first area in charge of which the first check target is located as 0 points, and the first check target If it is determined that the location is deviated from the preset location, the fire risk for the first area in charge may be calculated as a high score according to a distance where the first check target deviated from the preset location.

That is, the device 100 may calculate the risk of occurrence of a fire in the first area in charge by checking the location of the first check target.

When the first check target, the second check target, the third check target, etc. are located in the first responsible area, the device 100 sums up the fire risk calculated through the location check of each check target, It is possible to estimate the risk of fire occurrence for the area in charge.

4 is a view for explaining a process of confirming whether safety equipment is normally disposed and stored according to an embodiment.

First, in step S401 , the device 100 may calculate a fire risk for the first area in charge. For example, the device 100 may calculate the risk of occurrence of a fire in the first area in charge by checking the location of the first check target.

In step S402 , the device 100 may determine whether the fire risk for the first area is greater than a predefined reference value. Here, the reference value may be set differently for each area in charge, and may be set by the manager terminal 110 or the device 100 .

If it is determined in step S402 that the fire risk for the first area is greater than or equal to a predefined reference value, in step S403 , the device 100 may transmit a safety equipment confirmation notification message to the first user terminal 120 . Here, the safety equipment confirmation notification message is a message informing that it is necessary to check the safety equipment disposed in the first responsible area, and may include a manual for arrangement and storage of the safety equipments arranged in the first responsible area.

In step S404 , the device 100 may receive a confirmation result for the first safety equipment from the first user terminal 120 .

Specifically, the first supervisor using the first user terminal 120 can check whether the first safety equipment is placed and stored at an appropriate location through the manual included in the safety equipment confirmation notification message, and the first safety equipment When it is confirmed that the equipment is disposed at an appropriate location, the first user terminal 120 may recognize the first safety equipment through the electronic tag. When the first user terminal 120 recognizes the first safety equipment through the electronic tag, the device 100 may receive a result of checking the first safety equipment from the first user terminal 120 .

In step S405 , the device 100 may determine whether the first safety equipment is normally disposed and stored in the first responsible area based on the result of checking the first safety equipment.

When the device 100 receives the confirmation result for the first safety equipment, since it is confirmed that the first safety equipment is normally arranged and stored in the first area in charge, it is placed in the first area in which the first safety equipment is disposed. It can be recalculated by updating the fire hazard level to a low score.

5 is a diagram for explaining a process of updating a fire risk level using a measurement value measured by an environmental sensor according to an exemplary embodiment.

First, in step S501 , the device 100 may acquire a first measured value measured through an environmental sensor attached to the first safety equipment.

Specifically, an environmental sensor such as a temperature sensor, a humidity sensor, a smoke sensor, and a gas sensor may be attached to the first safety equipment, and the device 100 may acquire a first measured value measured through the environmental sensor. The environmental sensor may directly transmit the first measurement value to the device 100 , and when the environmental sensor and the first user terminal 120 are connected through short-range wireless communication, the first measurement is performed through the first user terminal 120 . The value may be transmitted to the device 100 .

In step S502 , the device 100 may determine whether the first measured value is out of a reference range. Here, the reference range may be set differently for each area in charge, and the reference range may be set to temperature, humidity, whether smoke is generated, whether gas is generated, etc. according to the type of the environmental sensor, and the manager terminal 110 or the device ( 100) can be set.

For example, when the first measured value is a temperature value, the device 100 determines whether the first measured value is out of a reference range of the temperature value, and when the first measured value is a humidity value, the first measured value It is determined whether the value is outside a reference range of the humidity value, and if the first measured value is a measured value indicating smoke generation, it is determined whether the first measured value is a value indicating smoke generation, and the first measured value is In the case of a measurement value indicating gas generation, it may be determined whether the first measurement value is a value indicating gas generation.

If it is determined in step S502 that the first measured value is out of the predefined reference range, in step S503 , the device 100 may check the average measured value of the first covered area.

The device 100 may store and manage the average measured value for each area in charge in the database, and may obtain and confirm the average measured value of the first area in charge from the database.

In operation S504 , the device 100 may generate a correction value based on a difference between the average measured value and the first measured value. For example, when the average measured value is a temperature value of 20 degrees and the first measured value is a temperature value of 30 degrees, the apparatus 100 may generate a correction value based on a difference of 10 degrees.

In step S505 , the device 100 may update the fire risk level for the first area in charge through the correction value.

The device 100 may generate a higher correction value as the difference between the average measured value and the first measured value is greater, and may recalculate by updating the fire risk for the first responsible area to a high score through the correction value. have.

6 is a view for explaining a process of outputting the task waiters and the display order of the task waiters according to an embodiment.

First, in step S601 , the device 100 may obtain account information of the first monitor logged into the first user terminal 120 .

The device 100 checks the first user account 121 logged in to the first user terminal 120 , and the user using the first user account 121 as a first monitor for monitoring the first area in charge. If selected, it is possible to obtain account information of the first monitor. Here, the account information may include information on the monitoring work experience of the first supervisor and the work participant who performed the task with the first supervisor.

In step S602, the device 100 applies the account information of the first monitor and the information of the task participants to the artificial intelligence, and outputs the display order of the first task waiters and the first task waiters to the first user terminal 120 can be sent to

Specifically, the device 100 may include a pre-trained second artificial intelligence (second artificial neural network). The second artificial neural network receives the account information of the first monitor and the information of the remaining task participants except for the first monitor, selects the task waiters who are determined to perform the task together with the first monitor, and performs the tasks with the selected task waiters. Together, they can be trained to infer which ranks they wish to work with. A specific learning operation of the second artificial neural network will be described later with reference to FIG. 7 .

According to an embodiment, the first task waiters may mean task participants who are not selected as watchers from among the task participants. The second artificial neural network may comprehensively infer the monitoring work experience of the first monitor and the monitoring work experience and preferred work field of the job participants, and output the first job waiters and the job desired rank with them. The job desired order with the first job waiters may be a display order of the first job waiters.

The first user terminal 120 may receive and obtain the output of the first artificial intelligence from the device 100 , and may display information of the first job waiters in a display order according to the output. Through this, the first monitor using the first user terminal 120 can check the task waiters determined to be highly likely to perform the task with them in order.

In step S603 , the device 100 may obtain location information of the first user terminal 120 . The device 100 may infer the location of the first supervisor who possesses the first user terminal 120 through the location of the first user terminal 120 , and tracks the location of the first supervisor so that the first supervisor 1 You can check whether you have moved into the waiting area connected to the area in charge.

In step S604 , the device 100 may determine whether the first monitor has entered the waiting area connected to the first area in charge through the location information of the first user terminal 120 .

If it is determined in step S604 that the first supervisor has not entered the waiting area connected to the first responsible area, the process returns to step S603, the device 100 continues to acquire the location information of the first user terminal 120, the first You can track the location of the watcher.

If it is determined in step S604 that the first supervisor has entered the waiting area connected to the first responsible area, in step S605, the device 100 outputs the display order of the second task waiters and the second task waiters to the first user terminal It can be transmitted to (120).

According to an embodiment, the second task waiters may mean task participants determined to be in the waiting area connected to the first responsible area among the first task waiters. In order to determine whether the second task waiters have entered the waiting area, the device 100 obtains location information of the remaining user terminals other than the first user terminal 120, and determines whether each of the task waiters has entered the waiting area. can be discerned. The device 100 may select the first task waiters determined to be in the waiting area connected to the first responsible area as the second task waiters.

According to an embodiment, the device 100 may transmit a notification message guiding movement to the waiting area connected to the first responsible area to each user terminal used by the first job waiters, and check the corresponding notification message. When the first job waiting person who wants to perform the monitoring operation for the first responsible area moves to the waiting area connected to the first responsible area, the first job waiting person who has moved to the waiting area may be selected as the second job waiting person.

When the output of the display order of the second task waiters and the second task waiters is received from the device 100, the first user terminal 120 may display the information of the second task waiters in order according to the desired task order. have.

Through this, the first monitor using the first user terminal 120 works in the waiting area connected to the first responsible area among the first task waiters who are considered to want the work together according to the inference of the second artificial intelligence. It is possible to quickly check the second task waiters who are the participants.

In step S606, the device 100, through the account information of the first monitor, checks whether there is a participant in the task who proceeded with the task with the first watcher, and determines that there is a participant in the task who proceeded with the task with the first monitor. If confirmed, it is possible to obtain whether the contact information of the confirmed work participant has been saved.

For example, if a user using the second user account 131 is identified as a task participant who performed the task with the first watcher, the device 100 displays the user's phone number using the second user account 131 . is stored in the contact application of the first user terminal 120, when the business card of the user using the second user account 131 is photographed by the camera application of the first user terminal 120, the first user account 121 ), check if the second user account 131 is added as an interested participant in the web page or application, and whether the contact information of the participant who worked with the first supervisor is saved. whether it is possible to obtain

In step S607, the device 100 may determine whether the contact information of the work participant who performed the work together with the first monitor is stored.

If the contact information of the task participant who performed the task with the first monitor in step S607 is stored, in step S608, the device 100 outputs the display order of the third task waiters and the third task waiters to the first user It can be transmitted to the terminal 120 .

According to an embodiment, the third task waiters may refer to task participants determined to be similar according to a predefined criterion in which the task participant and task participant information who proceeded with the task with the first monitor among the second task waiters. .

If the contact information of the task participant who performed the task with the first monitor in step S607 is not stored, in step S609, the device 100 outputs the display order of the fourth task waiters and the fourth task waiters to the first It can be transmitted to the user terminal 120 .

According to an embodiment, the fourth task waiters may mean task participants who are determined to be dissimilar to the task participants and task participants who have performed the task with the first monitor among the second task waiters according to a predefined criterion. can

In order to select the third task waiters and the fourth task waiters, the apparatus 100 may include a pre-trained third artificial intelligence (third artificial neural network). The third artificial neural network includes information on the first user account 121, which is the account of the first monitor, and the information of the second user account 131 that has performed the task together with the rest of the information other than the second user account 131 among those waiting for the second task. By receiving the information of the accounts, the user using the second user account 131 and the task participants considered similar according to a predefined criterion are selected, and the user using the second user account 131 and the predefined criteria are selected. It may be learned to select task participants considered to be dissimilar according to a criterion, and to infer a preference rank of the first user account 121 for each of the selected task participants. A specific learning operation of the third artificial neural network will be described later with reference to FIG. 7 .

According to an embodiment, the predefined criteria are information of the second user account 131 that performed the work with the first monitor using the first user account 121 and the second user account among the second task waiters. As the information of the third user account 141 and the fourth user account 151, which are accounts other than 131, is similar, the remaining accounts other than the second user account 131 are more similar than the second user account 131. This may be a criterion for judging it. The third artificial intelligence synthesizes the information of the second user account 131, information of the remaining accounts other than the second user account 131 among the second task waiters, and the similarity between task participants according to a predefined criterion. By inferring, it is possible to select the third task waiters and the fourth task waiters, and output the preference rankings of the third task waiters and the fourth task waiters. The preference order of the third task waiters and the fourth task waiters of the first user account 121 may be a display order of the third task waiters and the fourth task waiters.

Through this, when the first monitor using the first user account 121 is satisfied after working together and stores the contact information of the user using the second user account 131, the second user account 131 You can receive additional recommendations for task participants similar to the user who uses , and if you are dissatisfied and do not save the contact of the user who uses the second user account 131 after working together, the second user account 131 Task participants who are not similar to the users who use the .

According to an embodiment, the first supervisor is a main worker who performs a task on behalf of the first responsible area, and the operator selected through the third task waiters and the fourth task waiter is a sub worker assisting the first supervisor. can

7 is a diagram for explaining learning of an artificial neural network according to an embodiment.

The artificial neural network may be a component included in the device 100 and may be learned through the device 100 or a separate learning device.

The first artificial neural network receives the work information and the work participants' information, selects the monitors who are judged to be suitable for the work area based on the risk level for each work area and the skill level of the work participants, and assigns a responsible area to each of the selected supervisors Thus, it is possible to output the supervisors and the area assigned to each of the supervisors.

The second artificial neural network receives the account information of the first monitor and the information of the remaining task participants except for the first monitor, selects the task waiters who are determined to perform the task together with the first monitor, and performs the tasks with the selected task waiters. You can output the ranks you wish to work with.

The third artificial neural network includes information on the first user account 121, which is the account of the first monitor, and the information of the second user account 131 that has performed the task together with the rest of the information other than the second user account 131 among the second task waiters. By receiving the information of the accounts, the user using the second user account 131 and the task participants considered similar according to a predefined criterion are selected, and the user using the second user account 131 and the predefined criteria are selected. Task participants considered to be dissimilar according to the criteria may be selected, and a preference ranking of the first user account 121 for each selected task participant may be output.

Hereinafter, a process of learning the artificial neural network through the learning device will be described.

First, in step S701, the learning apparatus may obtain training data and a label.

For learning of the first artificial neural network, the learning apparatus may acquire, as training data, a data set including information on each task and information of supervisors participating in a task at the same risk level for each task zone. In addition, the learning apparatus may obtain a list of the supervisors who performed the task by participating in the actual task, and a survey result of satisfaction for each task as a label corresponding to each training data.

For learning of the second artificial neural network, the learning apparatus may obtain, as training data, a data set including information of each task participant and information of the remaining task participants participating in the same task as each task participant. In addition, the learning apparatus may obtain a list of task participants who actually performed the task by participating in the task, and a survey result of satisfaction for each task performance, as a label corresponding to each training data.

For learning of the third artificial neural network, the learning device includes information on the second user account 131 that performed the task with the first monitor and the second user account 131 among the second task participants. It is possible to obtain the information of the work participants as each training data. In addition, in the learning device, after the first observer participates in the work and actually works with the user who uses the second user account 131 , the result of the survey of satisfaction and the user who uses the second user account 131 and After performing the work together, a list of task participants participating in the progressed task and a survey result of satisfaction for each task may be obtained as a label corresponding to each training data.

In step S702, the learning apparatus may generate an input of the artificial neural network from the training data.

The learning apparatus may use the training data as it is as an input of the artificial neural network, or may generate an input of the artificial neural network after a normal process of removing unnecessary information from each training data.

In step S703, the learning apparatus may apply the input to the artificial neural network.

The artificial neural network included in the device 100 may be an artificial neural network that is learned according to supervised learning. The artificial neural network may be a convolutional neural network (CNN) or recurrent neural network (RNN) structure suitable for learning through supervised learning.

In step S704, the learning apparatus may obtain an output from the artificial neural network.

The output of the first artificial neural network may be an inference about the supervisors determined to be suitable for the work area based on the risk level for each work area and the proficiency of the work participants and the area in charge of each of the supervisors. Specifically, the first artificial neural network learns a pattern determined to be suitable for the work area through the risk level for each work area and the skill level of the work participants, selects monitors for each work area, and assigns a responsible area to each of the selected supervisors can be printed out.

The output of the second artificial neural network may be an inference of task participants who are likely to wish to perform the task with the first observer, and the desired rank of task with them. Specifically, the second artificial neural network learns a pattern according to changes in the monitoring work experience of the first supervisor, the monitoring work experience of the job participants, and the preferred work field, and outputs the first job waiters and the job desired ranking with them. can do.

The output of the third artificial neural network is a list of task participants considered to be similar according to predefined criteria to the user using the second user account 131 who performed the task with the first supervisor, the second user account that performed the task ( 131) and a list of task participants considered not to be similar according to a predefined criterion and a preference ranking of the first observer for each list may be inferred. The predefined criteria are the information of the second user account 131 that has worked with the first monitor using the first user account 121 and the rest other than the second user account 131 among the second task waiters. As the information of the third user account 141 and the fourth user account 151 that are accounts is similar, the remaining accounts other than the second user account 131 may be a criterion for determining that they are more similar than the second user account 131 . .

The third artificial neural network synthesizes the information of the second user account 131, information of the remaining accounts other than the second user account 131 among the second task waiters, and the similarity between task participants according to a predefined criterion. By inferring, it is possible to select the third task waiters and the fourth task waiters, and output the preference rankings of the third task waiters and the fourth task waiters.

In step S705, the learning device may compare the output with the label. The process of comparing the output of the artificial neural network corresponding to inference and the label corresponding to the correct answer may be performed by calculating a loss function. As the loss function, a known mean squared error (MSE), cross entropy error (CEE), etc. may be used. However, the present invention is not limited thereto, and loss functions used in various artificial neural network models may be used if the deviation, error, or difference between the output of the artificial neural network and the label can be measured.

In step S706 , the learning apparatus may optimize the artificial neural network based on the comparison value. The learning apparatus can gradually match the output of the artificial neural network corresponding to inference and the label corresponding to the correct answer by updating the weights of the nodes of the artificial neural network so that the comparison value becomes smaller and smaller, and through this, the artificial neural network can be optimized to output an inference close to the correct answer. Specifically, the learning apparatus may optimize the artificial neural network by repeating the process of resetting the weight of the artificial neural network so that the loss function corresponding to the comparison value approaches the estimated value of the minimum value. A known backpropagation algorithm, stochastic gradient descent, etc. may be used for optimization of an artificial neural network. However, the present invention is not limited thereto, and a weight optimization algorithm used in various neural network models may be used.

The learning apparatus may train the artificial neural network by repeating such a process.

Through this, the supervisors judged to be suitable for the work area are selected based on the level of risk for each work area and the proficiency of the work participants, and the area in charge is assigned to each of the selected supervisors, and the supervisor and the area assigned to each of the supervisors. It is possible to train the first artificial neural network to output . The first artificial neural network may be used to output the monitors selected for each work zone and the area assigned to each of the monitors.

In addition, it is possible to train a second artificial neural network that selects the task waiters determined to perform the task together with the first monitor, and outputs a ranking desired to perform the task with the selected task waiters. The second artificial neural network may be used to output a list of first task waiters and a display order of the first task waiters, and a list of second task waiters and a display order of the second task waiters.

In addition, the first user account 121, which is the account of the first observer, and the user using the second user account 131 who performed the task together with the user and the task participants considered to be similar according to a predefined criterion are selected, A second method for selecting task participants who are not similar to the user using the user account 131 according to a predefined criterion, and outputting a preference ranking of the first user account 121 for each selected task participant 3 Artificial neural networks can be trained. The third artificial neural network may be used to output a list of the third task waiters and the fourth task waiters and their display order.

8 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

According to one embodiment, the device 100 includes a processor 101 and a memory 102 . The processor 101 may include at least one of the devices described above with reference to FIGS. 1 to 7 , or perform at least one method described above with reference to FIGS. 1 to 7 . A person or organization using the apparatus 100 may provide a service related to some or all of the methods described above with reference to FIGS. 1 to 7 .

The memory 102 may store information related to the methods described above or may store a program implementing the methods described above. Memory 102 may be volatile memory or non-volatile memory.

The processor 101 may execute a program and control the apparatus 100 . The code of the program executed by the processor 101 may be stored in the memory 102 . The device 100 may be connected to an external device (eg, a personal computer or a network) through an input/output device (not shown), and may exchange data through wired/wireless communication.

The apparatus 100 may be used to train an artificial neural network or to use a learned artificial neural network. Memory 102 may include a learning or learned artificial neural network. The processor 101 may learn or execute an artificial neural network algorithm stored in the memory 102 . The apparatus 100 for learning an artificial neural network and the apparatus 100 for using the learned artificial neural network may be the same or may be separate.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and carry out program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (3)

A method for controlling fire monitoring of a construction site, performed by an apparatus (100), comprising:
obtaining work information for fire monitoring of a construction site from the manager terminal 110;
transmitting the job information to user terminals (120, 130, 140, 150);
obtaining information of task participants to participate in the task from the user terminals (120, 130, 140, 150);
applying the work information and the information of the work participants to artificial intelligence, outputting the supervisors selected through the risk level for each work area and the skill level of the work participants and the area assigned to each of the supervisors;
checking the area in charge assigned to each of the supervisors, and transmitting guide information about the area in charge of the first supervisor to the first user terminal 120;
When a detection signal for wearing the helmet is received from a detection sensor attached to the helmet of the first monitor, determining that the first monitor has started work;
determining whether the first monitor has arrived at the first area in charge by obtaining the location information of the first user terminal 120 when it is determined that the first supervisor has started the operation;
transmitting a check list for the first coverage area to the first user terminal 120 when it is determined that the first supervisor has arrived at the first coverage area;
When a first check target, which is any one of the checklists, is selected and the first check target is photographed through a camera attached to the hard hat of the first monitor, image information generated by shooting the first check target obtaining a;
estimating a fire risk for the first area in charge based on the analysis result of the image information;
transmitting a safety equipment confirmation notification message to the first user terminal 120 when the fire risk for the first area is determined to be greater than or equal to a predefined reference value;
When it is confirmed that the first safety equipment is placed in an appropriate position through the manual included in the safety equipment confirmation notification message, the first safety equipment is sent from the first user terminal 120 that recognizes the first safety equipment as an electronic tag. receiving a verification result for the equipment;
confirming whether the first safety equipment is normally disposed and stored in the first responsible area based on a result of checking the first safety equipment; and
When it is confirmed that the first safety equipment is normally arranged and stored in the first area in charge, updating the fire risk for the first area in charge to a low score and recalculating it;
The work information includes a difficulty set for each area of the construction site and an accident case that occurred for each area of the construction site,
wherein the information of the job participants includes surveillance work experience and preferred field of work;
Control methods for fire monitoring on construction sites. delete delete

Images