KR102508648B1 - Emergency monitoring method, device and system based on malfunction judgment of electric and firefighting equipment - Google Patents

Abstract

A device according to one embodiment receives basic information including installation location information and equipment information of electrical and firefighting equipment, receives state information of electrical and firefighting equipment from a state measurement sensor installed in the electrical and firefighting equipment, checks the possibility of malfunction of electrical and firefighting equipment based on the state information satisfying predetermined criteria, and checks the possibility of malfunction to transmit at least one of an emergency notification message and an inspection message to a manager terminal.

Description

Emergency situation monitoring method, device and system based on malfunction determination of electrical and firefighting equipment

The following embodiments relate to techniques for monitoring emergency situations based on malfunction determination of electrical and firefighting equipment.

In general, electrical equipment and firefighting equipment must be provided regardless of facilities such as homes, schools, companies, and public institutions. In preparation for emergency situations such as fire, vibration, and flame in the building, the electric light and firefighting equipment is equipped with a notification device to notify the emergency situation.

However, the notification device may malfunction due to moisture, dust, insects, or the like, and a child or worker may mistakenly touch the notification device and cause malfunction. When the notification device operates, the manager who manages the electrical and firefighting equipment must visit the site and determine whether the equipment is malfunctioning and the emergency situation one by one.

Therefore, it is required to develop a technology capable of monitoring an emergency situation based on the malfunction determination of electrical and firefighting equipment.

Republic of Korea Patent Registration No. 10-2410754 (Announcement on June 22, 2022) Republic of Korea Patent Registration No. 10-2116064 (Announced on May 27, 2020) Republic of Korea Patent Registration No. 10-2165207 (Announced on October 13, 2020) Republic of Korea Patent No. 10-2188260 (2020.12.08 announcement)

Embodiments are intended to provide a method for monitoring an emergency situation based on malfunction determination of electrical and firefighting equipment.

Embodiments attempt to check the possibility of a malfunction by using state information from a photographed image of electrical and firefighting equipment and a state measuring sensor.

Embodiments attempt to create an inspection cycle of electrical and fire-fighting equipment by using equipment information and malfunction determination history of electrical and fire-fighting equipment.

According to one embodiment, a method performed by an apparatus includes: receiving basic information including installation location information and equipment information of electrical and firefighting equipment; Receiving state information of the electrical and fire-fighting equipment from a state measurement sensor installed in the electric and fire-fighting equipment; confirming a possibility of a malfunction of the electrical and firefighting equipment based on whether the status information satisfies a predetermined criterion; and checking the possibility of malfunction and transmitting at least one of an emergency notification message and a check message to an administrator terminal.

The step of checking the possibility of a malfunction may include acquiring a first image by photographing the electrical and firefighting equipment for a preset time through a camera installed in the electrical and firefighting equipment, and a second image captured from the first image at normal times. Checking a difference by comparing the difference, extracting a part where the difference occurs, extracting a causal object by performing image analysis on the extracted part, and applying the causal object to an artificial neural network including an image analysis algorithm. Checking the category of the causal object by inputting it, if the category of the causal object matches the risk category stored in the risk category database, state information for a preset period of time based on a point in time when the state information satisfies a predetermined criterion generating as malfunction state information, comparing the malfunction state information with normal state information corresponding to normal state information, generating malfunction weights based on the comparison result, and generating the malfunction weights based on the malfunction weights. Possibility checks may be included.

A method performed by the device, comprising: checking the number of times the state information is determined to be an erroneous operation even though it satisfies a predetermined criterion; Checking the installation elapsed date of the electrical and firefighting equipment using the equipment information; checking the average life expectancy of the electrical and fire protection equipment; generating a risk index of the electrical and fire-fighting equipment using the number of times the malfunction is determined, the elapsed date of installation, and the average life expectancy; and generating an inspection cycle of the electrical and firefighting equipment according to the risk index.

A method performed by the device, comprising: comparing a risk index of the electrical and fire protection equipment with a preset first index; When the risk index is less than the first index, setting a first ratio as a ratio at which an image of the electric and firefighting equipment is displayed on the manager terminal through a camera installed in the electric and firefighting equipment; comparing the risk index with a preset second index when the risk index is greater than or equal to the first index; setting the ratio as a second ratio when the risk index is less than the second index; setting the ratio as a third ratio when the risk index is greater than or equal to the second index; and applying any one of the first ratio, the second ratio, and the third ratio to the captured image of the electricity and firefighting equipment and displaying the image on the screen of the manager terminal.

In the method performed by the device, further comprising the step of setting a possible dispatch probability for a manager, wherein the step of setting the dispatch possible probability includes, when the number of managers who want to participate in the manager is one, Setting the dispatch availability probability to 1 and obtaining manager dispatch information including basic information of managers and dispatch participation history when the number of managers who want to participate in the manager is several, and the manager from the dispatch participation history Extracting the number of dispatch participations, which is the number of times of participation in dispatches, extracting the number of participations for the same cause, which is the number of participations in emergency dispatches of the same cause as the cause of the emergency situation from the dispatch participation history of the manager, the dispatch participation Based on the number of times and the number of participation in the same cause, setting the probability of dispatch in the emergency situation to one of values greater than or equal to 0 and less than 1, and transmitting a guide message about the set probability of dispatch to the manager terminal. can include

An apparatus according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

Embodiments may provide a method for monitoring an emergency situation based on malfunction determination of electrical and firefighting equipment.

Embodiments may check the possibility of a malfunction by using state information from a photographed image of electrical and firefighting equipment and a state measuring sensor.

In embodiments, an inspection cycle of electrical and fire-fighting equipment may be generated by using facility information and malfunction determination history of the electrical and fire-fighting equipment.

1 is a diagram for explaining the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of monitoring an emergency situation based on determining malfunction of electrical and firefighting equipment according to an embodiment.
3 is a flowchart illustrating a process of checking a possibility of malfunction according to an embodiment.
4 is a flowchart illustrating a process of generating an inspection cycle for electrical and firefighting equipment according to an embodiment.
5 is a flowchart illustrating a process of setting a ratio at which images of electrical and firefighting equipment are to be displayed on a manager terminal according to an embodiment.
6 is a flowchart illustrating a process of setting a possible dispatch probability according to an embodiment.
7 is a flowchart illustrating learning of an artificial neural network according to an embodiment.
8 is an exemplary diagram of a configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can 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 changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed 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, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person 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 unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions 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 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 vehicles, kiosks, and wearable devices.

In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, a machine learns and judges on its own. The more the AI system is used, the higher the recognition rate and the more accurately the seller's taste can be understood, so the existing rule-based smart system is gradually being replaced by a deep learning-based AI system.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithm technology that classifies/learns the characteristics of input data by itself, and element technology is a technology that uses machine learning algorithms such as deep learning to mimic functions such as recognition and judgment of the human brain. It consists of technical fields such as understanding, inference/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/characters, including natural language processing, machine translation, dialogue systems, question and answering, voice recognition/synthesis, and the like. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, space understanding, image improvement, and the like. Inference prediction is a technique of reasoning and predicting logically by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology for controlling the autonomous driving of a vehicle and the movement of a robot, and includes motion control (navigation, collision, driving), manipulation control (action control), and the like.

In general, in order to apply machine learning algorithms to real life, learning is performed in a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram for explaining the configuration of a system according to an embodiment.

A system according to an embodiment may include a manager terminal 10 and a device 30 capable of communicating with each other through a communication network.

First, a communication network may be configured regardless of its communication mode, such as wired or wireless, and may be implemented in various forms so that communication between servers and communication between servers and terminals is performed.

The manager terminal 10 may be a terminal used by a manager who manages electrical and firefighting equipment according to the present invention. The manager terminal 10 may be a desktop computer, a laptop computer, a tablet, a smart phone, or the like. For example, as shown in FIG. 1 , the manager terminal 10 may be a smart phone, and may be employed differently depending on embodiments.

The manager terminal 10 may be configured to perform all or part of an arithmetic function, a storage/reference function, an input/output function, and a control function of a normal computer. The manager terminal 10 may be configured to communicate with the device 30 by wire or wireless.

The manager terminal 10 accesses a web page operated by a service provider or organization using the device 30, or an application developed and distributed by a service provider or organization using the device 30. can be installed The manager terminal 10 may interwork with the device 30 through a web page or application.

The manager terminal 10 may access the device 30 through a web page or application provided by the device 30 .

Singular expressions in the claims may be understood to include the plural. For example, an administrator of a claim may refer to one administrator or more than one administrator.

The device 30 may be a server owned by a person or organization that provides services using the device 30, may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 30 may be configured to perform all or part of an arithmetic function, a storage/reference function, an input/output function, and a control function of a typical computer.

The device 30 may be configured to communicate with the manager terminal 10 by wire or wirelessly, control the operation of the manager terminal 10, and control which information is to be displayed on the screen of the manager terminal 10. .

Meanwhile, for convenience of explanation, only the manager terminal 10 is illustrated in FIG. 1 , but the number of terminals may vary according to embodiments. As long as the processing capacity of the device 30 permits, the number of terminals is not particularly limited.

According to one embodiment, a database may be provided in the device 30, but is not limited thereto, and the database may be configured separately from the device 30. Apparatus 30 may include a number of artificial neural networks for performing machine learning algorithms.

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning (ML) is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as recognition and judgment, using machine learning algorithms, can also be understood as artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model derives a correlation between data by extracting and analyzing features from given data, and optimizing the parameters of the neural network model by repeating this process can be referred to as machine learning. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving a regularity between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons that transmit and receive signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can send and receive data according to a convolutional connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost , Perceptron, Genetic Programming, Clustering, etc. may be used.

Of these, CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. A CNN consists of one or several convolution layers and general artificial neural network layers on top, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

2 is a flowchart illustrating a process of monitoring an emergency situation based on determining malfunction of electrical and firefighting equipment according to an embodiment.

Referring to FIG. 2 , first, in step S201, the device 30 may receive basic information on electrical and firefighting equipment. Here, the basic information may include installation location information and facility information of electrical and firefighting equipment, but is not limited thereto.

At this time, the installation location information may include information about the address, location, region, etc. of the point where the electrical and firefighting equipment is installed, and the basic information is about the type, model name, lifespan, installation time and function of the electrical and firefighting equipment. information may be included.

In step S202, the device 30 may receive state information of the electrical and firefighting equipment from the state measuring sensor installed in the electrical and firefighting equipment.

Here, the state measurement sensor may include at least one of a smoke detection sensor, a humidity sensor, a temperature sensor, a camera, a flame detection sensor, and a fire detection sensor, but is not limited thereto.

In step S203, the device 30 may check the possibility of malfunction of the electrical and firefighting equipment based on whether the state information satisfies a predetermined criterion.

Here, the criterion may mean that it is set to determine that the operation of electrical and firefighting equipment is abnormally operated. According to one embodiment, when the state information satisfies a predetermined criterion, the device 30 may determine that an abnormality has occurred in the electrical and firefighting facilities and is operating abnormally.

For example, when the condition measurement sensor includes a humidity sensor, the criterion may mean a specific humidity value. At this time, the device 30 may check the possibility of malfunction of the electrical and firefighting equipment when the state information satisfies a specific humidity value or more.

For example, when the condition measuring sensor includes a temperature sensor, the reference may mean a specific temperature value. At this time, the device 30 may check the possibility of malfunction of the electrical and firefighting equipment when the state information satisfies a specific temperature value or higher.

In step S204, the device 30 may transmit at least one of an emergency notification message and a check message to the manager terminal 10 by checking the possibility of malfunction. At this time, a detailed description of a process for checking the possibility of malfunction will be described later with reference to FIG. 3 .

According to an embodiment, the device 30 checks the possibility of a malfunction and transmits at least one of an emergency notification message informing of an emergency situation or an inspection message requesting facility inspection to the manager terminal 10 according to the malfunction possibility report. can

The apparatus 30 transmits at least one of an emergency message and an inspection message to the manager terminal 10 according to the possibility of malfunction, so that when an abnormality occurs in the state of electrical and firefighting equipment, the manager can efficiently cope with the malfunction according to the possibility of malfunction. can make it

3 is a flowchart illustrating a process of checking a possibility of malfunction according to an embodiment.

Referring to FIG. 3 , first, in step S301, the device 30 may obtain a first image by photographing electrical and fire-fighting equipment for a preset time through a camera installed in the electrical and fire-fighting equipment. At this time, the preset time may be set differently according to embodiments.

In step S302, the device 30 compares the first image with the normally photographed second image to determine the difference.

In step S303, the device 30 may extract a part where a difference occurs.

In step S304, the device 30 may extract a causal object by performing image analysis on the extracted part.

According to an embodiment, the apparatus 30 compares a first image of electricity and firefighting equipment captured for a preset time with a second image taken normally, and detects a portion where a difference between the first image and the second image occurs. It can be extracted, and a causal object can be extracted by performing image analysis on the part where the difference has occurred.

For example, a portion in which a difference between the first image and the second image occurs may be extracted from the first image. The device 30 may extract a causal object by performing image analysis on the image of the extracted part.

In step S305, the device 30 may check the category of the causal object by inputting the causal object to an artificial neural network including an image analysis algorithm. Here, the artificial neural network may include an image analysis algorithm. Here, the artificial neural network may be an algorithm that receives a causal object, a causal category, and a risk category as inputs and outputs a category of the causal object.

The apparatus 30 may identify a category of the causal object for the causal object by analyzing an image of the extracted image for a portion where a difference between the first image and the second image occurs using an artificial neural network.

The artificial neural network may be an artificial neural network pre-trained using a specific image and information indicated by the specific image as learning data, but is not limited thereto.

Here, the device 30 may use an image of an image extracted for a portion where a difference between the first image and the second image occurs as an input value for image analysis performed by the artificial neural network, and after image analysis, the image It can be used as learning data for analysis learning, but is not limited thereto.

For example, based on the output of the artificial neural network, the apparatus 30 may determine that the category of the causal object is the first category when the output value of the artificial neural network is 1, and if the output value of the artificial neural network is 2 , it can be confirmed that the category of the cause object is the second category.

According to an embodiment, the artificial neural network may learn to extract the category of the causal object through a matching result obtained by matching the causal object and the causal category. The artificial neural network may be learned through a method described later with reference to FIG. 7 .

In step S306, if the category of the causative object matches the risk category stored in the risk category database, the device 30 converts the state information for a preset period based on the time point when the state information satisfies a predetermined criterion to the malfunction state information. can be created with

Risk categories may be previously stored in the risk category database of the device 30 . For example, the risk category may include arson, flame, and smoke, but is not limited thereto.

For example, when the category of the causal object is the first category and the risk category of the risk category database of the device 30 is the first category, the device 30 determines the time when the status information satisfies the predetermined criterion. Malfunction status information can be created.

In step S307, the device 30 may compare malfunction state information with normal state information corresponding to normal state information.

In step S308, the device 30 may generate a malfunction weight based on the comparison result. According to an embodiment, as a result of comparing the malfunction state information and the normal state information, the device 30 may generate a higher malfunction weight as the difference between the malfunction state information and the normal state information increases. The smaller the difference is, the lower the malfunction weight can be generated.

In step S309, the device 30 may check the possibility of malfunction based on the malfunction weight.

According to an embodiment, the higher the malfunction weight, the higher the possibility of malfunction, and the lower the malfunction weight, the lower the probability of malfunction.

4 is a flowchart illustrating a process of generating an inspection cycle for electrical and firefighting equipment according to an embodiment.

Referring to FIG. 4 , first, in step S401, the device 30 may check the number of times the state information has satisfied a predetermined criterion but has been determined to be an erroneous operation.

Here, the criterion may mean that it is set to determine that the operation of electrical and firefighting equipment is abnormally operated. According to one embodiment, when the state information satisfies a predetermined criterion, the device 30 may determine that an abnormality has occurred in the electrical and firefighting facilities and is operating abnormally.

That is, the device 30 may check the number of times that the state information satisfies a predetermined criterion, and it is determined that the electrical and firefighting facilities are abnormally operated, but the number of times the operation is determined to be malfunctioning.

In step S402, the device 30 may check the installation elapsed date of the electrical and firefighting equipment using the facility information. The device 30 may check the installation time from facility information, and compare the current time and the installation time to check the installation elapsed date of the electrical and firefighting equipment.

In step S403, the device 30 may check the average life expectancy of electrical and firefighting equipment.

According to an embodiment, the device 30 may determine the lifespan of the electrical and fire-fighting equipment from facility information of the electrical and fire-fighting equipment, and accordingly, the average life expectancy of the electrical and fire-fighting equipment may be determined.

In step S404, the device 30 may generate a risk index of the electrical and firefighting equipment by using the number of times the malfunction is determined, the elapsed installation date, and the average life expectancy.

According to one embodiment, the device 30 may calculate the risk index of the electrical and firefighting equipment by summing the number of times the malfunction is determined, the elapsed days of installation, and the average life expectancy.

In step S405, the device 30 may generate an inspection cycle of electrical and firefighting equipment according to the risk index.

According to one embodiment, the device 30 may generate a shorter inspection cycle of electrical and firefighting equipment as the risk index increases, and may generate a longer inspection cycle of electrical and firefighting equipment as the risk index decreases.

5 is a flowchart illustrating a process of setting a ratio at which images of electrical and firefighting equipment are to be displayed on a manager terminal according to an embodiment.

Referring to FIG. 5 , first, in step S501, the device 30 may compare the risk index of electrical and firefighting equipment with a preset first index. In this case, the first index may be set differently according to embodiments.

In step S502, if the risk index is less than the first index, the device 30 converts the video image taken of the electrical and firefighting equipment through the camera installed in the electrical and firefighting equipment to the manager terminal 10 at a first ratio. can be set

In step S503, when the risk index is greater than or equal to the first index, the device 30 may compare the risk index with a preset second index. In this case, the second index may be set differently according to embodiments.

In step S504, the device 30 may set the ratio as the second ratio when the risk index is less than the second index. Here, the second ratio may be set higher than the first ratio.

That is, when the risk index is greater than or equal to the first index and less than the second index, the device 30 displays the image of the electric and fire-fighting equipment through the camera installed in the electric and fire-fighting equipment on the manager terminal 10. It can be set in 2 ratios.

In step S505, the device 30 may set the ratio as the third ratio when the risk index is greater than or equal to the second index. Here, the third ratio may be set higher than the second ratio.

That is, the device 30 controls the ratio at which the image taken of the electrical and fire-fighting equipment through the camera installed in the electrical and fire-fighting equipment is displayed on the manager terminal 10 when the risk index is equal to or greater than the first index and equal to or greater than the second index. It can be set in 3 ratios.

In step S506, the device 30 may apply any one of the first ratio, the second ratio, and the third ratio to the captured image of electricity and firefighting equipment and display the image on the screen of the manager terminal 10.

6 is a flowchart illustrating a process of setting a possible dispatch probability according to an embodiment.

Referring to FIG. 6 , first, in step S601, the device 30 may determine whether the number of managers to participate is one or several managers. According to one embodiment, the device 30 may check how many administrators wish to participate during a pre-settable period.

In step S602, when the number of managers is one, the device 30 may set the probability of being dispatched to 1.

In step S603, if the number of managers is several, the device 30 may obtain manager dispatch information including basic information and dispatch participation history of managers. Here, the dispatch participation history may include, but is not limited to, information about the place, time, date, and number of dispatch participation in an emergency situation.

In step S604, the device 30 may extract the number of dispatch participation and the same cause participation number from the dispatch participation history.

In this case, the number of dispatch participation may refer to the number of times the user participates in a meeting, and the number of participation for the same cause may mean the number of times the user participates in an emergency dispatch for the same cause as the cause of the emergency.

In step S605, the device 30 may set the manager's possible dispatch probability to one of values greater than or equal to 0 and less than 1, based on the number of dispatch participations and the number of participations in the same cause.

According to an embodiment, when there are several managers, the device 30 may set the dispatch availability probabilities such that the sum of the dispatch availability probabilities set for each manager becomes 1.

In step S606, the device 30 may transmit a guide message about the set possibility of dispatch to the manager terminal 10.

7 is a flowchart illustrating learning of an artificial neural network according to an embodiment.

According to an embodiment, the artificial neural network may include an image analysis algorithm, and may be an algorithm that receives a causal object, a causal category, and a risk category as inputs and outputs a category of the causal object.

The learning device in which the learning of the artificial neural network is performed may be the same device as the device 30 that identifies the category of the causal object using the learned artificial neural network, or may be a separate device. Hereinafter, a process of learning an artificial neural network will be described.

First, in step S701, the learning device may generate an input based on a matching result obtained by matching a causal object and a causal category.

Specifically, the learning device may perform a process of pre-processing a matching result obtained by matching a causal object with a category of the causal object. The preprocessed matching result may be used as an input of the artificial neural network, or an input may be generated through a normal process of removing unnecessary information.

In step S702, the learning device may apply input to the artificial neural network. The artificial neural network may be an artificial neural network that is trained according to reinforcement learning. The artificial neural network may be a Q-Network, a Depp Q-Network (DQN), or a relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

An artificial neural network trained by reinforcement learning may be updated and optimized by reflecting evaluations on various rewards. For example, the compensation value may increase as the causal object and the causal category are selected and extracted.

In step S703, the learning device may obtain an output from the artificial neural network. The output of the artificial neural network may include information about the category of the causal object.

That is, the artificial neural network may output the category of the causal object through a matching result obtained by matching the causal object and the causal category.

In step S704, the learning device may evaluate the output of the artificial neural network and provide a reward.

Specifically, the learning device may award more rewards as the causal object and the causal category are matched and extracted.

In step S705, the learning device may update the artificial neural network based on the evaluation.

Specifically, the learning device is an expected value of the sum of reward values in an environment in which an artificial neural network selects and extracts a causal object and a causal category through a matching result of matching the causal object and the causal category. In order to maximize this, the artificial neural network may be updated through a process of optimizing a policy for determining actions to be taken in specific states.

Meanwhile, the process of optimizing the policy may be performed through a process of estimating the maximum value of the expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function may be performed through stochastic gradient descent (SGD) or the like. The process of optimizing the policy is not limited thereto, and various optimization algorithms used in reinforcement learning may be used.

The learning device may gradually update the artificial neural network by repeating the learning process of the artificial neural network as described above.

8 is an exemplary diagram of a configuration of a device 30 according to an embodiment.

Device 30 according to one embodiment includes a processor 31 and a memory 32 . Device 30 according to an embodiment may be the above-described server or terminal. The processor 31 may include at least one device described above with reference to FIGS. 1 to 7 or may perform at least one method described above with reference to FIGS. 1 to 7 . The memory 32 may store information related to the above method or store a program in which the above method is implemented. Memory 32 may be volatile memory or non-volatile memory.

The processor 31 may execute a program and control the device 30 . Program codes executed by the processor 31 may be stored in the memory 32 . The device 30 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, 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), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a 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 on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. 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.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (3)

In the method performed by the device,
Receiving basic information including installation location information and equipment information of electrical and firefighting equipment;
Receiving state information of the electrical and fire-fighting equipment from a state measurement sensor installed in the electric and fire-fighting equipment;
confirming a possibility of a malfunction of the electrical and firefighting equipment based on whether the status information satisfies a predetermined criterion; and
Checking the possibility of malfunction and transmitting at least one of an emergency notification message and an inspection message to an administrator terminal
including,
The step of confirming the possibility of malfunction is,
Obtaining a first image by photographing the electrical and fire-fighting equipment for a preset time through a camera installed in the electric and fire-fighting equipment;
Comparing the first image with a second image taken normally to determine a difference;
Extracting the part where the difference occurs;
Extracting a causal object by performing image analysis on the extracted part;
inputting the causal object to an artificial neural network including an image analysis algorithm to identify a category of the causal object;
When the category of the causative object matches a risk category stored in a risk category database, generating state information for a preset period of time as malfunction state information based on a point in time when the state information satisfies a predetermined criterion;
Comparing the malfunction state information with the normal state information corresponding to the normal state information;
Generating a malfunction weight based on the comparison result; and
Checking the possibility of malfunction based on the malfunction weight
including,
checking the number of times that the status information satisfies a predetermined criterion but was determined to be an erroneous operation;
Checking the installation elapsed date of the electrical and firefighting equipment using the equipment information;
checking the average life expectancy of the electrical and fire protection equipment;
generating a risk index of the electrical and fire-fighting equipment using the number of times the malfunction is determined, the elapsed date of installation, and the average life expectancy; and
Generating an inspection cycle of the electrical and firefighting equipment according to the risk index
Including more,
Comparing the risk index of the electrical and firefighting equipment with a preset first index;
When the risk index is less than the first index, setting a first ratio as a ratio at which an image of the electric and firefighting equipment is displayed on the manager terminal through a camera installed in the electric and firefighting equipment;
comparing the risk index with a preset second index when the risk index is greater than or equal to the first index;
setting the ratio as a second ratio when the risk index is less than the second index;
setting the ratio as a third ratio when the risk index is greater than or equal to the second index; and
Applying any one of the first ratio, the second ratio, and the third ratio to the image of the electricity and firefighting equipment and displaying the image on the screen of the manager terminal
containing
Emergency situation monitoring method based on malfunction judgment of electrical and firefighting equipment. delete delete

Images