KR102141219B1 - Method and apparatus for controlling design and construction process of fire protection equipment - Google Patents

Abstract

Disclosed are a method and apparatus for controlling a design and construction process of firefighting and disaster prevention equipment. A method for controlling a design and construction process of firefighting and disaster prevention equipment according to an embodiment of the present invention, which is based on artificial intelligence, comprises the following steps of: storing a design of a target space scanned by a designer for design of firefighting and disaster prevention equipment; generating a first input signal based on the design; inputting the first input signal to a previously trained convolution neural network in a block chain network; acquiring a first output signal based on an input result; arranging recommendation-optimized firefighting and disaster prevention equipment in the saved design according to recommended design, based on the first output signal; generating a corrected input signal according to a value input by the designer to adjust required firefighting and disaster prevention equipment and the number thereof, based on an arrangement result; arranging corrected firefighting and disaster prevention equipment in the design based on the recommended design and location relationship of each equipment, the location relationship including role overlapping prevention, distance and connection of each firefighting and disaster prevention equipment, based on the corrected input signal; generating a final corrected input signal according to a final input of the designer based on the arranged design; generating a final location determination and training signal of the firefighting and disaster prevention equipment based on the final corrected input signal; and training a convolution neural network based on the training signal.

Description

METHOD AND APPARATUS FOR CONTROLLING DESIGN AND CONSTRUCTION PROCESS OF FIRE PROTECTION EQUIPMENT}

The following embodiments relate to a control method for the design and construction process of a fire protection system.

Fire-fighting and disaster prevention equipment is a mechanism and equipment that prevents or suppresses the spread of fire by automatically or manually installing fire-fighting agents using fire extinguishing agents, depending on its type, indoor fire hydrant equipment, outdoor fire hydrant equipment, power fire pump equipment, sprinkler fire fighting equipment , Water spray, and the like.

The design of fire-fighting and disaster prevention facilities should be designed with the priority of safety management rather than efficiency compared to the designs of other facilities. Therefore, for the design of such a fire-fighting disaster prevention facility, it can be said that the design of a fire-fighting disaster prevention facility optimized for the design of a building is essential. Therefore, it is necessary to study a system capable of self-learning, optimizing, and preserving records of the design process through a blockchain network while automatically designing the fire protection equipment.

KR101807263 KR101364813 KR101467664 KR1020190062871

The embodiments are intended to increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of a fire protection system.

The embodiments are intended to provide continuous feedback using errors in design errors in a method of designing and constructing a fire protection system.

The embodiments intend to make information big data through a blockchain network and use enhanced security.

A method of controlling the design and construction process of a fire protection system according to an embodiment is a method of controlling a design and a construction process of a fire protection system based on artificial intelligence, which is scanned by a designer for the design of a fire protection system Storing a schematic of the space; Generating a first input signal based on the blueprint; Inputting the first input signal into a convolutional neural network previously learned in a blockchain network; Obtaining a first output signal based on the input result; Based on the first output signal, placing a fire-fighting disaster prevention facility optimized for recommendation in the stored design according to the recommended design; Generating a correction input signal according to a value input to adjust the number of fire-fighting disaster prevention facilities and the number required by the designer based on the arrangement result; Based on the modified input signal, the modified fire protection equipment is based on the recommended design and the location relationship of each facility, wherein the location relationship includes the role overlap prevention, distance and connection of each fire protection equipment, and the design diagram. Placing within; Generating a final corrected input signal according to the final input of the designer based on the arranged design drawing; Generating a final position determination and learning signal of the fire-fighting disaster prevention facility based on the final modified input signal; And training the convolutional neural network based on the learning signal.

According to one embodiment, the fire prevention facility is a fire detection sensor for detecting the occurrence of a fire; A fire alarm outputting a voice and lighting signal for a fire alarm based on the sensing of the fire detection sensor; A fire hydrant for allowing users of the target space to manually extinguish a fire; An automatic fire extinguishing device located on the ceiling of the target space to discharge firefighting water to facilitate early fire suppression; A fire fighting water pipe for supplying fire fighting water to the automatic fire extinguishing device and fire hydrant; And an automatic signal transmitter for firefighting facilities for automatically transmitting fire signals to fire departments and police departments in the vicinity of a fire.

According to an embodiment, the blockchain network includes blocks including a schematic, a database including type, number and location information of fire-fighting disaster prevention facilities, and the pre-trained convolutional neural network; Chains connecting each block in chronological order; And the network storage devices for storing the respective blocks and chains, wherein the network storage devices include a first network storage device including a producer that produces the fire protection equipment; A second network storage device including a designer using a control method of the design and construction process of the fire-fighting disaster prevention facility; A third network storage device including the neighboring fire department and police station; And a high-speed Internet connection network connecting the network storage devices.

According to an embodiment, the database includes design drawings of various spaces collected from big data; And determining the location and number to correspond to the blueprints, and including fire-fighting disaster prevention facilities designed accordingly. The combination of the fire-fighting disaster prevention facilities corresponding to the blueprints is at least two, and the fire-fighting disaster prevention facilities are in a database. Among the combination of the fire-fighting and disaster prevention facilities within, an optimized facility and a combination may be first presented, and a design closest to the correction input information and the final correction input information of the designer may be corrected and presented again.

According to an embodiment, the convolutional neural network uses as input a first input signal encoding the scanned design in a form suitable for the convolutional neural network, and based on the design, the convolutional neural network having the most similar design in the database The feature extraction neural network and classification is classified through a neural network, and based on the classification, a first output signal including the type, number, and location information of the fire fighting equipment corresponding thereto is output, and the design of the fire fighting equipment is performed. It can be learned through the first learning signal generated from the final correction input signal containing the final judgment of the Korean designer.

The apparatus according to an embodiment may be controlled by a computer program stored in a medium in order to execute the method of any one of the above-described methods in combination with hardware.

Embodiments can increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of a fire protection system.

Embodiments can provide continuous feedback using errors in design errors in the control method of the design and construction process of fire protection equipment.

Embodiments can make information big data through a blockchain network and use enhanced security.

1 is a flow chart for explaining a control method of the design and construction process of a fire protection system according to an embodiment.
2 is a view for explaining a fire prevention equipment according to an embodiment.
3 is a view for explaining a blockchain network according to an embodiment.
4 is a view for explaining a database according to an embodiment.
5 is a diagram for describing a convolutional neural network according to an embodiment.
6 is an exemplary view of a configuration of an apparatus according to an embodiment according to an embodiment.

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

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

The terms first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When a component is said to be "connected" to another component, it should be understood that other components may be present, either directly connected to or connected to the other component.

The terms used in the examples are used for illustrative purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described in the specification, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

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

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that detailed descriptions of related known technologies may unnecessarily obscure the subject matter of the embodiments, the detailed descriptions will be omitted.

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, and wearable devices.

1 is a flow chart for explaining a control method of the design and construction process of a fire protection system according to an embodiment.

According to one embodiment, in a method of controlling the design and construction process of a fire-fighting disaster prevention facility based on artificial intelligence, the design of the fire-fighting disaster prevention facility and a control device (hereinafter, a control device) of the fire-fighting disaster prevention facility are designed to control the fire-fighting disaster prevention facility In order to save the design of the target space scanned by the designer (101). The control device is a control device for the design process of the fire protection equipment, and may be implemented by, for example, a software module, a hardware module, or a combination thereof.

According to an embodiment, the control device may be an electronic device including a communication function. For example, the electronic device includes a smart phone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop personal computer (PC), and a laptop. Laptop personal computer (PC), netbook computer, personal digital assistant (PDA), portable multimedia player (PMP), MP3 player, mobile medical device, camera, or wearable device (e.g. Include at least one of head-mounted-device (HMD) such as electronic glasses, electronic clothing, electronic bracelets, electronic necklaces, electronic accessories, electronic tattoos, smart cars or smartwatches. Can.

According to one embodiment, the electronic device may be a smart home appliance with a communication function. For smart household appliances, for example, electronic devices are televisions, digital video disk (DVD) players, audio, refrigerators, air conditioners, cleaners, ovens, microwave ovens, washing machines, air cleaners, set-top boxes, TVs. It may include at least one of a box (eg, Samsung HomeSyncTM, Apple TVTM, or Google TVTM), game consoles, electronic dictionary, electronic keys, camcorder, or electronic picture frame.

According to an embodiment, the electronic device includes various medical devices (eg, magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), computed tomography (CT), photographing device, ultrasound device, etc.), navigation device, GPS receiver ( Global positioning system receiver (EDR), event data recorder (EDR), flight data recorder (FDR), automotive infotainment devices, marine electronic equipment (e.g. navigation systems and gyro compasses, etc.), avionics, security It may include at least one of a device, a head unit for a vehicle, an industrial or household robot, an automatic teller's machine (ATM) of a financial institution, or a point of sales (POS) of a store.

According to one embodiment, the electronic device is a furniture or part of a building/structure including a communication function, an electronic board, an electronic signature receiving device, a projector, or various measurement devices. It may include at least one of a device (for example, water, electricity, gas, or radio wave measurement devices). The electronic device according to an embodiment may be a combination of one or more of the various devices described above. Also, the electronic device according to an embodiment may be a flexible device. Also, it is apparent to those skilled in the art that the electronic device according to an embodiment is not limited to the above-described devices. The term user used in various embodiments may refer to a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).

An electronic device according to an embodiment includes a processor, a memory, a user interface, and a communication interface, and may be connected to another electronic device through a network. The communication interface may transmit and receive data to and from other electronic devices within a predetermined distance through a wired, wireless network, or wired serial communication. The network enables wired and wireless communication between electronic devices and various entities according to an embodiment. The electronic device can communicate with various entities over the network, and the network can use standard communication technologies and/or protocols. At this time, the network (network) includes, but is not limited to, the Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), etc. Anyone who has ordinary knowledge in the field of communication technology can know that it can be another kind of network that can transmit and receive information.

According to one embodiment, the target space is a detached house, a multi-family house, a first-class neighborhood living facility, a second-class neighborhood living facility, a cultural and assembly facility, a religious facility, a sales facility, a transportation facility, a medical facility, an educational research facility, Labor facilities, training facilities, sports facilities, business facilities, lodging facilities, amusement facilities, factories, warehouse facilities, dangerous goods storage and treatment facilities, automobile related facilities, animal and plant related facilities, manure and garbage disposal facilities, correctional and military facilities, It may be any one of broadcasting and communication facilities, power generation facilities, cemetery-related facilities, tourist resting facilities, and funeral homes, but is not limited thereto.

According to an embodiment, the design of the target space may include a plan view, a sectional view, an elevation view, a side view and a back view, but is not limited thereto. The design in the method of designing and controlling the fire prevention equipment and the construction process may be two-dimensional or three-dimensional. The blueprint can be input to the control device through a scan, but in some cases, the blueprint can be drawn using a design program. The design drawing through the design program can be automatically input into the control device without having to go through a scan.

According to one embodiment, the control device may generate a first input signal based on the design diagram (102 ). The control device may input the first input signal to the convolutional neural network previously learned in the blockchain network (103).

According to an embodiment, the control device may encode the scanned design for generating an input signal in a form suitable for a convolutional neural network in a blockchain network. A detailed description of the generation of the first input signal will be described later with reference to FIG. 5.

The convolutional neural network according to an embodiment may be designed to determine the most similar design among the designs in the database based on the real-time scanned design, and to determine fire fighting facilities corresponding thereto. Such a convolutional neural network is composed of a feature extraction neural network and a classification neural network, and the feature extraction neural network proceeds by stacking the input signal sequentially in a convolutional layer and a pooling layer. The convolution layer includes a convolution operation, a convolution filter, and an active function. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The active function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that serves to reduce the matrix size of the input, and uses a method of extracting representative values by grouping pixels in a specific area. In the calculation of the pooling layer, an average value or a maximum value is generally used, but is not limited thereto. The operation is performed using a square matrix, and generally uses a 9X9 matrix. The convolutional layer and the pooling layer are alternately repeated until the input is small enough while maintaining the difference.

According to one embodiment, the classification neural network has a hidden layer and an output layer. In the convolutional neural network for the control method of the design and construction process of fire protection equipment, there are generally three or more hidden layers, and the number of nodes in each hidden layer is designated as 100, but may be set to be more or less in some cases. The active function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The output layer node of the convolutional neural network can be 10 in total. The output layer activation function of the classification neural network uses a softmax function. The softmax function is a representative function of one-hot encoding, which sums all the output nodes to a total of 1, sets the output of the output node with the largest value to 1, and the output of the remaining output nodes to 0. . It is possible to select only one of the 10 outputs through the Softmax function.

The blockchain network according to an embodiment is composed of blocks storing a database and a chain connecting them in chronological order, and the database can store data such as designs, types of fire prevention facilities, and location information. have. The stored database is managed as big data, and the blockchain network can help securely store information in this database and make it available to limited users. The blockchain network and the convolutional neural network will be described later with reference to FIGS. 3, 4, and 5.

According to one embodiment, the control device may obtain a first output signal based on the input result (104). Based on the first output signal, the control device may place the fire-fighting disaster prevention equipment optimized for recommendation in a stored design according to the recommended design (105).

According to an embodiment, the convolutional neural network may have 10 outputs, each of which may include information on the type, number, and location of fire-fighting disaster prevention facilities based on the scanned design. The control device may position each fire-fighting disaster prevention facility in the scanned design, based on the type, number, and location information of the fire-fighting disaster prevention facility in the first output signal. The type, number, and location information of fire-fighting and disaster prevention facilities may be determined as the first priority combination among recommended combinations, and may be referred to as a recommended design. The scanned design may be a design stored in the form of a soft copy in the control device based on color information of the existing hard copy design.

According to an embodiment, the control device may generate a correction input signal according to a value input to adjust the number of fire-fighting disaster prevention facilities and a designer's required based on the placement result (106). Based on the modified input signal, the control device may place the modified fire-fighting disaster prevention facility in the design drawing based on the recommended design and the positional relationship of each facility (107).

According to one embodiment, a designer or user of a control method of a design and construction process of a fire protection equipment may input a type of fire protection equipment selected from the recommended design and matters deemed necessary to be modified underwater. . This input can be used to generate a modified input signal. The modified input signal may be used to select the most similar design among other designs previously included in the first output signal, and after selecting the most similar design, the modified input signal may be modified according to information contained in the modified input signal. It is possible to create new location information suitable for the type and number. The control device can locate the modified fire protection equipment in the design based on the newly generated location information. In this case, if there are types and number of fire protection equipment that are not included in the existing first output signal, each of the fire protection equipment It can be placed in the blueprint based on the location relationship.

The location relationship according to an embodiment may include preventing overlap of roles, distances, and connections of the respective fire prevention facilities. Prevention of overlapping roles of fire-fighting and disaster prevention facilities can be controlled by comparing the increased safety and efficiency of each fire-fighting disaster prevention facility by comparing the roles of each fire-fighting disaster prevention facility with similar or identical roles. The distance of the fire-fighting disaster prevention facilities may mean a distance that each fire-fighting disaster prevention facility can be optimized based on the role overlap prevention. Each distance may include a straight line distance and a distance in consideration of the actual moving line. The connection of fire-fighting and disaster prevention facilities means a connection relationship of each of the fire-fighting and disaster prevention facilities, and may be considered to exhibit an optimized function with the minimum connection complexity as possible. Information about each location relationship may exist in a database in the blockchain network, and may be included in the first output signal.

According to one embodiment, the control device may generate a final modified input signal according to the designer's final input based on the placed design (108). The control device may generate a final positioning and learning signal of the fire protection system based on the final modified input signal (109). The control device may train the convolutional neural network based on the learning signal (110 ).

According to one embodiment, the designer may review the revised design diagram according to the revised input signal, and then input the revised and confirmed information. The input of corrections and confirmations can be used to generate the final correction input signal. If the designer does not input corrections and confirmations, the control device can generate a learning signal based on the previously modified design, and the learning signal can be used in a direction to increase the confidence level of the convolutional neural network for the first output signal. Can. The designer's final modified input is based on one hour after the first output signal of the convolutional neural network is generated, but may be more or less in some cases. The control device can increase accuracy and efficiency by applying deep learning technology to a method of controlling the design and construction process of fire protection equipment.

2 is a view for explaining a fire prevention equipment according to an embodiment.

Referring to Figure 2, the fire prevention facility is a fire detection sensor 201 for detecting the occurrence of a fire; A fire alarm 202 for outputting a voice and lighting signal for a fire alarm based on the sensing of the fire detection sensor 201; A fire hydrant 203 for manually extinguishing users of the target space; Located on the ceiling of the target space, the automatic fire extinguishing device 204 to facilitate the early fire suppression by discharging the fire water; A fire fighting water pipe 205 for supplying fire fighting water to the automatic fire extinguishing device 204 and the fire hydrant 203; And an automatic signal transmitter 206 for a firefighting facility for automatically transmitting a fire signal to a fire department and a police station in the vicinity of a fire.

The fire detection sensor 201 according to an embodiment is a sensor that directly detects fire, a differential detection sensor using expansion of air, a heat detection sensor using heat accumulation, and a compensation type that detects both air expansion and heat accumulation. It can be classified into a sensor and a smoke detection sensor for detecting smoke. Depending on the detection method, it can be classified into a spot-type detection sensor that detects a local part and a distribution-type detection sensor that detects the entire area. The fire detection sensor 201 is an equipment that plays a central role among fire-fighting and disaster prevention facilities, and may enable the initiation of most automatically operated fire-fighting disaster prevention facilities.

The fire alarm 202 according to an embodiment may be a device that outputs a voice and lighting signal to notify a user of a target space when the fire detection sensor 201 senses a fire as a result of sensing. Since the errors of the fire detection sensor 201 and the fire alarm 202 can cause serious damage to the target space and the user, most of them are designed to be matched 1:1, and the fire detection sensors 201 matched to each other in one space And at least two fire alarms 202.

The fire hydrant 203 according to an embodiment refers to a facility for installing a fire hose installed in a water supply pipe of a waterworks, and can be divided into an indoor fire hydrant and an outdoor fire hydrant according to a location. Outdoor fire hydrants can be divided into ground type and underground type. Indoor fire hydrants are equipment that can be used manually by users of the target space, and the installation standards and specifications can follow those specified in the Fire Services Act.

The automatic fire extinguishing device 204 according to an embodiment is a device that automatically operates in the early stage of a fire together with the fire detection sensor 201 and the fire alarm 202, and discharges water from the ceiling in the form of a spray to initially extinguish the fire. Can help. A representative form of the automatic fire extinguishing device 204 is a sprinkler, and in the event of a fire, it starts spraying indirectly by a signal transmitted from the fire detection sensor 201, or is automatically pressurized while the lid of the sprinkler melts and falls off due to heat caused by the fire. You can start spraying in a direct way to let the water spray.

The pipe 205 for fire fighting water according to an embodiment may be an automatic fire extinguishing device 204 and a device that serves as a passage for supplying fire fighting water to the fire hydrant 203. The pipe 205 for fire fighting water may have heat-resistant properties and may be designed to have a sufficient cross-sectional area for smooth movement of fire fighting water.

The automatic signal transmitter 206 according to an embodiment is a device that automatically generates a fire report signal when the fire detection sensor 201 detects a fire, and transmits a report signal to a fire department and a police station in a nearby jurisdiction. It can be equipment that plays an important role in salvation. The automatic signal transmitter 206 may respond to the first signal transmission among the plurality of fire detection sensors 201, and basically includes a heat detection sensor to generate and transmit signals even when the fire detection sensor 201 malfunctions. have. Even if the automatic signal transmitter 206 in the target space malfunctions, the voice signal frequency band of the fire alarm 202 is determined so that the voice signal of the fire alarm 202 can stimulate the nearby automatic signal transmitter 206. It may include a voice sensor capable of.

3 is a view for explaining a blockchain network according to an embodiment.

Referring to FIG. 3, the blockchain network includes blocks 301 including schematics, a database including type, number and location information of fire-fighting disaster prevention facilities, and a pre-trained convolutional neural network; Chains 302 connecting each block 301 in chronological order; And it may be a private blockchain network including the first (310), second (320), third network storage device 330 for storing each blockchain.

According to an embodiment, the block 301 of the blockchain network may include a database including blueprints, types of fire prevention facilities, and location information, and a pre-trained convolutional neural network dealing with the database. Each block 301 is generally connected in chronological order, so that new blocks 301 can be produced at 10 minute intervals. The contents of the already generated block 301 are stored in all network storage devices, and cannot be changed unless the majority of the contents are changed in time. For example, in a blockchain network having a total of three network storage devices, when it is assumed that one block 301 is provided for each network storage device, if the contents of two or more blocks 301 cannot be changed within a limited time, Each block 301 may change the value of the block 301 having a different content from the majority to be equal to the majority by verification. Accordingly, it is possible to maintain high security. In fact, the number of network storage devices participating in the blockchain network may reach tens to hundreds of thousands, and thus, it may exhibit higher security.

Chains 302 according to one embodiment may consist of hash values. The chains 302 allow the blocks 301 to be continuous in chronological order. At this time, each block 301 may be connected using a hash value. In block 301, a database and a hash value of the database, a previous header, and a header of the current block may be stored. Here, the header of the current block functions as a previous header in the next block, so that each block 301 can be organically connected. In addition, the hash value is transformed into a completely different form when the contents of the block are changed even a little, which effectively prevents an attempt to change the contents of the database. Since the header of the current block becomes the total hash value including the database, the hash value of the database, and the previous header, it is difficult to successfully attempt to compromise security by effectively modifying the database and the hash value. Because when the database and hash values are modified, the contents of the header are changed, and accordingly, the previous header that enters the next block is also changed, and accordingly, the header of the block is also changed, so that the previous header of the next block can be changed again. That is, all subsequent blocks 301 must be hacked. Therefore, it is possible to increase the security of the blockchain with the chain 302 through the hash value. The control device can make information big data through the blockchain network and use enhanced security.

According to an embodiment, the network storage devices include a first network storage device 310 including a producer that produces a fire prevention facility; A second network storage device 320 including a designer using a control method of the design and construction process of the fire prevention equipment; A third network storage device 330 including a nearby fire department and a police station; And it may include a high-speed Internet connection network 303 for connecting each network storage device. The network storage devices classified as the first, second, and third may be determined according to the number of practitioners included, the number of users, and the number of storage devices.

According to one embodiment, the first network storage device 310 may include a producer that produces a fire-fighting disaster prevention facility, and the producers may be one company or more. The number of first network storage devices 310 may be determined according to the number of storage devices used by each company. Producers of fire protection equipment of the first network storage device 310 can update the information on the type of fire protection equipment based on the database and convolutional neural network of the blockchain network, according to the needs in the design. Fire prevention equipment can be maintained or developed.

According to one embodiment, the second network storage device 320 may include a designer using a method of designing and constructing a fire protection system. The number of the second network storage device 320 may be determined according to the number of companies designing it and its users in the design and construction process of the fire protection equipment. The designer of the second network storage device 320 may also be referred to as an actual user (hereinafter referred to as a user) using a control method and apparatus for designing and constructing a fire protection system. Users of the control device of the design and construction process of the fire protection system of the second network storage device 320 may facilitate the learning of the convolutional neural network by manually inputting information about errors occurring during actual use.

According to an embodiment, the third network storage device 330 may include a fire department and a police station nearby. Fire departments and police departments in the jurisdiction of the third network storage device 330 are organizations capable of automatically receiving dispatch notifications according to signals transmitted from an automatic signal transmitter, and confirm the design of a fire prevention equipment in a target space through a blockchain network. Based on this, it is possible to carry out extinguishing and rescue operations in case of fire.

The high-speed Internet connection network 303 according to an embodiment generally refers to an Internet connection network having a speed of 10 Mb/s or more, and includes a local area network (LAN), a wireless LAN (Wireless) as a connection network including wired, wireless, and optical cable technologies. Local Area Network (WAN), Wide Area Network (WAN), Personal Area Network (PAN), and the like.

4 is a view for explaining a database according to an embodiment.

Referring to FIG. 4, the database includes design drawings 401 of various spaces collected from big data; And determining the location and number to correspond to the design drawings 401, and may include fire protection facilities 402 designed accordingly.

According to one embodiment, the database in the blockchain network may store values manually entered by the administrator initially by the administrator, and the first input values include designs of various spaces collected online based on big data. 401. The design drawings 401 may acquire only information including information on the purpose and area of use of the space. The initial input value may also include the type, number, and location information of the firefighting disaster prevention facilities 402 corresponding to these designs 401. Those values have ordinary knowledge of firefighting disaster prevention facility design. I can tell. The type, number, and location information of each fire-fighting disaster prevention facilities 402 is made by fire-fighting disaster prevention design experts and officials of national organizations related to fire-fighting disaster prevention, and the values input through at least 100 experts and civil servants Through this, you can rank based on the maximum recommendation. The input of the database except the first input can be updated through the learning process of the convolutional neural network.

According to an embodiment, a design similar to the design input through the convolutional neural network may be searched among the design drawings 401 in the database, and through this, the type, number, and location information of the fire protection equipment corresponding to the similar design may be obtained. have. The type, number, and location information of the fire-fighting disaster prevention equipment corresponding to the blueprint may be recommended based on the ranking among values stored in the database, and these values may be included in the first output signal. The combination of fire protection equipment 402 corresponding to the design drawings 401 may be at least two or more.

According to one embodiment, the fire-fighting and disaster prevention facilities 402 may be initially presented with optimized facilities and combinations among the combination of the fire-fighting and disaster prevention facilities 402 in the database, and the designer's correction input information and final correction input information and The nearest design can be modified and presented again. The combination of the type and number of fire protection equipment presented first can be based on a ranking derived from values input by experts and officials, and this ranking can be modified through learning of a convolutional neural network. The designer's correction input information and the final correction input information may be derived to select the closest combination among the combinations of the next order included in the first output signal, and in some cases, correction values not included in the combination are based on the positional relationship. Can be automatically entered. The designer's correction input information and the final correction input information may be used to train a convolutional neural network as a learning signal in the future.

5 is a diagram for describing a convolutional neural network according to an embodiment.

Referring to FIG. 5, blocks in a blockchain network may include a pre-trained convolutional neural network 510 and a database, the first input signal 501 as an input, and the first output signal 502 as an output. And learning through the learning signal 503.

According to an embodiment, the first input signal 501 that is the input of the convolutional neural network 510 may encode the scanned design into a form suitable for the convolutional neural network. The first input signal 501 may encode a value obtained by quantifying color information of each pixel of the scanned blueprint, which is suitable for a convolutional neural network. The color information may include RGB information for each pixel, brightness, and saturation. The first input signal 501 provides the information so that the blueprint boundary can be clarified by distinguishing the blueprint of the target space from the background based on each value of color information. The color information included in the first input signal 501 may be compared with the designs in the database through the convolutional neural network 510.

According to an embodiment, the convolutional neural network 510 may classify the most similar designation in the database through the feature extraction neural network and the classification neural network based on the design in the first input signal. The feature extraction neural network proceeds by stacking the input signal sequentially in a convolutional layer and a pooling layer. The convolution layer includes a convolution operation, a convolution filter, and an active function. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The active function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that serves to reduce the matrix size of the input, and uses a method of extracting representative values by grouping pixels in a specific area. In the calculation of the pooling layer, an average value or a maximum value is generally used, but is not limited thereto. The operation is performed using a square matrix, and generally uses a 9X9 matrix. The convolutional layer and the pooling layer may be alternately repeated until the input is small enough while maintaining a difference. The classification neural network has a hidden layer and an output layer. In the convolutional neural network 510 for a method of designing and controlling a fire protection system, there are generally three or more hidden layers, and the number of nodes in each hidden layer is designated as 100, but may be determined as more or less depending on the case. The active function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The output layer node of the convolutional neural network 510 may be 10 in total. The output layer activation function of the classification neural network uses a softmax function. The softmax function is a representative function of one-hot encoding, which sums all the output nodes to a total of 1, sets the output of the output node with the largest value to 1, and the output of the remaining output nodes to 0. . It may be possible to select only one of the 10 outputs through the Softmax function. The 10 outputs show the most similar design in the database, and various information about this can be stored in the database.

According to an embodiment, the first output signal 502 that is the output of the convolutional neural network 510 may include information on the type, number, and location of fire-fighting disaster prevention facilities corresponding to the classification of the convolutional neural network. The first output signal 502 may show a combination of the type, number, and location information of the fire-fighting disaster prevention facility, wherein the classification of the combination may be generally based on information stored on the database. The data stored on the database may increase or decrease the number of data according to the learning process of the convolutional neural network 510, and accordingly, the number of output nodes may be changed to 10 or more.

According to one embodiment, the learning signal 503 for learning the convolutional neural network 510 may be generated from a final modified input signal that contains the designer's final judgment regarding the design of the fire protection equipment. The designer can manually input the information to be corrected based on the determination of the need to generate the learning signal, and through this, reinforcement or weakening of the database information may be achieved according to the type of the learning signal 503.

The learning signal 503 according to an embodiment is made based on an error between a correct answer and an output value. In some cases, an SGD using a delta, a batch method, or a method using a back propagation algorithm may be used. According to the learning signal, the convolutional neural network 510 performs learning by modifying an existing weight, and may use momentum in some cases. The cost function can be used to calculate the error, and the cross entropy function can be used as the cost function.

According to one embodiment, the convolutional neural network 510 can learn to determine the most similar design in the database based on the learning signal 503 and to modify the type, number, and location information of the fire protection equipment corresponding thereto. have. The pre-trained convolutional neural network 510 has three or more hidden layers, and each hidden layer can have 50 or more hidden nodes. ReLU function, sigmoid function and tanh function can be used as the active function of each hidden node, but is not limited thereto. As a function of the output node, a softmax function using one-hot encoding can be used. The output selects only one classification according to the one-hot encoding technique, and can execute commands from the selected classification.

According to one embodiment, the database may store information as big data, and may be continuously updated through a high-speed Internet connection network connected to a blockchain network.

The control device according to an embodiment may continuously provide feedback by using an error of a design error in a method of designing and constructing a fire protection system.

6 is an exemplary view of a configuration of an apparatus according to an embodiment.

The device 1201 according to an embodiment includes a processor 1202 and a memory 1203. The device 1201 according to an embodiment may be the above-described server or terminal. The processor may include at least one device described above with reference to FIGS. 1 to 5, or may perform at least one method described above with reference to FIGS. 1 to 5. The memory 1203 may store information related to the above-described method or a program implemented with the above-described method. The memory 1203 may be volatile memory or nonvolatile memory.

According to an embodiment, the processor 1202 may execute a program and control the device 1201. The code of the program executed by the processor 1202 may be stored in the memory 1203. The device 1201 is connected to an external device (for example, a personal computer or a network) through an input/output device (not shown) and can exchange data.

The embodiments described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices, methods, and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, and field programmable gates (FPGAs). It can be implemented using one or more general purpose computers or special purpose computers, such as arrays, programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

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, or the like alone or in combination. The program instructions recorded on the medium may be specially designed and constructed for the embodiments or may be known and usable by 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, DVDs, and magnetic media such as floptical disks. -Hardware devices specifically 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 code that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device 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 include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave. The software may be distributed on 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 by the limited drawings, those skilled in the art can 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 components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (5)

In the processor, storing the design of the target space scanned by the designer for the design of the fire prevention equipment;
In the processor, based on the color information for each pixel of the blueprint-the color information includes RGB information, brightness, and saturation-generating a first input signal encoding the color information for each pixel with a numerical value step;
In the processor, inputting the first input signal into a convolutional neural network in a blockchain network;
Obtaining, by the processor, a first output signal based on a result of the input to the convolutional neural network;
Obtaining, from the processor, a recommended fire protection equipment and a recommended design based on the first output signal;
Placing, in the processor, the recommended fire-fighting disaster prevention facility in the stored design based on the recommended design;
Generating, by the processor, a correction input signal according to a value input by the designer to adjust the type and number of fire-fighting disaster prevention facilities, based on a result of the arrangement in the schematic;
Obtaining, by the processor, a modified firefighting disaster prevention facility based on the modified input signal;
Placing, in the processor, the modified fire prevention facility in the design based on the recommended design and the positional relationship of the modified fire protection facility;
Generating, by the processor, a final modified input signal according to the final input of the designer based on the design diagram;
Determining, by the processor, a final location of the modified firefighting disaster prevention facility based on the last modified input signal and generating a learning signal; And
In the processor, learning the convolutional neural network based on the learning signal.
Including,
The blockchain network
Blocks comprising a convolutional neural network and a database including blueprints, types, number and location information of fire protection facilities;
Chains connecting the blocks in chronological order; And
Network storage devices that store the blocks and chains
It is a private blockchain network that includes,
The network storage devices
A first network storage device including a producer that produces the fire protection equipment;
A second network storage device including a designer using a control method of the design and construction process of the fire-fighting disaster prevention facility;
A third network storage device including a nearby fire department and police station; And
Internet connection network connecting the network storage devices
Including,
The database is
Blueprints corresponding to a plurality of spaces; And
Fire and disaster prevention facilities are determined in accordance with the determined location and number, and corresponding to the design drawings
Including,
There are two or more combinations of the fire protection facilities corresponding to the blueprints,
The fire prevention equipment
A fire detection sensor that detects the occurrence of a fire;
A fire alarm outputting a voice and lighting signal for a fire alarm based on the sensing of the fire detection sensor;
Fire hydrants for manually extinguishing users of the target space;
An automatic fire extinguishing device located on the ceiling of the target space to discharge firefighting water to facilitate early fire suppression;
A pipe for fire fighting water for supplying fire fighting water to the automatic fire extinguishing device and the fire hydrant; And
Automatic signal transmitter for firefighting facilities to automatically transmit fire signals to nearby fire departments and police stations in the event of a fire
Including,
The fire prevention facilities in the database are determined by ranked combinations,
The first output signal includes the ranked combinations,
The recommended fire protection equipment and the recommended design are designated by the first ranked combination among the ranked combinations,
The positional relationship of the modified firefighting disaster prevention facility is
When the roles of the fire-fighting disaster prevention facilities are classified as similar or identical, mutually based on data in the database for the convenience increase and efficiency reduction indicators measured by placing the classified fire-fighting disaster prevention facilities within a predefined range. Preventing overlap of roles determined through determination of a control device that performs comparison;
A distance determined through determination of the control device based on data in the database for a straight line distance and a user's expected movement line based on the positions of the fire prevention equipment to which the role overlap prevention is applied; And
A connection determined by the control device based on data in the database for connection complexity and functional optimization of the fire protection equipment in a relationship connected through conduits and piping.
Including,
The convolutional neural network
Based on the color information included for each pixel in the first input signal, the blueprint is separated from the background to recognize only the blueprint,
Performing a convolution operation and a pooling operation on the first input signal using a convolution layer and a pooling layer,
The total sum of the values of the output nodes of the output layer and the values of the output nodes is 1 using a classification neural network including a plurality of hidden layers and an output layer of a square matrix whose matrix size is reduced than the first input signal by the pooling operation. Determine the similar design most similar to the design among the designs in the database by Lim-,
Obtain the type, number and location information of the recommended fire-fighting disaster prevention facilities corresponding to the similar design, based on the design drawings, the type, number and location information of fire-fighting disaster prevention facilities in the database,
Based on the type, number, and location information of the recommended fire-fighting disaster prevention facility, a recommendation design for locating the recommended fire-fighting disaster prevention facility in the blueprint is generated, and information about the recommended fire-fighting disaster prevention facility and the recommended design is provided in the first. In the output signal,
It is learned in advance based on the types, number, and location information of the fire protection equipment designed to correspond to the blueprints and the blueprints in the database,
Based on the final correction input of the designer, iteratively performs learning,
When the modified fire-fighting disaster prevention equipment is placed on the blueprint and the final input signal is not input within one hour, learning through an automatically generated learning signal based on the blueprint generated from the crystal input signal,
Control method for the design and construction process of fire protection equipment.

delete delete delete delete

Images