KR102269581B1 - System and method for managing bulding based on artificial intelligence - Google Patents

Abstract

The present invention relates to a building management system using artificial intelligence (AI) to precisely control building energy and disaster relief and a building management method thereof. According to the present invention, the building management system comprises: an environmental information sensing unit detecting environmental information inside and outside a building; a user information detection unit detecting user information in the building; a communication unit transmitting and receiving the detected environment information and user information; and a building control management unit controlling energy and disaster relief of a building on the basis of the environmental information and the user information. The building control management unit stores and classifies data about the received environmental information and user information when the environmental information and the user information are received; learns the stored and classified data; analyzes a user state and energy state by floor and room of the building on the basis of data learning; predicts and determines the user state and the energy state on the basis of data learning and user and energy state analysis results; and controls and manages the user state and energy state for each floor and room of the building on the basis of prediction and determination results.

Description

SYSTEM AND METHOD FOR MANAGING BULDING BASED ON ARTIFICIAL INTELLIGENCE

The present invention relates to a building management system, and more particularly, to a building management system and a building management method capable of precisely controlling building energy and disaster relief using artificial intelligence.

In general, as the facilities of buildings are modernized, an automatic control system that automatically controls various systems such as electric power, lighting, disaster prevention, etc. installed in a building is spreading, and the building management system that can integrate and manage these various systems as a whole is spreading. Development is actively underway.

Such a building management system provides a function to automatically turn on/off facilities or equipment in a building through sensing of a human body or sensing temperature, humidity, illuminance, or the like, or automatically controls according to a set value of a predetermined time. has a function.

However, since such a building management system automatically controls the facilities in the building according to a predetermined setting value without considering the user distribution in the building, it may cause unnecessary energy wastage, and may provide an uncomfortable environment for some users in the building. have.

In particular, when a disaster occurs in a building, there may be problems that may cause great environmental constraints to users in the building, causing further confusion and loss.

Therefore, there is a demand for the development of a building management system capable of precisely controlling building energy and disaster relief using artificial intelligence in the future.

Laid-open Patent Publication No. 10-2008-0073162 (published on August 8, 2008)

A technical task to be achieved by an embodiment of the present invention is a building management system that can precisely control the structure of building energy and disasters based on the learning of the user state inside and outside the building using artificial intelligence. and building management methods.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. will be able

In order to solve the technical problem as described above, an artificial intelligence-based building management system according to an embodiment of the present invention includes an environment information sensing unit for detecting environmental information inside and outside the building; a user information detection unit that detects user information in a building; a communication unit for transmitting and receiving the sensed environment information and user information; And, it includes a building control management unit for controlling the energy and disaster structure of the building based on the environmental information and user information, and the building control management unit, when receiving the environmental information and the user information, the received environmental information and data on the user information is stored and classify, learn stored and classified data, analyze user state and energy state by floor and room of a building based on data learning, and predict user and energy state in advance based on data learning and user and energy state analysis results It makes predictions and judgments, and based on the prediction and judgment results, it is possible to control and manage the user and energy status by floor and room of a building.

In the artificial intelligence-based building management system of the present invention, the environment information sensing unit may include an indoor environment information sensing unit for sensing environment information inside the building, and an outdoor environment information sensing unit sensing environment information outside the building.

In the artificial intelligence-based building management system of the present invention, the user information detection unit may include an image information detection unit that acquires image information of a user located in a building, and a human body information detection unit that acquires human body information of a user located in the building. can

In the artificial intelligence-based building management system of the present invention, the user information detection unit may include a user complex information detection unit for acquiring image information and human body information of a user located in a building.

The artificial intelligence-based building management system of the present invention may further include a meteorological information collecting unit that collects meteorological information from the first external server, and a disaster information collecting unit that collects disaster information from the second external server.

In the artificial intelligence-based building management system of the present invention, the building control management unit can learn data related to the gender, age, health condition, disability, pregnancy status, movement line, and resident location of the building user when learning data. .

In the artificial intelligence-based building management system of the present invention, the building control management unit, when learning data, the user's gender, age, health condition, disability, pregnancy status, user distribution status by floor of the building and each floor of the building You can learn the distribution status of each user.

In the artificial intelligence-based building management system of the present invention, the building control management unit, when learning data, can learn the user's structure priority corresponding to the user distribution status for each floor of the building and the user distribution status for each room on each floor of the building. .

In the artificial intelligence-based building management system of the present invention, the building control management unit, when learning data, by month, by day, by holiday, by season, by national day, by anniversary, by specific event day, by environmental state, by weather state, disaster By state, it is possible to learn the user distribution status by floor of the building and the user distribution status by room on each floor of the building.

In the artificial intelligence-based building management system of the present invention, the building control management unit, when learning data, at least one of the first conditions including the user's gender, age, health status, disability, and pregnancy, and month, For each situation in which at least one of the second conditions including days, holidays, seasons, national holidays, anniversaries, specific event days, environmental conditions, meteorological conditions, and disaster conditions overlap with each other, the user distribution status by floor of a building and each room on each floor of the building User distribution status can be learned.

In the artificial intelligence-based building management system of the present invention, the building control management unit, when analyzing the user status, analyzes the location and movement of the user by floor and room of the building based on data learning, and based on this, analyzes the location and movement of the user by floor and It is possible to grasp the user distribution status and user movement status by room.

In the artificial intelligence-based building management system of the present invention, when analyzing the energy state, the building control management unit may integrate and analyze the energy use status for each floor and each room of the building based on data learning.

In the artificial intelligence-based building management system of the present invention, the building control management unit, when predicting and judging the user and energy state in advance, based on the data learning and user and energy state analysis results, the user distribution status and users by floor and room of the building It is possible to predict and determine the current state of movement, and predict and determine the real-time energy consumption by floor and room of a building.

In the artificial intelligence-based building management system of the present invention, when the building control management unit predicts and determines the user and energy state in advance, based on the data learning and user and energy state analysis results, the user by floor and room of the building according to the disaster situation It is possible to predict and determine the distribution status, user movement status, and user structure priority, and predict and determine real-time energy usage for each floor and room of the building according to a disaster situation.

In the artificial intelligence-based building management system of the present invention, when the building control management unit controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the user distribution for each floor and each room of the building is predicted to be less than or equal to the standard distribution amount This enables pre-control to reduce energy usage for the corresponding floor and the corresponding room of the building.

In the artificial intelligence-based building management system of the present invention, when the building control management unit controls and manages the user and energy state for each floor and room of the building, based on the determination result, if the distribution of users per floor and per room of the building is less than the standard distribution, the building It is possible to control in real time so that the energy consumption is reduced for the corresponding floor of the room and the corresponding room.

In the artificial intelligence-based building management system of the present invention, when the building control management unit controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the building floor and room predicted to the place where the user wants to move It can be controlled in advance to increase the energy usage for

In the artificial intelligence-based building management system of the present invention, when the building control management unit controls and manages the user and energy state for each floor and room of the building, based on the determination result, energy consumption is It can be controlled in real time to increase.

In the artificial intelligence-based building management system of the present invention, the building control management unit controls and manages the user and energy state by floor and room of the building, and when a disaster occurs, the user distribution status by floor and room of the building, user movement status and generate user rescue priority information and control the communication unit to transmit the information to an external rescue organization.

In the artificial intelligence-based building management system of the present invention, the building control management unit controls and manages the user and energy state by floor and room of the building, and when a disaster occurs, the user distribution status by floor and room of the building, user movement status and generating a notification message based on the user structure priority information and controlling the communication unit to transmit the generated notification message to a corresponding user's terminal.

In the artificial intelligence-based building management system of the present invention, when generating a notification message, the building control management unit determines the current status of each user based on the user distribution status, user movement status, and user structure priority information for each floor and room of the building. It is possible to analyze and create a customized alarm message for each user based on the current state of each user and the type of disaster situation.

In the artificial intelligence-based building management system of the present invention, when the building control management unit generates a customized notification message, if the user's visual health is less than or equal to a reference value, a customized notification message with an enlarged text size and a customized voice providing a notification message by voice At least one of a message and a customized vibration message providing a notification message as vibration may be generated.

In the artificial intelligence-based building management system of the present invention, the building control management unit, when transmitting the notification message, determines the notification message transmission order for each user based on the user structure priority information, and sequentially sends the notification message according to the determined notification message transmission priority can be transmitted to the user terminal.

In the artificial intelligence-based building management system of the present invention, the building control management unit controls and manages the user and energy state by floor and room of the building, and when a disaster occurs, the user distribution status by floor and room of the building, user movement status And it is possible to determine the emergency escape route based on the user structure priority information, and control the lighting of the building so that only the lamps located in the identified emergency escape route are turned on.

In the artificial intelligence-based building management system of the present invention, the building control management unit includes: a storage unit for storing data about the received environment information and user information; a classification unit for classifying data on the received environment information and user information; a learning unit for learning stored and classified data; an analysis unit that analyzes the user state and energy state for each floor and room of the building based on data learning; a prediction and determination unit that predicts and determines the user and energy state in advance based on the data learning and the user and energy state analysis results; And, it may include a control management unit for controlling and managing the user and energy state for each floor and each room of the building based on the prediction and determination result.

In the artificial intelligence-based building management system of the present invention, the building control management unit may further include a monitoring unit that displays the user and energy state and their control management information for each floor and room of the building.

On the other hand, the building management method of the artificial intelligence-based building management system according to an embodiment of the present invention, the steps of obtaining the environment information and user information in the building inside and outside the building; storing and classifying data on the acquired environment information and user information; learning stored and classified data; analyzing the user state and energy state for each floor and room of a building based on data learning; Predicting and judging a user and energy state based on data learning and user and energy state analysis results; And, it may include the step of controlling and managing the user and energy state for each floor and each room of the building based on the prediction and determination result.

The effects of the artificial intelligence-based building management system and method according to the present invention will be described as follows.

The present invention uses artificial intelligence to learn the internal and external environments of a building and the state of the user in the building, and based on this, it is possible to precisely control the structure according to the occurrence of building energy and disasters.

In addition, the present invention can predict and determine the user's movement line and distribution status and user type in advance for each floor and each room of the building, so that each floor and each room of the building can be controlled in detail.

In addition, according to the present invention, even if the same user exists in the same space, the user type (gender, age, disabled, pregnant woman, etc.) can be accurately identified through image information and biometric information, so that each floor and each room can be controlled in detail.

In addition, the present invention provides a comfortable indoor environment for users by controlling facilities and devices for each floor and each room before a predetermined time before users enter and exit each floor and each room based on learning data on user movement and distribution for each floor and each room. can be provided, and through this, it is possible to precisely control the energy consumption of each floor and each room.

In addition, the present invention, in an emergency situation, based on the user's image information and human body information, it is possible to quickly rescue the user by identifying the type and distribution status of each floor and each room.

Further scope of applicability of the present invention will become apparent from the following detailed description. However, it should be understood that the detailed description and specific embodiments such as preferred embodiments of the present invention are given by way of illustration only, since various changes and modifications within the spirit and scope of the present invention may be clearly understood by those skilled in the art.

1 is a view showing an artificial intelligence-based building management system according to the present invention.
2 is a flowchart illustrating an artificial intelligence-based building management method according to the present invention.
3 is a flowchart illustrating an artificial intelligence-based building management method according to another embodiment of the present invention.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

The suffixes “module” and “unit” for components used in the following description are simply given in consideration of the ease of writing the present specification, and the “module” and “unit” may be used interchangeably.

Furthermore, embodiments of the present invention will be described in detail with reference to the accompanying drawings and the contents described in the accompanying drawings, but the present invention is not limited or limited by the embodiments.

The terms used in the present specification have been selected as widely used general terms as possible while considering functions in the present invention, but these may vary depending on the intention or custom of a person skilled in the art or the advent of new technology. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in the description of the corresponding invention. Therefore, it is intended to clarify that the terms used in this specification should be interpreted based on the actual meaning of the terms and the contents of the entire specification, rather than the names of simple terms.

1 is a view showing an artificial intelligence-based building management system according to the present invention.

As shown in Fig. 1, the artificial intelligence-based building management system 100 of the present invention includes an environment information detection unit 110 that detects environmental information inside and outside the building, a user information detection unit that detects user information in the building ( 120), a communication unit 130 for transmitting and receiving the sensed environment information and user information, and a building control management unit 140 for controlling the energy and disaster relief of the building based on the environment information and user information.

Here, the environment information sensing unit 110 may include an indoor environment information sensing unit 112 for sensing environment information inside the building, and an outdoor environment information sensing unit 114 for sensing environment information outside the building. .

As an example, the indoor environment information detection unit 112 may include at least one of a temperature sensor, a humidity sensor, a fire sensor, an illuminance sensor, a gas sensor, a dust sensor, and a power sensor installed inside a building, limited to this it doesn't happen

In addition, as an example, the outdoor environment information sensing unit 114 may include at least one of a temperature sensor, a humidity sensor, a fire sensor, an illuminance sensor, a wind direction sensor, a wind speed sensor, a rainfall sensor, and a vibration sensor installed outside the building. may be, but is not limited thereto.

Next, the user information detection unit 120 includes an image information detection unit 122 that acquires image information of a user located in a building, and a human body information detection unit 124 that acquires human body information of a user located in the building. may include

For example, the image information sensing unit 122 may include at least one of an occupancy sensor, an image sensor, an infrared sensor, and a complex sensor including all of them, but is not limited thereto.

A plurality of image information sensing units 122 are installed for each floor, room, user movement area, and user movement device of a building, and may acquire image information of a user existing in the building in real time.

Also, as an example, the human body information sensing unit 124 may include at least one of a wearable device, a personal identification card, and a biometric sensor, but is not limited thereto.

Here, the wearable device may be mounted on the user's body to obtain user personal state information including the user's heart rate, body temperature, and stress index.

In addition, the biometric sensor includes an external biometric recognition sensor including a fingerprint recognition sensor, an iris recognition sensor, and a palm recognition sensor, a biometric internal recognition sensor including a vein recognition sensor, and an external biometric recognition sensor and a biometric internal recognition sensor. It may include a biocomposite recognition sensor including

Next, the user information detection unit 120 may include a user complex information detection unit that acquires both image information and human body information of a user located in a building.

As an example, the user complex information sensing unit may include a wearable device equipped with an image sensor, but is not limited thereto.

Meanwhile, the communication unit 130 may include at least one of a wireless communication module, a mobile communication module, a wireless Internet module, a short-range communication module, and a location information module.

For example, the wireless communication module includes at least one of the environment information detection unit 110 , the user information detection unit 120 , the weather information collection unit 150 , and the disaster information collection unit 160 and the building control management unit 140 . It can enable wireless communication between

And, the mobile communication module, the technical standards or communication methods for mobile communication (eg, Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), EV- Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (DO), Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), LTE-A (LTE-A) Long Term Evolution-Advanced), etc.) can transmit and receive radio signals with at least one of a base station, an external terminal, and a server on a mobile communication network.

Here, the wireless signal may include various types of data according to transmission/reception of a voice call signal, a video call signal, or a text/multimedia message.

Next, the wireless Internet module refers to a module for wireless Internet access, and is configured to transmit and receive wireless signals in a communication network according to wireless Internet technologies.

As wireless Internet technologies, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), and the like.

Next, the short-range communication module, as for short-range communication, Bluetooth (BluetoothTM, RFID (Radio Frequency Identification), infrared communication (Infrared Data Association; IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near)) Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies may be used to support short-distance communication.

In addition, the location information module is a module for acquiring the location (or current location) of the user's mobile terminal, and examples thereof include a Global Positioning System (GPS) module, a Wireless Fidelity (WiFi) module, a beacon module, and the like.

For example, when a user's mobile terminal utilizes a GPS module, it acquires its own location using a signal sent from a GPS satellite, and provides the acquired location information to the building control management unit 140 through the communication unit 130 . can do.

As another example, when the user's mobile terminal utilizes the Wi-Fi module, based on the information of the Wi-Fi module and the wireless AP (Wireless Access Point) that transmits or receives the wireless signal, the user's mobile terminal acquires its location, The acquired location information may be provided to the building control management unit 140 through the communication unit 130 .

As another example, the user's mobile terminal acquires its location by receiving an inaudible sound wave in a specific area using a microphone, and provides the obtained location information to the building control management unit 140 through the communication unit 130 . You may.

In addition, the artificial intelligence-based building management system 100 of the present invention includes a weather information collection unit 150 for collecting weather information from a first external server, and a disaster information collection unit for collecting disaster information from a second external server ( 160) may be further included.

As an example, the first external server may be at least one of the servers of weather-related organizations located in Korea and abroad, but is not limited thereto.

The second external server may be at least one of disaster-related agency servers located in Korea and abroad, but is not limited thereto.

Here, the communication unit 130 may transmit and receive the collected weather information and disaster information.

Next, the building control management unit 140 includes a storage unit 142 for storing data on the received environment information and user information, a classification unit 143 for classifying data on the received environment information and user information, storage and The learning unit 144 for learning the classified data, the analysis unit 145 for analyzing the user state and energy state for each floor and room of the building based on data learning, the user and the energy state based on the data learning and user and energy state analysis results It may include a prediction and determination unit 146 that predicts and determines the energy state in advance, and a control management unit 147 that controls and manages users and energy states for each floor and room of a building based on the prediction and determination results.

In addition, the building control management unit 140 may further include a monitoring unit 148 for displaying the user and energy state and their control management information for each floor and room of the building.

For example, the storage unit 142 of the building control management unit 140 may include a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory. (e.g. SD or XD memory), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, may include at least one type of storage medium of an optical disk, but is not limited thereto.

In addition, the learning unit 144 of the building control management unit 140 may learn data using an artificial neural network.

Here, the artificial neural network is a deep neural network (DNN), and may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer.

For example, a deep neural network is a convolutional neural network (CNN), a recurrent neural network (RNN), an auto encoder, a generative adversarial network (GAN), a constrained Boltzmann machine ( Restricted boltzmann machine (RBM), deep belief network (DBN), Q network, U network, Siamese network, etc. may be included, but are not limited thereto.

In addition, the learning unit 144 of the building control management unit 140 may be learned by at least one of teacher learning (supervised learning), non-supervised learning (unsupervised learning), and semi-supervised learning (semi-supervised learning).

Here, the learning of the artificial neural network is to minimize the error of the output, repeatedly input the learning data to the artificial neural network, calculate the output of the artificial neural network for the learning data and the error of the target, and artificially reduce the error. It may be a process of updating the weight of each node of the artificial neural network by backpropagating the error of the neural network from the output layer of the artificial neural network to the input layer.

Accordingly, when learning data, the learning unit 144 of the building control management unit 140 may learn data related to the gender, age, health condition, disability, pregnancy status, movement line, and resident location of the building user. .

In addition, the learning unit 144 of the building control management unit 140, when learning data, the user's gender, age, health condition, disability, pregnancy status, the user distribution status by floor of the building and each floor room of the building You can learn the distribution status of each user.

Here, when learning data, the learning unit 144 of the building control management unit 140 may learn the user's structure priority corresponding to the user distribution status by floor of the building and the user distribution status by room on each floor of the building. .

In addition, the learning unit 144 of the building control management unit 140, when learning data, by month, by day, by holiday, by season, by national day, by anniversary, by specific event day, by environmental state, by weather state, disaster It is possible to learn the user distribution status for each floor of the building and the user distribution status for each room on each floor of the building by status.

Here, when learning data, the learning unit 144 of the building control management unit 140 may learn the user's structure priority corresponding to the user distribution status by floor of the building and the user distribution status by room on each floor of the building. .

In addition, the learning unit 144 of the building control management unit 140, when learning data, at least any one of the first conditions including the user's gender, age, health status, disability, pregnancy status, and month, For each situation in which at least one of the second conditions including days, holidays, seasons, national holidays, anniversaries, specific event days, environmental conditions, meteorological conditions, and disaster conditions overlap with each other, the user distribution status by floor of a building and each room on each floor of the building User distribution status can be learned.

Here, when learning data, the learning unit 144 of the building control management unit 140 may learn the user's structure priority corresponding to the user distribution status by floor of the building and the user distribution status by room on each floor of the building. .

Next, the analysis unit 145 of the building control management unit 140, when analyzing the user status, analyzes the location and movement of the user by floor and room of the building based on data learning, and based on this, analyzes the location and movement of the user by floor and It is possible to grasp the user distribution status and user movement status by room.

And, when analyzing the energy state, the analysis unit 145 of the building control management unit 140 may integrate and analyze the energy use status for each floor and each room of the building based on data learning.

Next, the prediction determination unit 146 of the building control management unit 140, when predicting and determining the user and energy state in advance, based on the data learning and user and energy state analysis results, the user distribution status and It is possible to predict and determine the user movement status, and predict and determine the real-time energy consumption by floor and room of a building.

In addition, the prediction determination unit 146 of the building control management unit 140, when predicting and determining the user and energy state in advance, based on the data learning and the user and energy state analysis results for each floor and room of the building according to the disaster situation It is possible to predict and determine the user distribution status, user movement status, and user structure priority, and predict and determine real-time energy consumption by floor and room of a building according to a disaster situation.

Next, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the amount of user distribution for each floor and each room of the building is predicted to be less than or equal to the reference distribution amount This enables pre-control to reduce energy usage for the corresponding floor and the corresponding room of the building.

In addition, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the amount of user distribution for each floor and each room of the building is predicted to exceed the standard distribution amount When this happens, it is possible to pre-control the increase in energy use for the corresponding floor and the corresponding room of the building.

And, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the determination result, if the amount of user distribution for each floor and each room of the building is less than the standard distribution amount, the building It is possible to control in real time so that the energy consumption is reduced for the corresponding floor of the room and the corresponding room.

In addition, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the determination result, if the distribution amount of users per floor and room of the building exceeds the standard distribution amount, the building It is possible to control in real time to increase the energy usage for the corresponding floor of the room and the corresponding room.

Next, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the building floor and room predicted to the place where the user wants to move It can be controlled in advance to increase the energy usage for

In addition, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, based on the prediction result, the floor and room of the building predicted as the place where the user leaves It can be pre-controlled to reduce energy usage.

And, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, the energy usage for the floor and room of the building to which the user moved based on the determination result is It can be controlled in real time to increase.

In addition, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state for each floor and room of the building, the energy consumption for the floor and room of the building where the user has already left based on the determination result is It can be controlled in real time to reduce it.

Next, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state by floor and room of the building, when a disaster situation occurs, the user distribution status by floor and room of the building, user movement status And it is possible to control the communication unit 130 to generate the user rescue priority information and transmit the information to an external rescue organization.

In addition, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state by floor and room of the building, when a disaster situation occurs, the user distribution status by floor and room of the building, user movement status And it is possible to control the communication unit 130 to generate a notification message based on the user structure priority information and transmit the generated notification message to the terminal of the corresponding user.

Here, the control management unit 147 of the building control management unit 140, when generating the notification message, the current state of each user based on the user distribution status, user movement status, and user structure priority information for each floor and room of the building It is possible to analyze and create a customized alarm message for each user based on the current state of each user and the type of disaster situation.

In some cases, when the control management unit 147 of the building control management unit 140 generates a customized notification message, if the visual health of the user is less than the reference value, the customized notification message with the font size enlarged, the notification message is provided by voice. At least one of a customized voice message and a customized vibration message providing a notification message as vibration may be generated.

In addition, the control management unit 147 of the building control management unit 140, when transmitting the notification message, determines the notification message transmission order for each user based on the user structure priority information, and sequentially according to the determined notification message transmission priority can be transmitted to the user terminal.

The reason is so that users in the building can be evacuated quickly and quickly.

For example, a user terminal includes a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a slate PC, Any one movement selected from a wearable device including a tablet PC, an ultrabook, a smart watch, a smart glass, and a head mounted display (HMD) It may be a terminal, but is not limited thereto.

Next, when the control management unit 147 of the building control management unit 140 controls and manages the user and energy state by floor and room of the building, when a disaster situation occurs, the user distribution status by floor and room of the building, user movement status And it is possible to determine the emergency escape route based on the user structure priority information, and control the lighting of the building so that only the lamps located in the identified emergency escape route are turned on.

The reason is so that users in the building can be evacuated quickly and quickly.

In addition, the control management unit 147 of the building control management unit 140, when learning data, when motion is detected in a set space, extracts a feature based on the motion information, and based on the extracted feature and the classification criterion set in the learning model The classification standard is reinforced by resetting the preset classification standard, and the user state and energy state can be analyzed for each floor and room of the building by re-learning the classified data based on the reinforced classification standard.

Here, when the control management unit 147 of the building control management unit 140 analyzes the user state and energy state for each floor and room of the building, based on the reinforced classification criteria, the data is classified by occupants, age groups, and animals. And by re-learning the classified data, it is possible to analyze the user state and energy state for each floor and room of the building.

For example, when the control management unit 147 of the building control management unit 140 analyzes the user state and energy state for each floor and room of the building, based on the reinforced classification criteria, data by number of occupants, age groups, and animals By classifying and re-learning the classified data, it is possible to control air purification in consideration of the number of occupants, air-conditioning control in consideration of body temperature of indoor users, and power-saving operation control in consideration of users' commute time, but is not limited thereto.

As such, the present invention extracts a feature based on motion information, resets a preset classification criterion based on the extracted feature and a classification criterion set in the learning model, and strengthens the classification criterion, thereby limiting the presence detection sensor (for example, a user It is possible to supplement the problem of judgment error when there is no movement for a certain period of time even when the occupant is in the occupancy, and the problem that it is impossible to identify the number of people, age groups, animals, etc.).

For example, the number of occupants, age groups, animals, etc. may be identified using the image sensor and cross-checked with the occupancy sensor may have the effect of increasing the accuracy of occupancy.

As another example, the wearable device is equipped with an ID card function to manage the user's access, commuting, and check the user's heart rate, body temperature, and pulse, and cross-check the image sensor and occupancy sensor to create a comfortable environment in the building. You can control the air conditioning system.

Accordingly, the present invention can perform air purification control in consideration of the number of occupants, air conditioning control in consideration of body temperature of indoor users, and power saving operation control by time zone in consideration of users' commuting time. Taken together, artificial intelligence can determine the optimal conditions.

The present invention configured as described above uses artificial intelligence to learn the internal and external environments of the building and the state of the user in the building, and based on this, it is possible to precisely control the structure according to the occurrence of building energy and disasters.

In addition, the present invention can predict and determine the user's movement line and distribution status and user type in advance for each floor and each room of the building, so that it is possible to precisely control each floor and each room of the building.

In addition, according to the present invention, even if the same user exists in the same space, the user type (gender, age, disabled, pregnant woman, etc.) can be accurately identified through image information and biometric information, so that each floor and each room can be controlled in detail.

In addition, the present invention provides a comfortable indoor environment for users by controlling facilities and devices for each floor and each room before a predetermined time before users enter and exit each floor and each room based on learning data on user movement and distribution for each floor and each room. can be provided, and through this, it is possible to precisely control the energy consumption of each floor and each room.

In addition, the present invention, in an emergency situation, based on the user's image information and human body information, it is possible to quickly rescue the user by identifying the type and distribution status of each floor and each room.

As such, the present invention provides internal environmental information collected from temperature/humidity/gas/illuminance/infrared sensors installed inside a building and external temperature/humidity/wind direction/wind speed/rainfall/vibration sensors installed outside, etc., collected from the Meteorological Administration, etc. It is a system that can precisely integrate and manage building energy based on environmental information.

In particular, in the present invention, image data collected from image sensors and human body data collected from wearable devices in collecting environmental information are converted into big data with internal and external environmental information used for building management, and this is used as artificial intelligence technology. It can be implemented to enable precise energy management for each room, each floor, and other spaces of a building by processing

In addition, the present invention, in an emergency situation, by determining the priority of emergency rescue in consideration of the user's gender, age, disability, pregnant woman, health status, etc. may proceed.

2 is a flowchart illustrating an artificial intelligence-based building management method according to the present invention.

As shown in Figure 2, the present invention, first, it is possible to obtain the environment information inside and outside the building and the user information in the building (S10).

Next, the present invention can store and classify data on the obtained environment information and user information (S20).

Next, the present invention can learn the stored and classified data (S30).

Here, the present invention can learn the building user's gender, age, health status, disability, pregnancy status, movement lines, and data related to the resident location.

In some cases, the present invention may learn the user distribution status for each floor of the building and the user distribution status for each room on each floor of the building for each user's gender, age, health status, disability, and pregnancy status.

In another case, the present invention provides the user distribution status for each floor of the building and each room on each floor by month, day, holiday, season, national holiday, anniversary, specific event day, environmental condition, weather condition, and disaster condition. It is also possible to learn the user distribution status.

As another case, the present invention provides at least one of the first conditions including the user's gender, age, health condition, disability, and pregnancy status, and month, day, holiday, season, national holiday, anniversary, specific event date , the user distribution status by floor of the building and the user distribution status for each room on each floor of the building may be learned for each situation in which at least one of the second conditions including , environmental status, weather status, and disaster status overlaps each other.

And, according to the present invention, based on data learning, it is possible to analyze the user state and energy state for each floor and each room of the building (S40).

Here, in the present invention, based on data learning, the user's location and movement status are analyzed for each floor and room of the building, and based on this, the user distribution status and user movement status can be grasped for each floor and room of the building based on this.

In addition, the present invention can perform an integrated analysis of the energy use status for each floor and room of a building based on data learning.

Next, the present invention can predict and determine the user and energy state in advance based on the data learning and the user and energy state analysis results ( S50 ).

Here, the present invention predicts and determines the user distribution status and user movement status for each floor and room of a building based on data learning and user and energy state analysis results, and predicts and determines real-time energy usage for each floor and room of the building. can

In some cases, the present invention predicts and determines the user distribution status, user movement status, and user structure priorities by floor and room of a building according to a disaster situation based on data learning and user and energy status analysis results, and It is also possible to predict and determine the real-time energy consumption by floor and room of a building according to the following.

Next, according to the present invention, based on the prediction and determination result, it is possible to control and manage the user and energy state for each floor and each room of the building ( S60 ).

Here, in the present invention, when the distribution amount of users is predicted to be less than or equal to the reference distribution amount for each floor and each room of the building based on the prediction result, it is possible to control in advance so that the energy consumption for the corresponding floor and the corresponding room of the building is reduced.

In some cases, the present invention may perform real-time control so that, based on the determination result, the energy usage for the corresponding floor and the corresponding room of the building is reduced if the user distribution is less than the reference distribution for each floor and each room of the building based on the determination result.

As another case, the present invention may pre-control so that energy usage is increased for the floor and room of the building predicted to the place where the user intends to move based on the prediction result.

As another case, in the present invention, based on the determination result, it is possible to control in real time to increase the energy usage for the floor and room of the building to which the user moves.

As another case, in the present invention, when a disaster situation occurs, the user distribution status, user movement status, and user structure priority information can be generated for each floor and room of a building, and the corresponding information can be transmitted to an external rescue organization.

As another case, in the present invention, when a disaster situation occurs, a notification message is generated based on the user distribution status, user movement status, and user structure priority information for each floor and room of the building, and the generated notification message is transmitted to the corresponding user's terminal. can be sent to

As described above, the present invention can use artificial intelligence to learn the internal and external environments of the building and the user state in the building, and based on this, it is possible to precisely control the structure according to the occurrence of building energy and disasters.

In addition, the present invention can predict and determine the user's movement line and distribution status and user type in advance for each floor and each room of the building, so that each floor and each room of the building can be controlled in detail.

In addition, according to the present invention, even if the same user exists in the same space, the user type (gender, age, disabled, pregnant woman, etc.) can be accurately identified through image information and biometric information, so that each floor and each room can be controlled in detail.

In addition, the present invention provides a comfortable indoor environment for users by controlling facilities and devices for each floor and each room before a predetermined time before users enter and exit each floor and each room based on learning data on user movement and distribution for each floor and each room. can be provided, and through this, it is possible to precisely control the energy consumption of each floor and each room.

In addition, the present invention, in an emergency situation, based on the user's image information and human body information, it is possible to quickly rescue the user by identifying the type and distribution status of each floor and each room.

3 is a flowchart illustrating an artificial intelligence-based building management method according to another embodiment of the present invention.

As shown in FIG. 3 , in the present invention, first, it is possible to perform basic sensing to obtain environment information inside and outside the building and user information in the building ( S100 ).

Here, according to the present invention, an image sensor installed at a fixed position may first recognize and set fixed objects in a room.

Next, the present invention can extract features from the obtained environment information and user information, and store and classify data based on the extracted features (S200, S300).

Here, in the present invention, when a motion is detected in a set space, it is detected, classified into a person/child by a key, and a person/animal by a motion, and feature extraction can be performed, for example, an adult/child, an animal/human, etc. can be classified as

Next, the present invention can learn the stored and classified data through the learning model (S400).

Here, the present invention may perform AI learning for classification discrimination.

And, in the present invention, when a motion is detected, a feature may be extracted based on the motion information (S800, S900).

Here, in the present invention, it is possible to sense the image sensor and extract a feature when motion is detected.

Next, the present invention can strengthen the classification criterion by resetting the preset classification criterion based on the extracted features and the classification criterion set in the learning model (S500).

Here, the present invention may classify data by number of occupants, age groups, and animals based on the reinforced classification criteria.

Next, the present invention can detect the user state and energy state based on the reinforced classification criteria, and artificially control the user and energy state by floor and room of a building (S600. S700).

For example, the present invention may perform air purification control in consideration of the number of occupants, air conditioning control in consideration of body temperature of indoor users, and power saving operation control in consideration of commuting time of users.

As such, the present invention extracts a feature based on motion information, resets a preset classification criterion based on the extracted feature and a classification criterion set in the learning model, and strengthens the classification criterion, thereby limiting the presence detection sensor (for example, a user It is possible to supplement the problem of judgment error when there is no movement for a certain period of time even when the occupant is in the occupancy, and the problem that it is impossible to identify the number of people, age groups, animals, etc.).

For example, the number of occupants, age groups, animals, etc. may be identified using the image sensor and cross-checked with the occupancy sensor may have the effect of increasing the accuracy of occupancy.

As another example, the wearable device is equipped with an ID card function to manage the user's access, commuting, and check the user's heart rate, body temperature, and pulse, and cross-check the image sensor and occupancy sensor to create a comfortable environment in the building. You can control the air conditioning system.

Features, structures, effects, etc. described in the present inventions above are included in at least one embodiment of the present invention, and are not necessarily limited to only one embodiment. Furthermore, features, structures, effects, etc. illustrated in each embodiment can be combined or modified for other embodiments by those of ordinary skill in the art to which the embodiments belong. Accordingly, the contents related to such combinations and modifications should be interpreted as being included in the scope of the present invention.

In addition, although the embodiment has been described above, it is merely an example and does not limit the present invention, and those of ordinary skill in the art to which the present invention pertains are exemplified above in a range that does not depart from the essential characteristics of the present embodiment It can be seen that various modifications and applications that have not been made are possible. For example, each component specifically shown in the embodiment can be implemented by modification. And differences related to such modifications and applications should be construed as being included in the scope of the present invention defined in the appended claims.

100: building management system
110: environmental information detection unit
120: user information detection unit
130: communication department
140: building control management unit
150: weather information collection unit
160: Disaster information collection unit

Claims (10)

an environmental information sensing unit for detecting environmental information inside and outside the building;
a user information detection unit for detecting user information in the building;
a communication unit for transmitting and receiving the sensed environment information and user information; And,
A building control management unit for controlling the energy and disaster relief of the building based on the environment information and user information,
The building control management unit,
When the environment information and user information are received, the data for the received environment information and user information is stored and classified, the stored and classified data is learned, and the user for each floor and room of the building based on the data learning Analyze the state and energy state, predict and determine the user and energy state in advance based on the data learning and the user and energy state analysis result, and based on the prediction and determination result, the user and energy for each floor and room of the building When controlling and managing the state and predicting and judging the user and energy state in advance, based on the data learning and the user and energy state analysis results, the user distribution status and user movement status for each floor and room of the building according to the disaster situation and predicting and judging user structure priorities, and predicting and judging real-time energy usage for each floor and room of the building according to the disaster situation. According to claim 1,
The environmental information sensing unit,
an indoor environment information sensing unit for detecting the environment information of the building interior; And,
Artificial intelligence-based building management system, characterized in that it comprises an outdoor environment information sensing unit for detecting the environmental information outside the building. According to claim 1,
The user information detection unit,
an image information sensing unit for acquiring image information of a user located in the building; And,
Artificial intelligence-based building management system, characterized in that it comprises a human body information detection unit for acquiring the human body information of the user located in the building. According to claim 1,
a meteorological information collecting unit for collecting meteorological information from a first external server; And,
Artificial intelligence-based building management system, characterized in that it further comprises a disaster information collection unit for collecting disaster information from the second external server. According to claim 1,
The building control management unit,
When learning the data, artificial intelligence-based building management system, characterized in that for learning the data related to the gender, age, health status, disability, pregnancy status, movement route, resident location of the building user. According to claim 1,
The building control management unit,
When predicting and judging the user and energy state in advance, based on the data learning and the user and energy state analysis results, predict and determine the user distribution status and user movement status for each floor and room of the building, and for each floor of the building and an artificial intelligence-based building management system for predicting and judging real-time energy usage for each room. delete According to claim 1,
The building control management unit,
a storage unit for storing data on the received environment information and user information;
a classification unit for classifying data on the received environment information and user information;
a learning unit for learning the stored and classified data;
an analysis unit that analyzes the user state and energy state for each floor and room of the building based on the data learning;
a prediction and determination unit for predicting and determining in advance the user and energy state based on the data learning and the user and energy state analysis results; And,
Artificial intelligence-based building management system, characterized in that it comprises a control management unit for controlling and managing the user and energy state for each floor and each room of the building based on the prediction and determination result. According to claim 1,
The building control management unit,
When learning the data, when motion is detected in a set space, a feature is extracted based on motion information, and the classification criterion is strengthened by resetting a preset classification criterion based on the extracted feature and a classification criterion set in the learning model, Artificial intelligence-based building management system, characterized in that by re-learning the classified data based on the reinforced classification criteria, the user state and energy state are analyzed for each floor and room of the building. In the building management method of the artificial intelligence-based building management system,
acquiring environment information inside and outside the building and user information in the building;
storing and classifying data on the obtained environment information and user information;
learning the stored and classified data;
analyzing the user state and energy state for each floor and room of the building based on the data learning;
predicting and judging the user and energy state in advance based on the data learning and the user and energy state analysis results; And,
Controlling and managing the user and energy state for each floor and room of the building based on the prediction and determination result,
In the step of predicting and judging the user and energy state in advance, based on the data learning and the user and energy state analysis result, the user distribution status, user movement status, and user structure priority by floor and room of the building according to the disaster situation predicting and judging, and predicting and judging real-time energy usage for each floor and room of the building according to the disaster situation.

Images