KR102343710B1 - Method and System For Controlling Climate Change and Disaster Risk Intelligently - Google Patents

Abstract

The present invention relates to a system for intelligent disaster and climate change control, which includes: a sensor device in an area requiring water management; a central control center collecting sensor data from the sensor device and generating disaster package information by processing disaster prediction information generated by applying the sensor data to a pre-stored disaster prediction model; and a data platform server receiving the generated package information from the central control center and generating a disaster product reflecting disaster information demand characteristics by reprocessing the received disaster package information. The data platform server provides the disaster product to a consumer terminal in an application form via a wireless communication network.

Description

{Method and System For Controlling Climate Change and Disaster Risk Intelligently}

This specification relates to intelligent water resource management.

The Mekong River is a transboundary international river that flows through China, Laos, Myanmar, Thailand, Cambodia, and Vietnam, and is a very important point for the growth and coexistence of ASEAN. However, due to climate change, water disasters are frequent, flooding and dry water are frequent due to the failure of watershed management, and it is adversely affecting the lives of residents. Furthermore, it is pointed out as an impediment to the economic development of the Mekong River.

Floods and droughts occur frequently in the Mekong River basin. In particular, the Mekong Delta region, which is a low-lying region, is an area that has the greatest damage from subsidence as the precipitation level decreases and sea level rises downstream of the Mekong River. Natural disasters and water management are urgently needed. .

In addition, although the Mekong Delta region in southern Vietnam is very vulnerable to floods and droughts, there is no water disaster forecasting, warning, and monitoring system at the regional level, so an integrated system improvement at the national level is required.

Among about 240 global projects in the Mekong River basin over the past 10 years, there is no business model for disaster reduction and flood management in response to climate change.

The present specification aims to solve the above-mentioned problems and to build an integrated water disaster management and water management system for specific regions and regions by implementing an integrated business model at the national level.

In addition, the present specification provides integrated water disaster management in specific regions and regional units by implementing water disaster management and prediction models through various sensing systems for water resource management in specific regions, and advanced regional information provided by national organizations. and to establish a water management system.

In addition, the present specification aims to provide various data products to disaster disaster information consumers by providing the disaster disaster package information obtained through the aforementioned water disaster management and prediction model to the data platform service provider.

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

The intelligent disaster disaster and climate change management method according to an embodiment of the present specification includes the weather information, map information and disaster disaster information, acquiring data from a plurality of sensors built at a plurality of points located within a specific area; learning a model for predicting disaster information in the specific area using the obtained information as learning data; storing the learned prediction model; collecting sensing data from a plurality of sensors built at a plurality of points located within the specific area after the storage of the predictive model is completed; and defining the collected data as input data of the predictive model, and transmitting the predicted disaster and disaster information of the specific area to at least one entity based on the output information of the predictive model. do.

The intelligent disaster disaster and climate change management method includes: generating disaster disaster package information based on the predicted disaster disaster information; and transmitting the disaster and disaster package information to the at least one entity.

The disaster package information may include at least one of rainfall prediction information, precipitation prediction information, flood prediction information, an expected flooding area, an expected flooding time, a water level prediction, a drought expected area, and drought period prediction information.

The intelligent disaster and climate change management method may further include transmitting the disaster and disaster package information to a server of a data platform operator through a wireless communication unit.

The training data is a wake-up laser image data set collected for a predetermined time, and the training model may include at least one of an RNN, a GRU, and an LSTM model.

The learning data includes an atmospheric-ocean junction model simulation for a predetermined time in the past and observation data for a predetermined time in the past, and the results of the prediction model are, , may include at least one of the occurrence positions.

The intelligent disaster and climate change management method may further include a step of determining whether the stored prediction model needs to be updated on a predetermined basis or a predetermined period.

The predetermined criterion is, when a sudden global climate change is predicted based on the prediction model or external input data, when an abnormal climate with a similar pattern is detected in the specific area, the river level in the specific area is a predetermined range When it deviates, it may include at least one of wind directions among the weather information of the specific area.

An intelligent disaster disaster and climate change management method according to another embodiment of the present specification includes: building a sensor system in a specific area requiring water management; collecting sensor data by the sensor system; generating disaster package information by processing the generated disaster disaster prediction information by applying the sensor data to a pre-stored disaster disaster prediction model; transmitting the generated package information to a data platform server; generating, by the data platform server, an application product by reprocessing the received disaster and disaster package information in consideration of disaster and disaster information demand characteristics; and supplying, by the data platform server, the generated product through a mobile communication server through a consumer terminal.

An intelligent disaster disaster and climate change management system according to another embodiment of the present specification includes a sensor device built in a specific area requiring water management; a central control center that collects sensor data by the sensor device and processes the generated disaster disaster prediction information by applying the sensor data to a pre-stored disaster disaster prediction model to generate disaster disaster package information; and a data platform server that receives the generated package information from the central control center, and reprocesses the received disaster and disaster package information to generate a disaster disaster product in consideration of disaster disaster information demand characteristics; including, the data platform server provides the disaster disaster product in the form of an application to a consumer terminal through a wireless communication network.

The present specification provides an intelligent disaster disaster management method according to an embodiment, by implementing a national integrated business model, it is possible to build an integrated water disaster management and water management system in a specific region and regional unit.

In addition, according to an embodiment of the present specification, it is possible to increase the efficient management and utilization of climate information and disaster information, and data-based effective water resource management is possible.

In addition, according to an embodiment of the present specification, disaster disaster package information obtained through a water disaster management and prediction model is provided to a data platform service provider, thereby providing various data products to disaster disaster information consumers.

In addition, according to an embodiment of the present specification, the disaster disaster information and climate information business market can be expanded.

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

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as a part of the detailed description to help the understanding of the present specification, provide embodiments of the present specification, and together with the detailed description, explain the technical features of the present specification.
1 is a diagram for illustratively explaining an environment in which an intelligent disaster disaster management method is implemented in embodiments of the present specification.
2 is a schematic system diagram for explaining a business model for implementing an intelligent disaster disaster management method according to an embodiment of the present specification.
3 is an example of a sequence diagram for implementing an intelligent disaster disaster management method according to an embodiment of the present specification.
4 to 5 are diagrams for explaining an example of infrastructure construction in a specific area described in FIG. 3 .
6 is a block diagram illustrating a disaster disaster management system according to an embodiment of the present specification.
FIG. 7 is a diagram for exemplarily explaining a learning system of a disaster disaster prediction model in the central control center among the disaster disaster management system shown in FIG. 6 .
8 is a flowchart of a learning method of a disaster disaster prediction model in a central control center in a disaster disaster management system according to an embodiment of the present specification.
9 is a flowchart of a method of generating and utilizing disaster disaster package information based on on-site information of a specific area in the central control center according to an embodiment of the present specification.
10 is a flowchart of a method of providing a disaster disaster service through a business model according to the implementation of the disaster disaster management system according to an embodiment of the present specification.
11 is a diagram for explaining another example of a disaster service provided through a disaster management system according to an embodiment of the present specification.
BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as a part of the detailed description to facilitate the understanding of the present invention, provide embodiments of the present invention, and together with the detailed description, explain the technical features of the present invention.

Hereinafter, the embodiments disclosed in the present specification will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numbers regardless of reference numerals, and redundant description thereof will be omitted. The suffixes "module" and "part" for components used in the following description are given or mixed in consideration of only the ease of writing the specification, and do not have distinct meanings or roles by themselves. In addition, in describing the embodiments disclosed in the present specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in the present specification, and the technical idea disclosed herein is not limited by the accompanying drawings, and all changes included in the spirit and scope of the present invention , should be understood to include equivalents or substitutes.

Terms including an ordinal number such as 1st, 2nd, etc. may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

When an element is referred to as being “connected” or “connected” to another element, it is understood that it may be directly connected or connected to the other element, but other elements may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle.

The singular expression includes the plural expression unless the context clearly dictates otherwise.

In the present application, terms such as “comprises” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

1 is a diagram for illustratively explaining an environment in which an intelligent disaster disaster management method is implemented in embodiments of the present specification.

Referring to Figure 1, the region where the disaster disaster service is provided in this specification includes the Mekong Delta region, but the scope of the present specification is not limited thereto. Of course, it is also possible to include all areas where disaster prevention and response are impossible.

The economic activity may include transportation, tourism, agriculture, aquaculture, and the like.

In the Mekong Delta region in which the disaster disaster service is provided according to an embodiment of the present specification, housing areas such as floating houses are located centered on rivers, and as there is an area running agriculture and transportation business in the background, local residents' It can be defined as a special area where residence, livelihood, travel business of foreigners, and ecosystem maintenance activities are inextricably linked with rivers and form an organic relationship. Throughout this specification, a specific region means a region with the above-described special characteristics, which is not limited to a region included in a specific country, and is an area concurrently in contact with the borders of multiple countries and multiple countries, and is a public institution Alternatively, it may be an area where water resources can be efficiently used while preventing damage from disasters only through the systematic management of the government. In addition, the specific region may include a region having a complex tributary, a topographical relationship with the complex tributary, and a complex topographical characteristic (eg, a region having a large change in land height) as a downstream rather than an upstream of a river.

Therefore, the disaster disaster service to which this specification is applied may be different from a general area in which at least a substantial part of a river, a residential area, a business area, etc. are physically and spatially separated.

2 is a schematic system diagram for explaining a business model for implementing an intelligent disaster disaster management method according to an embodiment of the present specification.

As described with reference to FIG. 1, in order to provide disaster disaster prevention, response and application services through the disaster disaster management system and the system according to an embodiment of the present specification, private companies, public institutions, local governments, government agencies, etc. A service or function performing entity may exist throughout the industry.

Referring to Figure 2, the components (entities, entities) of the system for the implementation of the business model for implementing an embodiment of the present specification is a central control center (Control Center, 210), ICT (Information & Communications Technology) company (ICT Provider, 220), a data platform provider (Data Platform Provider, 230), and may include a mobile communication provider (Mobile Communication Provider, 240).

The central control center 210, as a data station, generates disaster and disaster package information based on the sensing data collected in the aforementioned specific area. The generated disaster and disaster package information may be directly provided to a government agency or public institution (including a local government) 211 , a local resident 212 in a specific area, or may be provided to a data platform operator 230 . The central control center 210 may be located in the specific area, preferably in the Mekong Delta, in particular, in a location where damage from disasters is frequent.

The central control center 210 may be referred to as a data station or a data center, and may store data acquired from sensor systems, meteorological and disaster-related government agencies, research institutes, etc. It may consist of a UPS for According to one embodiment of the present specification, the disaster and disaster package information generated by the central control center 210 may be directly provided to a specific local resident 212, a local government agency 211, and/or a data platform operator 230. can

In FIG. 2 , the central control center 210 is a data station operated by a government agency. The government agency may include an agency that manages water resources, a public agency that has a database system for water resource management, or an agency that creates a new business model based on water resources.

Meanwhile, in FIG. 2, the government agency is limited to the central control center 210, but the central control center 210 is an agency that manages data such as data collection, data generation, and data transmission, but the In the business model, other government agencies may exist in addition to the central control center 210 . For example, examples of the other government agencies include an infrastructure building organization (eg, Korea Rural Community Corporation) that builds flood management and water storage facilities in the specific area. The infrastructure construction institution is a water resource specialized institution, and can build clapboards, flood barriers, irrigation facilities, etc. to identify areas vulnerable to climate change in the Mekong Delta, prevent flooding during floods, and solve water shortages during drought. The infrastructure building institution may be paid a predetermined fee for a certain period and transfer know-how and technology related to facility management and construction to local government agencies and companies.

In addition, a government agency to which the specific region belongs may also be an element necessary for the implementation of the business model. For example, the government agency to which the specific region belongs is, for example, 1) Meteorological research institute, weather satellite center, weather radar center, aircraft meteorological service, supercomputer center for meteorological service, etc. Administrative agency in charge of business, 2) Administrative agency in charge of investment and operation of social overhead capital such as roads, railroads, air transport, shipping, and tourism, 3) In charge of overall information and communication such as mail, telephone, telegraph, and the Internet Administrative agencies may be included.

The ICT company 220 builds a sensor system in the specific area described above. For example, the ICT company 220 may build a sensor system in a specific area to build a water resource infrastructure in the Mekong Delta region. The sensor system detects the river water level, water quantity, flow rate, and the like. The ICT company 220 may build a sensor system capable of monitoring the river in real time at a certain point from the upstream to the downstream of a specific area (Mekong Delta) for flood prediction and prevention. On the other hand, the sensor system may be built by the aforementioned infrastructure building organization.

The data platform operator 230 receives disaster disaster package information from the central control center 210 . The data platform operator 230 may be defined as an operator that collects, analyzes, processes, and stores data such as devices, Internet/social media, sensor data, and public/company data, and visualizes knowledge after data processing to provide smart services. .

The data platform operator 230 analyzes, processes, and stores package information for prediction of disasters and climate change provided from the central control center 210, and can generate products that can provide the package information to consumers related to disasters. have.

The mobile communication operator 240 may provide package information of the central control center 210 in the form of various applications to the user 241 and the user terminal 242 in connection with the data platform operator 230 .

In the above, the constituent entities of the business model that can be implemented through an embodiment of the present specification and the schematic functions of each entity have been described with reference to FIG. 2 . Hereinafter, an overall implementation scenario of the business model will be described with reference to FIG. 3 .

3 is an example of a sequence diagram for implementing an intelligent disaster disaster management method according to an embodiment of the present specification. In addition, it will be described with reference to the following drawings necessary for the description of FIG. 3 together. In addition, the constituent entities of the business model according to an embodiment of the present specification are defined as in FIG. 3 for convenience of description. The constituent entities of the business model may include, for example, ICT institutions, government institutions, Web Cloud (data platform) companies, mobile communication operators, consumers, and the like. Here, the government agency may be divided into a plurality of different government agencies according to functions.

In FIG. 3, for convenience of explanation, government agency 1 that builds infrastructure in a specific area, government agency 2 that performs weather information, geographic information on land, and information and communication-related tasks as a government agency of a specific area, and a central control center (data station ) can be divided into 3 government agencies responsible for the functions of In the present specification, government agencies are divided as above for convenience of explanation, but it goes without saying that the government agencies may be further subdivided or integrated as needed.

The government agency 1 may include the Korea Rural Community Corporation, etc., and the government agency 2 may include the Korea Meteorological Administration, the Ministry of Land, Infrastructure and Transport, the Ministry of Science and ICT, the Ministry of Agriculture, Food and Rural Affairs, and the like.

Government agency 1 can build flood management and water storage facilities in a specific area (S301)

In addition, the ICT company may install a sensor system for efficiently managing the water resources of the built facility in the vicinity of the built facility (S303)

4 to 5 are diagrams for explaining an example of infrastructure construction in a specific area described in FIG. 3 .

Referring to FIG. 4 , the specific area may include a main river area 400 and a water blocking facility 430 for preventing damage to residents of a specific area due to the overflow of the river. The specific area may be divided into a plurality of sectors, and each center may be divided such that a house 440 , an ecosystem, and agricultural facilities 450 form one cluster. One sector may include a water storage facility 410 . The water storage facility included in one sector may be connected to the water storage facility included in another neighboring sector through a predetermined water channel facility 420 .

The water barrier facility 430 may be constructed by a method possessed by the government agency 1, and may be constructed with a gravity method such as a dam type, a box type, a caisson cell type, and a sheet pile method such as a self-supporting type or a ring beam type, In the present specification, in addition to the above-described construction method, a new construction method suitable for the local situation of a specific region (Mekong Delta region) may be applied.

Meanwhile, referring to FIG. 4 , the ICT company may build the sensor system 510 along the periphery of the main waterway of the main river 500 . The sensor system 510 may be built every predetermined distance along the main waterway. All of the conventional sensor technologies for water resource management may be applied to the sensor system 510, and any sensing technology owned by an ICT company equipped with an optimal sensing technology for monitoring water resources in the Mekong Delta may be included, of course. The sensor system 510 may further include a communication module for transmitting sensor data to the central control center 520 .

Government agency 3 may 1) build a disaster disaster prediction model capable of predicting disaster information in a specific area or generating disaster response information based on the sensed data received from the built-up sensor system. Here, government agency 3 will be referred to as the central control center for convenience of explanation. 2) The central control center can generate disaster and disaster package information by applying the sensing data to the built prediction model.

The function of the central control center can be largely divided into the above-mentioned function 1) and function 2). In relation to function 1), the central control center may collect sensor data (S305), obtain weather information, road network information, and IoT (Internet of Things) communication network information (S307) to build a predictive model. In addition, in relation to function 2), the central control center may create a disaster disaster information package (S309)

The process of constructing a predictive model and generating disaster and disaster package information of the central control center will be described in more detail with reference to FIGS. 6 to 9 .

6 is a block diagram illustrating a disaster disaster management system according to an embodiment of the present specification.

Referring to FIG. 6 , the server 600 of the central control center includes a data learning unit 610 , a predictive model 620 learned through the data learning unit, and a processor 630 controlling all functions related to data learning and application of the learning model. ) is included.

The data learning unit 610 may include a data collection unit 611 for collecting learning data, and a learning system 612 for training the collected learning data.

The data collection unit 611 may acquire sensing data collected from regional information 601 , weather data 603 , and sensor 605 of a specific region (Mekong Delta region). The data collection unit 611 may include a wireless communication unit. The area information 601 may include map information, a difference in river and sea level, and a height difference between the zone and the like. The area information 601 may further include information on which disaster history in a specific area is mapped, rather than simple map information. Also, the local information 601 may be collected in real time by the data collection unit 611 whenever it is updated by a government agency. The meteorological data 603 may include raw data acquired through radar, aviation, or weather satellite, or data obtained by analyzing and processing the raw data. The area information 601 and the weather data 603 are data obtained through a government agency to which a specific area belongs. Meanwhile, the meteorological data 603 may be acquired from an external organization such as an international meteorological institution in addition to a government institution to which the specific region belongs. The raw data obtained through the weather satellite may include a satellite image. A meteorological satellite is an artificial satellite that is located above the earth and observes various weather elements such as the earth's cloud state. have.

The intelligent disaster disaster and climate change management system according to an embodiment of the present specification may acquire a satellite image from a Communication, Ocean and Meteorological Satellite (COMS). Chollian Satellite 2A covers the FD (Full Disk) area of the basic image (16 channels) once for 10 minutes, the Extended Local Area (ELA) area of the Korean Peninsula 5 times, and the LA, Local area 5 times can be observed. In particular, by extracting the East Asian region from global observation and servicing at 10-minute intervals, satellite images of the Mekong Delta region can be utilized for analysis. The phase image may receive a satellite image from the National Meteorological Satellite Center and/or the Korea Meteorological Administration. have.

The above-mentioned satellite image is not limited to the clairvoyant satellite image and may include images obtained from various weather satellites.

It goes without saying that the learning data collected through the data collection unit is not limited to the above-described examples and may be added or subtracted according to the purpose of learning. The operation of the learning system 612 will be described in more detail with reference to FIG. 7 .

The processor 630 may store the prediction model 620 in the memory to complete the preparation for application of the disaster disaster prediction model. After the provision of the predictive model is completed, the processor 630 may generate disaster disaster package information based on the sensed data. The processor 630 may build a data platform so that the generated package information can be used according to various demand patterns of government agencies, local governments, private companies, and local residents in a specific area, or may provide package information to data platform operators. have.

FIG. 7 is a diagram for exemplarily explaining a learning system of a disaster disaster prediction model in the central control center among the disaster disaster management system shown in FIG. 6 .

Learning of the disaster disaster prediction model in the central control center disclosed in this specification may be implemented in a computer device. The computer device may include an AI processor 100 and a memory 150 . The computer device may include an electronic device including the AI processor 100 capable of performing AI processing, or a server including the AI processor 100 .

The AI processor 100 is included in a specific area, but through sensor data obtained from a plurality of sensor systems having different constructed location information to automatically predict disaster and disaster prediction information, climate information, etc. To train a learning model In order to do so, it may include a data learning unit 100 for storing the learned model, a memory 150 for storing the learned model, and a data processing unit 140 for processing data through a learning model for sensor data newly acquired after model learning is completed. .

The computer device is a device capable of learning a neural network, and may be implemented as various electronic devices such as a server, a desktop PC, a notebook PC, and a tablet PC.

The AI processor 100 may learn the neural network through the model learning unit 130 using a program stored in the memory 150 . In particular, the AI processor 100 may learn a neural network for predicting disasters, weather changes, and climate changes in a specific region.

Here, a neural network for predicting a disaster, weather change, and climate change in a specific region may be designed to simulate the human brain structure on a computer, and a plurality of weighted neural networks simulating neurons of a human neural network may include network nodes of The plurality of network modes may transmit and receive data according to a connection relationship, respectively, so as to simulate a synaptic activity of a neuron in which a neuron sends and receives a signal through a synapse. Here, the neural network may include a deep learning model developed from a neural network model. In a deep learning model, a plurality of network nodes can send and receive data according to a convolutional connection relationship while being located in different layers. Examples of neural network models include deep neural networks (DNN), convolutional deep neural networks (CNN), Recurrent Boltzmann Machine (RNN), Restricted Boltzmann Machine (RBM), deep trust It includes various deep learning techniques such as neural networks (DBN, deep belief networks) and deep Q-networks, and can be applied to fields such as computer vision, speech recognition, natural language processing, and voice/signal processing.

Meanwhile, the processor performing the above-described function may be a general-purpose processor (eg, CPU), but may be an AI-only processor (eg, GPU, NPU) for artificial intelligence learning.

The memory 150 may store various programs and data necessary for the operation of the AI processor 100 . The memory 150 may be implemented as a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SDD). The memory 150 is accessed by the AI processor 100 , and reading/writing/modification/deletion/update of data by the AI processor 100 may be performed. Also, the memory 150 may store a neural network model (eg, an artificial neural network model, a classification model, etc.) generated through a learning algorithm for prediction according to an embodiment of the present specification.

Meanwhile, the AI processor 100 may include a data learning unit 120 that learns a neural network for prediction.

The data learning unit 110 may learn a criterion regarding which training data to use for prediction and how to classify and recognize data using the training data. The data learning unit 110 may learn the deep learning model by acquiring learning data to be used for learning and applying the acquired learning data to the deep learning model.

The data learning unit 110 may be manufactured in the form of at least one hardware chip and mounted on the computer device and/or the AI processor 100 . For example, the data learning unit 110 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or may be manufactured as a part of a general-purpose processor (CPU) or a graphics-only processor (GPU) for a computer device and/or AI It may be mounted on the processor 100 .

Also, the data learning unit 110 may be implemented as a software module. When implemented as a software module (or a program module including instructions), the software module may be stored in a computer-readable non-transitory computer readable medium. In this case, the at least one software module may be provided by an operating system (OS) or may be provided by an application.

The data learning unit 110 may include a training data acquiring unit 120 and a model learning unit 130 .

The training data acquisition unit 120 may acquire training data required for a neural network model for classifying and recognizing data. For example, local information, weather information, and/or a weather prediction label according to the local information and the weather information of a specific area of the training data may be acquired.

The model learning unit 130 may use the acquired training data to learn the neural network model to have a criterion for determining how to classify predetermined data. In this case, the model learning unit 130 may train the neural network model through supervised learning using at least a portion of the training data as a criterion for determination. Alternatively, the model learning unit 130 may learn the neural network model through unsupervised learning for discovering a judgment criterion by self-learning using learning data without guidance. Also, the model learning unit 24 may train the neural network model through reinforcement learning using feedback on whether the result of the situation determination according to the learning is correct. Also, the model learning unit 130 may train the neural network model by using a learning algorithm including an error back-propagation method or a gradient decent method.

When the neural network model is learned, the model learning unit 130 may store the learned neural network model in the memory 150 . The model learning unit 130 may store the learned neural network model in the memory of the central control center and/or the server connected to the central control center through a wired or wireless network.

The data learning unit 110 further includes a training data preprocessor (not shown) and a training data selection unit (not shown) to improve the analysis result of the recognition model or to save resources or time required for generating the recognition model You may.

The learning data preprocessor may preprocess the acquired data so that the acquired data can be used for learning for situation determination. Also, the learning data selection unit may select data necessary for learning from among the training data acquired by the training data acquiring unit 120 or the training data preprocessed by the preprocessing unit. The selected training data may be provided to the model learning unit 130 .

The operation of the learning data preprocessor and/or the learning data selection unit may be processed separately from the learning data acquisition unit 611 illustrated in FIG. 6 , or may be implemented by being integrated into the training data acquisition unit 611 .

In addition, the data learning unit 110 may further include a model evaluation unit (not shown) in order to improve the analysis result of the neural network model.

The model evaluator may input evaluation data to the neural network model and, when an analysis result output from the evaluation data does not satisfy a predetermined criterion, cause the model learning unit 130 to learn again. In this case, the evaluation data may be predefined data for evaluating the recognition model. As an example, the model evaluation unit may evaluate as not satisfying a predetermined criterion when, among the analysis results of the learned recognition model for the evaluation data, the number or ratio of evaluation data for which the analysis result is not accurate exceeds a preset threshold. have.

The data processing unit 140 applies the input data to the learning model (classifier) stored in the memory to automatically output the disaster disaster prediction and response method in a specific area.

Meanwhile, although not shown, the server 600 of the central control center shown in FIG. 6 may further include a communication unit (not shown). The communication unit may transmit the AI processing result by the AI processor 100 to an external electronic device (eg, a network server, etc.).

On the other hand, although the computing device shown in FIG. 6 has been functionally divided into the AI processor 100, the memory 150, and the communication unit (not shown), the above-described components are integrated into one module and are called AI modules. It should be pointed out that it may be

Hereinafter, a method of learning the disaster disaster prediction model in the central control center will be described in more detail with reference to FIGS. 6 and 7 .

8 is a flowchart of a method of learning a disaster disaster prediction model in a central control center in a disaster disaster management system according to an embodiment of the present specification. The learning method of FIG. 5 may be executed under the control of the processor 630 shown in FIG. 6 .

The processor may collect weather information, map information, disaster information, and sensing data of a specific region (S800).

The processor may define the collected data as learning data and train a disaster disaster and climate information prediction model (S810).

The processor may store the learned disaster disaster and climate information prediction model in the memory (S820).

The processor may determine whether it is necessary to update the learned predictive model based on a predetermined criterion or monitoring according to a predetermined period (S830). The predetermined criterion may include disaster disaster situation information that persists in a specific region when data related to abrupt global climate change is collected. The data related to abrupt global climate change may include a case in which new forecast data for global climate change is input, not limited to the specific region. In this case, if only the pre-learned prediction model is applied, it may not be possible to predict a disaster in a specific area due to climate change in the near future. On the other hand, if data that has a similar pattern of meteorological information that is not at the level that will cause a sudden disaster and continues at regular intervals is detected, the reliability of the prediction model may be lowered due to not updating the prediction model, so even in this case, the prediction model It may be determined that an update is necessary.

Meanwhile, the processor may determine the need to update the prediction model based on the water level of a specific local river. For example, the processor determines whether or not the prediction model needs to be updated in consideration of the number of times the water level of the river deviates from a certain range, or the number of times it exceeds the predetermined range based on a certain period, the number of days that the state outside the predetermined range continues, etc. can judge In particular, in the case of the Mekong Delta region, the damage caused by the shortage of agricultural water supply due to the drought is considerable. Furthermore, if the dry state of farmland continues due to prolonged drought, seawater flooded into river basins at high tide cannot be washed out at low tide, resulting in considerable damage to farmland due to flooding.

In addition, the processor may determine the need to update the prediction model based on the wind direction among the weather information of a specific area. For example, when the wind direction blows from the sea to the land, it can be determined that there is a need to update the prediction model when the wind direction continues for a certain period and for a certain time even though there is currently no risk of flooding.

9 is a flowchart of a method of generating and utilizing disaster disaster package information based on on-site information of a specific area in the central control center according to an embodiment of the present specification. The method of FIG. 9 may be executed under the control of the processor 630 shown in FIG. 6 .

After the prediction model is completed, the sensing data collected from the sensor system will be used to predict actual disasters.

The processor collects sensing data (S900). The processor may obtain disaster disaster prediction information by applying the collected data to the learned prediction model (S910).

The processor may generate disaster disaster package information based on the disaster disaster prediction information obtained through the prediction model. The prediction information obtained by the prediction model and the disaster disaster package information may be different. For example, the disaster and disaster package information may include, in addition to information for predicting a change in the state of water resources in a specific area, area information where damage is expected in relation to the specific area. The disaster and disaster package information has a macroscopic range of climate information, meteorological information, such as flood prediction, flood prediction area, flood prediction time, water level prediction, drought prediction area, and situation information of a specific area at the time the sensing data is acquired, such as drought period prediction. information, and may include disaster and disaster information.

The processor may transmit the disaster package information to the web cloud (S930). Here, the web cloud may be a server of a data platform operator.

With reference to FIG. 3 again, after the central control center generates disaster and disaster package information, data transmission/reception with the constituent units of the business model and cost burden accordingly will be described. Meanwhile, FIG. 10 is a flowchart of a method of providing a disaster disaster service through a business model according to the implementation of the disaster disaster management system according to an embodiment of the present specification.

3 and 10, the central control center generates disaster disaster package information (S1000 in FIG. 10), and transmits the generated disaster disaster package information to the server of the data platform company (S311, S1110). A data platform company can create and sell a new climate information product using the package information. The data platform company pays a price for using the package information received from the government agency (S311).

The data platform company can analyze and process the received package information and reprocess it into data that has product potential ( 313 ). The data platform company can provide a climate information product to consumers through the application by creating an application program (application) utilizing the package information (S1130).

The package information may have different reprocessing characteristics based on the attributes of the consumer. Accordingly, the data platform company can analyze and process data in consideration of the characteristics of consumers of disaster and disaster information (S1120). For example, if the consumer is a local resident performing agriculture in a specific area, the data platform company reproduces various information that can affect the agriculture of local farmers through package information, or prepares for a disaster that affects agriculture can provide a way. In addition, when the consumer is a traveler, the data platform company may provide a climate product that can affect travel by considering the consumer's current location, a travel destination included in a travel itinerary, and the like.

The reprocessed package information may be provided to a customer through a mobile communication service provider.

On the other hand, the mobile communication service provider may pay a price for using the reprocessed package information provided by the data platform company (S317). In addition, the consumer may pay the communication cost to the mobile communication service provider (S321).

On the other hand, disaster and disaster package information reprocessed through a data platform company is data generated by government agencies, has a strong public interest, and there is a concern that it may be abused by consumers who need disaster and disaster package information. Accordingly, the central control center needs to manage public data even after a package of disaster and disaster information is created and distributed through a predetermined path. Accordingly, the subject who actually uses the disaster and disaster package information or uses the reprocessed disaster and disaster package information pays the information management cost to the central control center (S318). For example, the information management cost may be defined as borne by the mobile communication service provider.

Meanwhile, in FIG. 10 , the central control center may transmit the generated disaster and disaster package information directly to the government/public institution without going through a data platform operator. In the case of data platform operators, the purpose is to create and sell climate products by analyzing the needs of consumers, whereas the disaster and disaster package information is not for commercial use, but for disaster and disaster information through reprocessing necessary for public interest purposes. It can also be processed so that it is provided free of charge to the consumers who need it.

On the other hand, according to an embodiment of the present specification, the disaster disaster package information generated by the central control center may be used as a water resource utilization model for creating economic value for the local community in a specific area.

11 is a diagram for explaining another example of a disaster service provided through a disaster management system according to an embodiment of the present specification. Referring to FIG. 11 , as shown in FIG. 4 , a specific area is divided into a plurality of sectors, and one sector provides water supply with a water storage area ( 410 in FIG. 4 / 520 in FIG. 11 ) and neighboring sectors 530 and 540 . There may be a water channel or the like (not shown) for the purpose. In particular, in the Mekong Delta, a representative 520 representing a plurality of residents included in a specific sector manages the water storage area due to the Vietnamese government's policy, and the plurality of residents use the water resources managed in the water storage area. Instead, you can implement a pay-as-you-go business model.

The present invention described above can be implemented as computer-readable codes on a medium in which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. There is also a carrier wave (eg, transmission over the Internet) that is implemented in the form of. Accordingly, the above detailed description should not be construed as restrictive in all respects but as exemplary. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (10)

The central control center receives the weather information, map information and disaster information from an organization that manages meteorological information, map information, and disaster and disaster information of a specific area requiring water management; acquiring data from a sensor, the specific area being divided into a plurality of sectors, one sector having a water storage area and a water channel for supplying water with a neighboring sector;
learning, by the central control center, a model for predicting disaster information in the specific area by using the acquired information as learning data;
collecting, by the central control center, the learned prediction model, and after the storage of the prediction model is completed, sensing data from a plurality of sensors constructed at a plurality of points located within the specific area;
The central control center defines the collected data as the input data of the predictive model, and transmits the predicted disaster and disaster information of the specific area to at least one entity based on the output information of the predictive model to do;
generating, by the central control center, disaster disaster package information based on the predicted disaster information;
transmitting, by the central control center, the disaster disaster package information to a server of a data platform operator through a wireless communication unit; and
The server of the data platform operator analyzes and reprocesses the disaster and disaster package information to generate a climate information application based on the properties of the consumers in the specific area, and provides a climate product service through the terminal of the consumers in the specific area;
An intelligent disaster disaster and climate change management method, including
delete The method of claim 1,
The disaster and disaster package information is,
An intelligent disaster and climate change management method, comprising at least one of rainfall forecast information, precipitation forecast information, flood forecast information, flood forecast area, flood forecast time, water level forecast, drought forecast area, and drought period forecast information.
delete The method of claim 1,
The learning data is a wake-up laser image data set collected for a predetermined time,
The learned prediction model, an intelligent disaster disaster and climate change management method, characterized in that it comprises at least one of RNN, GRU, LSTM model.
The method of claim 1,
The learning data includes an atmospheric-ocean junction model simulation for a predetermined time in the past and observation data for a predetermined time in the past,
The result of the prediction model is,
Intelligent disaster disaster and climate change management method, characterized in that it includes at least one of the occurrence of El Niño, intensity, and location in the characteristic area.
The method of claim 1,
determining, by the central control center, whether it is necessary to update the stored prediction model on a predetermined basis or a predetermined period;
Intelligent disaster disaster and climate change management method, characterized in that it further comprises.
8. The method of claim 7,
The predetermined criterion is
When a sudden global climate change is predicted based on the prediction model or external input data, when an abnormal climate with a similar pattern is detected in the specific region, when the river level in the specific region is out of a predetermined range, when the specific region Intelligent disaster disaster and climate change management method, characterized in that it includes at least one of the wind direction among the weather information of the.
delete a sensor device built in a specific area requiring water management, wherein the specific area is divided into a plurality of sectors, and one sector includes a water storage area and a water channel for supplying water with a neighboring sector;
a central control center that collects sensor data by the sensor device and processes the generated disaster disaster prediction information by applying the sensor data to a pre-stored disaster disaster prediction model to generate disaster disaster package information; and
Receives the generated disaster and disaster package information from the central control center, analyzes and reprocesses the received disaster and disaster package information to create a climate information application considering the characteristics of demand for disaster and disaster information, and through a wireless communication unit, consumers in the specific area a data platform server that provides a climate product service through a terminal;
An intelligent disaster disaster and climate change management system that includes.

Images