Flood damage prediction analysis device based on ordered logistic regression analysis

Abstract

A flood damage prediction analysis device based on ordered logistic regression analysis is provided. [Solution] The accuracy and reliability of flood damage prediction are further improved by including a data collection module that collects flood damage related information data including accumulated precipitation and flood damage history data for a specific area; a data extraction module that extracts flood damage location and damage extent data according to the cumulative precipitation based on the collected flood damage related information data; a data analysis module that receives the flood damage location and damage extent data according to the extracted cumulative precipitation and generates a flood damage prediction analysis model for predicting the flood damage risk of the specific area according to the cumulative precipitation using a predetermined ordinal logistic regression analysis technique; and a flood damage category setting module that uses the generated flood damage prediction analysis model to predict the probability that each cumulative precipitation falls into a flood damage level category and sets a cumulative precipitation range for each flood damage level category.

Description

[Technical field]

[0001] The present invention relates to a flood damage prediction and analysis device based on ordered logistic regression analysis. [Background technology]

[0002] In recent years, as flood damage caused by torrential rains has led to frequent disasters and safety accidents in daily life that threaten the safety of the people, there is a growing need for services that can help predict damage in advance and prevent accidents.

[0003] As a result, there have been increasing attempts to develop flood risk services using flood damage prediction models. Conventional flood damage prediction technology assigns a score based on the amount of precipitation per hour. Hourly precipitation indicates the amount of precipitation that falls intensively over a one-hour period, and is an indicator that better conveys the intensity of precipitation than cumulative precipitation or daily precipitation.

[0004] However, existing flood damage prediction technologies have different flood damage standards for different regions. For example, a heavy rain warning is usually issued when the hourly precipitation is 20mm or more, or the daily precipitation is 80mm or more. However, the scale of flood damage can vary even with the same precipitation depending on various factors that cause flood damage.

[0005] In addition, the conventional method of scoring based on the amount of precipitation per hour is limited to one-off data, and has limitations in terms of accurate and reliable prediction of flood damage.

[0006] In addition, many of the organizations that provide information on flooding only grasp the flooding situation based on the Japan Meteorological Agency's forecast information, and the reality is that they do not inform citizens early on about the risk of sudden flooding. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Korean Patent Publication No. 10-2023-0102277 (Published on July 7, 2023) Summary of the Invention [Problem to be solved by the invention]

[0008] The present invention has been made to solve the above-mentioned problems, and its purpose is to provide a flood damage prediction and analysis device based on ordered logistic regression analysis, which applies ordered logistic regression analysis to accumulated precipitation in days / hours / minutes and flood damage history data in hours / minutes to set a standard range of accumulated precipitation according to the degree of flood damage in a specific area, thereby making it possible to easily determine the risk of flood damage by city / county / ward just by knowing the accumulated precipitation value, and further improve the accuracy and reliability of flood damage predictions. [Means for solving the problem]

[0009] In order to achieve the above object, one aspect of the present invention provides a flood damage prediction and analysis device based on ordered logistic regression analysis, including: a data collection module that collects flood damage-related information data including accumulated precipitation and flood damage history data for a specific region from an external source; a data extraction module that receives the flood damage-related information data for the specific region collected from the data collection module and extracts flood damage location and damage extent data for the specific region according to the accumulated precipitation based on the data; a data analysis module that receives the flood damage location and damage extent data for the specific region according to the cumulative precipitation extracted from the data extraction module and generates a flood damage prediction analysis model for predicting the flood damage risk for the specific region according to the cumulative precipitation based on the data using a predetermined ordered logistic regression analysis technique; and a flood damage category setting module that predicts the probability that each cumulative precipitation falls into a predetermined flood damage level category using the flood damage prediction analysis model generated from the data analysis module, and sets a cumulative precipitation range for each flood damage level stage according to the predicted probability value.

[0010] Here, it is preferable that the system further includes a data summarization module that receives flood damage related information data for the specific region collected from the data collection module, summarizes the flood damage related information data for the specific region according to the accumulated precipitation using pre-set data column names, formats and feature elements, and transmits the results of the summarized information data to the data extraction module.

[0011] Preferably, the data extraction module can extract flood damage location and damage extent data for the specific area according to the accumulated precipitation based on the results of summarized information data for flood damage-related information data for the specific area transmitted from the data summarization module.

[0012] Preferably, the name of the pre-defined data column may include at least one of the following column names: date and time of receipt of flood damage, address of flood-damaged area, details of flood damage, and extent of flood damage.

[0013] Preferably, the degree of flood damage in the specific area extracted from the data extraction module can be composed of a first stage of "minor" when the flood damage is very little or only superficial, a second stage of "normal" when the flood damage is of intermediate level and surrounding facilities are affected, and a third stage of "serious" when the damage is severe and large-scale flooding causes loss of life and serious damage.

[0014] Preferably, the system may further include a data pre-processing module that receives flood damage related information data for the specific region collected from the data collection module, and based on the received information data, if information data for a column of the degree of flood damage among the names of preset data columns is empty, extracts preset keyword information related to flood damage from information data for a column of preset flood damage contents, and inserts the extracted keyword information into the information data for the empty column of the degree of flood damage in order to process missing data values ​​for the column of the degree of flood damage.

[0015] Preferably, the data pre-processing module can convert and extract the address value of the flood-damaged area into a longitude and latitude value using information data for the flood-damaged area address column among the names of pre-set data columns based on the flood-damage-related information data for the specific area collected from the data collection module.

[0016] Preferably, the data pre-processing module can compare the degree of flood damage in the specific area and the accumulated precipitation value in the specific area based on the flood damage related information data of the specific area collected from the data collection module using a predetermined quartile approach method, and if a predetermined abnormal value is found, remove the abnormal value.

[0017] Preferably, the data categorization module may further include a data categorization module that categorizes the extent of flood damage in the specific area using data on the extent of flood damage in the specific area according to the accumulated precipitation extracted from the data extraction module, and transmits the categorized data on the extent of flood damage in the specific area to the data analysis module.

[0018] Preferably, the data analysis module is provided with the location of flood damage in the specific area according to the accumulated precipitation extracted from the data extraction module and the flood damage extent data in the specific area categorized from the data categorization module, and based on this, can generate a flood damage prediction analysis model for predicting the risk of flood damage in the specific area according to the accumulated precipitation using a predetermined ordered logistic regression analysis technique.

[0019] Preferably, the data visualization module may further include a data visualization module that receives data on the location and extent of flood damage in the specific area according to the accumulated precipitation extracted from the data extraction module and visualizes the location and extent of flood damage in the specific area according to the accumulated precipitation based on a preset legal cave boundary.

[0020] Preferably, the data visualization module can further use at least one of pre-stored population information and land compaction degree information data for the specific area to visualize the location and extent of flood damage in the specific area by accumulated precipitation.

[0021] Preferably, the flood damage level classification module may further include a flood damage level classification module that classifies the level of flood damage according to the real-time accumulated precipitation value of the specific area using the range of accumulated precipitation for each flood damage level set from the flood damage category setting module.

[0022] Preferably, the system may further include a data storage module that receives at least one of information data among flood damage related information data for the specific region collected from the data collection module, flood damage location and damage extent information data for the specific region according to the accumulated precipitation extracted from the data extraction module, flood damage prediction analysis model information data generated from the data analysis module, and accumulated precipitation range information data for each flood damage level stage set from the flood damage category setting module, and based on this, stores at least one of information among flood damage related information, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage in a database (DB) for each specific region.

[0023] Preferably, the system may further include a data communication module that transmits predetermined unique specific area identification information to an external terminal or server via wired or wireless communication together with at least one of flood damage related information data for the specific area collected from the data collection module, flood damage location and damage extent information data for the specific area according to the accumulated precipitation extracted from the data extraction module, flood damage prediction analysis model information data generated from the data analysis module, and accumulated precipitation range information data for each flood damage extent stage set from the flood damage category setting module.

[0024] Preferably, the external terminal or server receives preset unique specific region identification information or device identification information along with at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and cumulative precipitation range information for each flood damage degree stage transmitted from the data communication module via a pre-installed flood damage-related application service, and based on this, can display or output as audio on a display screen so that the user can visually or audibly confirm at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and cumulative precipitation range information for each flood damage degree stage.

[0025] Preferably, the external terminal or server receives preset unique specific region identification information or device identification information along with at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and cumulative precipitation range information for each flood damage degree stage transmitted from the data communication module via a pre-installed flood damage-related application service, and based on this, can provide a service to store and manage at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and cumulative precipitation range information for each flood damage degree stage in a database (DB) in a separate storage module.

[0026] Preferably, the flood damage category setting module can set the cumulative precipitation that has the smallest difference in predicted probability value for moving from the Nth flood damage level (N=0, 1, 2, 3, ...) to the next Mth flood damage level (M=1, 2, 3, ...) as the reference range of cumulative precipitation for each flood damage level. Effect of the Invention

[0027] According to the flood damage prediction analysis device based on the ordered logistic regression analysis of the present invention described above, by applying the ordered logistic regression analysis method to the cumulative precipitation in days / hours / minutes and the flood damage history data in hours / minutes, a standard range of cumulative precipitation according to the degree of flood damage in a specific area is set. This has the advantage that not only can the risk of flood damage by city / county / ward be easily determined by knowing only the cumulative precipitation value, but also the accuracy and reliability of flood damage prediction can be further improved. [Brief description of the drawings]

[0028] [Figure 1] 1 is an overall block diagram illustrating a flood damage prediction and analysis device based on an ordered logistic regression analysis according to an embodiment of the present invention; [Diagram 2] 11 is a diagram illustrating, in the form of a table, a range of accumulated precipitation for each flood damage level set using a flood damage category setting module applied to one embodiment of the present invention. FIG. [Diagram 3] 11 is a diagram illustrating, in the form of a table, a range of accumulated precipitation for each flood damage level set using a flood damage category setting module applied to one embodiment of the present invention. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] The above-mentioned objects, features and advantages will be described in detail below with reference to the accompanying drawings, so that a person having ordinary skill in the art to which the present invention pertains can easily carry out the technical idea of ​​the present invention. In describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

[0030] Terms including ordinal numbers such as "first", "second", etc. may be used to describe various components, but these components are not limited by these terms. These terms are used only for the purpose of distinguishing one component from another component. For example, a first component can be named a second component, and similarly, a second component can be named a first component, without departing from the scope of the present invention. The terms used in this application are merely used to describe specific embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0031] The terms used in the present invention are selected as general terms that are currently widely used as much as possible while taking into consideration the functions in the present invention, but this may vary depending on the intentions or precedents of engineers engaged in the relevant field, the emergence of new technologies, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meanings will be described in detail in the description of the relevant invention. Therefore, the terms used in the present invention should be defined based on the meanings that the terms have and the overall content of the present invention, rather than simply the names of the terms.

[0032] Throughout the specification, when a part "includes" a certain component, this means that it can further include other components, not excluding other components, unless otherwise specified to the contrary. Furthermore, the terms "unit," "module," etc. described in the specification mean a unit that processes at least one function or operation, which can be realized in hardware or software, or a combination of hardware and software.

[0033] Hereinafter, the embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the following exemplary embodiments of the present invention can be modified into various different forms, and the scope of the present invention is not limited to these embodiments. The embodiments of the present invention are provided to more completely explain the present invention to those skilled in the art.

[0034] The combination of each block of the attached blocks and each step of the flowcharts may be performed by computer program instructions (execution engine), which may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, such that the instructions executed through the processor of the computer or other programmable data processing equipment generate means for performing the functions described in each block of the block diagrams or each step of the flowcharts. These computer program instructions may also be stored in a computer usable or computer readable memory that can direct a computer or other programmable data processing equipment to perform the functions in a specific manner, such that the instructions stored in the computer usable or computer readable memory can produce an article of manufacture that includes instruction means for performing the functions described in each block of the block diagrams or each step of the flowcharts.

[0035] The computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on the computer or other programmable data processing device to generate a computer-implemented process, such that the instructions for the computer or other programmable data processing device provide steps for performing the functions described in each block of the block diagrams and each step of the flowcharts.

[0036] It should also be noted that each block or step may represent a module, segment, or part of code that includes one or more executable instructions for performing a particular logical function, and that in some alternative embodiments, the functions noted in the blocks or steps may occur out of order. For example, two blocks or steps shown in succession may be performed substantially simultaneously, and the blocks or steps may be performed in the reverse order of the corresponding functions, if necessary.

[0037] FIG. 1 is an overall block diagram for explaining a flood damage prediction and analysis device based on ordered logistic regression analysis according to one embodiment of the present invention, and FIG. 2 and FIG. 3 are diagrams for explaining, in the form of a table, the range of cumulative precipitation for each flood damage level set by a flood damage category setting module applied to one embodiment of the present invention.

[0038] 1 to 3, the flood damage prediction and analysis device based on ordered logistic regression analysis according to an embodiment of the present invention mainly includes a data collection module 100, a data extraction module 150, a data analysis module 200, a flood damage category setting module 250, and a power supply module 300. The flood damage prediction and analysis device based on ordered logistic regression analysis according to an embodiment of the present invention may further include a data summarization module 350, a data pre-processing module 400, a data categorization module 450, a data visualization module 500, a flood damage level classification module 550, a data storage module 600, a data communication module 650, an external terminal 20, and / or a server 30. Meanwhile, since the components shown in FIGS. 1 to 3 are not essential, the flood damage prediction and analysis device based on ordered logistic regression analysis according to an embodiment of the present invention may have more or less components.

[0039] Hereinafter, components of a flood damage prediction and analysis device based on ordered logistic regression analysis according to an embodiment of the present invention will be described in detail.

[0040] The data collection module 100 performs a function of collecting flood damage-related information data including accumulated precipitation and / or flood damage history data for a specific area from an external source (eg, the Internet, a government server, etc.).

[0041] The data extraction module 150 receives flood damage related information data for the specific area collected from the data collection module 100, and based on the received information, extracts flood damage location and / or damage extent data for the specific area according to the accumulated precipitation.

[0042] In addition, the data extraction module 150 can perform the function of extracting flood damage location and / or damage extent data for the specific area according to the accumulated precipitation based on the results of summarized information data for flood damage-related information data for the specific area transmitted from the data summarization module 350.

[0043] In addition, the degree of flood damage in the specific area extracted from the data extraction module 150 is preferably composed of, for example, a first stage of "minor" when the flood damage is very little or only on the surface, a second stage of "normal" when the flood damage is of intermediate level and surrounding facilities are affected, and a third stage of "serious" when the damage is severe and large-scale flooding causes loss of life and serious damage.

[0044] The data analysis module 200 receives data on the location and / or extent of flood damage in the specific area according to the accumulated precipitation extracted from the data extraction module 150, and based on this, performs the function of generating a flood damage prediction analysis model for predicting the risk of flood damage in the specific area according to the accumulated precipitation using a pre-set ordered logistic regression analysis technique.

[0045] In addition, the data analysis module 200 receives the flood damage location of the specific area according to the accumulated precipitation extracted from the data extraction module 150 and the flood damage extent data of the specific area categorized from the data categorization module 450, and based on this, can perform the function of generating a flood damage prediction analysis model for predicting the flood damage risk of the specific area according to the accumulated precipitation using a predetermined ordered logistic regression analysis technique.

[0046] On the other hand, regression analysis is a statistical analysis technique that analyzes the relationship between independent variables and dependent variables. It aims to estimate the functional relationship between the independent variables and dependent variables using given data, and then use this to predict the dependent variable when the value of the independent variable is given.

[0047] In addition, the regression analysis is used not only for prediction but also for analyzing the relationship between an independent variable and a dependent variable. Among them, logistic regression analysis is a statistical analysis technique that analyzes the relationship between an independent variable and a dependent variable when the dependent variable follows a binomial distribution (0 or 1), and is mainly used to understand how the value of the independent variable affects a specific result (e.g., success or failure, true or false, etc.) from data.

[0048] The Ordered Logistic Regression Analysis technique is one of the statistical analysis techniques used when the dependent variable is ordinal or ordered categorical data. This Ordered Logistic Regression Analysis technique is applied when there is an order or hierarchy between categories, unlike nominal categorical variables.

[0049] Ordinal logistic regression analysis is an extension of logistic regression analysis, and uses the cumulative log odds ratio to show the boundaries between categories. This can be used to understand and predict how each independent variable changes the probability between categories of the dependent variable. It is mainly used with survey data and customer satisfaction data.

[0050] When the above-mentioned ordered logistic regression analysis technique is applied to the present invention, a summary of a flood damage prediction analysis model that predicts the probability of flood damage depending on the accumulated precipitation in a specific area can be output.

[0051] That is, the coefficient of cumulative precipitation for a particular region is associated with an increase in the log odds ratio for the extent of damage. According to the coefficient, standard error, and t-value, there is evidence that there is a statistically significant relationship between cumulative precipitation and the extent of damage, indicating that as cumulative precipitation increases, the extent of damage increases.

[0052] There is also an intercept for each level of flood damage, with a specific value for each of the 0|1, 1|2, and 2|3 levels. Furthermore, the coeftest(fit) function outputs the test results for the regression coefficients of the model. The coefficients of cumulative precipitation and the intercept coefficients for each level boundary of flood damage have very small p-values ​​and can be considered significant at the confidence level. Therefore, it can be seen that as cumulative precipitation increases, the degree of flood damage increases.

[0053] The flood damage category setting module 250 uses a flood damage prediction analysis model generated from the data analysis module 200 to predict the probability that each accumulated precipitation falls into a preset flood damage category, and sets the range of accumulated precipitation for each flood damage level according to the predicted probability value.

[0054] In addition, the flood damage category setting module 250 can perform the function of setting the cumulative precipitation amount with the smallest difference in predicted probability value for moving from the Nth flood damage level stage (N=0, 1, 2, 3, ...) (N is a natural number equal to or greater than 0) to the next Mth flood damage level stage (M=1, 2, 3, ...) (M is a natural number equal to or greater than 1) as the reference range of the cumulative precipitation amount for each flood damage level stage.

[0055] For example, since serious damage generally occurs when accumulated precipitation exceeds 300 mm, the maximum value of accumulated precipitation is set to 300 mm. Therefore, a flood damage prediction analysis model is used to predict the probability that each accumulated precipitation amount will fall into the range of flood damage levels, based on 1 mm increments from 1 mm to approximately 300 mm.

[0056] At this time, the degree of flood damage is divided into three levels: for example, "minor," "normal," and "severe." However, since there are cases where no damage occurs at all, a zero level, "no damage," is added, making it possible to calculate the probability value in a total of four levels.

[0057] Generally, when the probability prediction value in the ordered logistic regression analysis exceeds 0.5 (when the probability is 50% or more), it is considered to belong to the relevant category, but since there is a proportional relationship between the accumulated precipitation and the level of flood damage, the standard for moving to the next level of flood damage must be linked to the accumulated precipitation. Therefore, it is preferable to set the accumulated precipitation that has the smallest probability difference from each level as the standard for the level of damage.

[0058] For example, suppose you want to set the standard cumulative precipitation amount for moving from stage 0 to stage 1. As shown in Figure 2, 73 mm, which has the smallest probability difference, can be set as the standard cumulative precipitation amount for stages 0 and 1. Therefore, as shown in Figure 3, the range of cumulative precipitation amounts based on the standard level of flood damage can be obtained.

[0059] The power supply module 300 functions to supply the necessary power to each module, i.e., the data collection module 100, the data extraction module 150, the data analysis module 200, the flood damage category setting module 250, the data summary module 350, the data pre-processing module 400, the data categorization module 450, the data visualization module 500, the flood damage extent classification module 550, the data storage module 600, and / or the data communication module 650, and is preferably implemented to convert commercial alternating current (AC) power (e.g., AC 220V) into direct current (DC) and / or alternating current (AC) power for continuous power supply, but is not limited thereto and may also be implemented to include a conventional portable battery.

[0060] In addition, the power supply module 300 may include a power management unit (not shown) that protects components from external power shock and outputs a constant voltage. The power management unit may include an ESD (Electro Static Damage) protector, a power detector, a rectifier, and a power breaker.

[0061] Here, the ESD protector is configured to protect electrical components from static electricity or a sudden power shock. The power detector is configured to send a cutoff signal to the power breaker when a voltage outside an allowable voltage range flows in, and to transmit a step-up or step-down signal to the rectifier according to a change in voltage within the allowable voltage range. The rectifier is configured to perform a step-up or step-down rectification operation according to the signal from the power detector so that a constant voltage is supplied while minimizing fluctuations in the input voltage. The power breaker is configured to cut off the power supplied from the battery according to the cutoff signal transmitted from the power detector.

[0062] The various embodiments described herein may be implemented, for example, using software, hardware, or a combination of both in a computer or similar device readable storage medium.

[0063] According to a hardware implementation, the embodiments described herein may be implemented using at least one of application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, electronic units for performing functions. In some cases, the embodiments may be implemented by at least one of the data collection module 100, the data extraction module 150, the data analysis module 200, the flood damage categorization module 250, the data summarization module 350, the data pre-processing module 400, the data categorization module 450, the data visualization module 500, the flood damage level classification module 550, the data storage module 600, the data communication module 650, and / or a separate control module (not shown).

[0064] According to the software implementation, the embodiments such as procedures or functions can be implemented with separate software modules each configured to perform at least one function or operation. The software code can be implemented by a software application written in a suitable programming language. The software code can be stored in a storage module (not shown) and executed by at least one of the data collection module 100, the data extraction module 150, the data analysis module 200, the flood damage categorization module 250, the data summarization module 350, the data pre-processing module 400, the data categorization module 450, the data visualization module 500, the flood damage level classification module 550, the data storage module 600, the data communication module 650, and / or a separate control module (not shown).

[0065] The storage module may include at least one type of storage medium, for example, a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk.

[0066] Furthermore, the data summarization module 350 receives flood damage related information data for the specific area collected from the data collection module 100, and based on this, summarizes the flood damage related information data for the specific area according to the accumulated precipitation using pre-set data column names, formats and / or feature elements, and transmits the results of the summarized information data to the data extraction module 150.

[0067] Here, the name of the pre-set data column preferably includes at least one of the following column names: date and time of receipt of flood damage, address of flood-damaged area, details of flood damage, and / or extent of flood damage.

[0068] The data pre-processing module 400 receives flood damage related information data for the specific region collected from the data collection module 100, and based on this, if there is empty information data for a column of the degree of flood damage among the names of pre-set data columns, in order to process missing data values ​​for the column of the degree of flood damage, extracts keyword information related to pre-set flood damage from the information data for the pre-set column of flood damage contents, and inserts the extracted keyword information into the information data for the empty column of the degree of flood damage.

[0069] For example, if the column detailing flood damage contains information data such as "flooding due to clogged drainage channels," it is possible to extract keywords such as "drainage channels, clogged channels, water, flooding" that are related to flooding damage.

[0070] In addition, the data pre-processing module 400 can perform the function of converting the address value of the flood-damaged area into a longitude and latitude value and extracting it using information data for the flood-damaged area address column among the names of pre-set data columns based on the flood-damaged area-related information data collected from the data collection module 100.

[0071] In addition, the data pre-processing module 400 can compare the degree of flood damage in the specific region and the accumulated precipitation value in the specific region based on the flood damage related information data collected from the data collection module 100 using a preset quartile approach method, and if a preset abnormal value is found, can perform the function of removing the abnormal value.

[0072] In addition, the data pre-processing module 400 can identify abnormal values ​​to be removed through a correlation graph between the flood damage level categorized by the data categorization module 450 and the accumulated precipitation in order to identify abnormal values.

[0073] The data categorization module 450 categorizes the extent of flood damage in the specific region using the flood damage extent data for the specific region according to the accumulated precipitation extracted from the data extraction module 150, and transmits the categorized flood damage extent data for the specific region to the data analysis module 200.

[0074] In addition, the data categorization module 450 may extract keywords having noun morphemes of token units included in the flood damage level of the specific region, sort the keywords based on the keyword score for each flood damage level stage, check whether the keywords have a high correlation with the flood damage level stage, select them as standard keywords, and perform categorization using the presence or absence of keywords for each flood damage level stage. At this time, the keyword extraction result preferably includes the score (or importance), morphemes, number, etc. for each keyword.

[0075] Furthermore, the data categorization module 450 can analyze the flood damage level data of the specific region and categorize the flood damage level into three levels (for example, flood damage level level 1, level 2, and level 3). That is, flood damage level 1 is when the "damage level" column contains the word "minor" or the "damage level" column contains the value "none", flood damage level 2 is when there is a value other than flood damage level levels 1 and 3, and flood damage level 3 is when the "damage level" column contains a value containing the words "serious|emergency|evacuation|collapse".

[0076] The data visualization module 500 receives data on the location and / or extent of flood damage in a specific area according to the accumulated precipitation extracted from the data extraction module 150, and performs the function of visualizing the location and / or extent of flood damage in the specific area according to the accumulated precipitation based on the predetermined legal cavern boundaries.

[0077] In addition, since the correlation between the total population and the degree of land compaction at the flood damage locations in the specific region is very high, the data visualization module 500 can further use at least one of the pre-stored population information and / or land compaction information data for the specific region to perform the function of visualizing the location and / or extent of flood damage in the specific region by accumulated precipitation.

[0078] In addition, the correlation between the accumulated precipitation and the flood damage level data of the specific area can be easily confirmed using the flood damage location and / or damage level by accumulated precipitation for the specific area visualized by the data visualization module 500. That is, it can be seen that the risk area classification is significant because the damage area is clearly classified within the specific area. Therefore, it can be seen that there is a difference in the scale of damage by area as the accumulated precipitation increases.

[0079] Such a data visualization module 500 may be implemented on a variety of display devices, including, for example, a liquid crystal display (LCD), a light emitting diode display (LED), a thin film transistor-liquid crystal display (TFT LCD), an organic light emitting diode (OLED), a flexible display, a plasma display panel, etc. Panel, PDP), surface alternate lighting (ALiS), digital light processing (DLP), liquid crystal on silicon (LCoS), surface conduction electron emitter display (SED), field emission display (FED), laser TV (quantum dot laser, liquid crystal laser), optical dielectric liquid display (FLD), interferometric modulator display (iMoD), thick film dielectric electric (TDEL), quantum dot display (QD-LED), telescopic pixel display (TPD), organic light emitting transistor (OLET), laser fluorescent display (LPD), and three-dimensional display (3D display), but is not limited to these, and may include any one that can visualize various data such as video, image, character, or document.

[0080] The flood damage level classification module 550 performs the function of classifying the level of flood damage according to the real-time accumulated precipitation value of the specific area using the range of accumulated precipitation for each flood damage level set by the flood damage category setting module 250.

[0081] The data storage module 600 stores flood damage related information data of the specific area collected from the data collection module 100, flood damage location and / or damage extent information data of the specific area according to the accumulated precipitation extracted from the data extraction module 150, flood damage prediction analysis model information data generated from the data analysis module 200, accumulated precipitation range information data for each flood damage level stage set from the flood damage category setting module 250, summary result information data of the summarized information data from the data summarization module 350, preprocessing result information data preprocessed from the data preprocessing module 400, data category information data, and the like. The data visualization module 500 receives at least one of flood damage extent information data for the specific region categorized by the data visualization module 450 and / or flood damage location and / or damage extent information data by accumulated precipitation for the specific region visualized by the data visualization module 500, and based on the received data, performs a function of converting at least one of flood damage related information, flood damage location and damage extent information, flood damage prediction analysis model information, accumulated precipitation range information by flood damage extent stage, summary result information, preprocessing result information, categorized information, and / or visualized information into a database (DB) and storing it for the specific region.

[0082] The data storage module 600 may include a program memory and a data memory. The program memory stores a program for controlling a general operation of the flood damage prediction and analysis device based on ordered logistic regression analysis according to an embodiment of the present invention. In this case, the program memory may store programs for performing operations and functions of the data collection module 100, the data extraction module 150, the data analysis module 200, the flood damage category setting module 250, the power supply module 300, the data summarization module 350, the data pre-processing module 400, the data categorization module 450, the data visualization module 500, the flood damage degree classification module 550, the data storage module 600, and / or the data communication module 650.

[0083] The program memory may store programs for driving the data collection module 100, data extraction module 150, data analysis module 200, flood damage category setting module 250, power supply module 300, data summary module 350, data pre-processing module 400, data categorization module 450, data visualization module 500, flood damage extent classification module 550, data storage module 600, and / or data communication module 650, etc.

[0084] The data memory stores data generated during execution of programs in the data collection module 100, data extraction module 150, data analysis module 200, flood damage category setting module 250, power supply module 300, data summarization module 350, data pre-processing module 400, data categorization module 450, data visualization module 500, flood damage level classification module 550, data storage module 600, and / or data communication module 650. For example, flood damage-related information for each specific region, flood damage location and damage level information, flood damage prediction analysis model information, accumulated precipitation range information for each flood damage level stage, summary result information, pre-processing result information, categorized information, and / or visualized information may be stored in the data memory of the data storage module 600. In addition, unique specific region identification information applied to an embodiment of the present invention may be stored in the data memory of the data storage module 600.

[0085] That is, the data storage module 600 may store and maintain at least one program code executed via the data collection module 100, the data extraction module 150, the data analysis module 200, the flood damage category setting module 250, the power supply module 300, the data summary module 350, the data pre-processing module 400, the data categorization module 450, the data visualization module 500, the flood damage extent classification module 550, the data storage module 600, and / or the data communication module 650, etc., and at least one dataset in which the program code is used.

[0086] Such a data storage module 600 may include at least one type of readable storage medium, for example, a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk.

[0087] The data communication module 650 performs a function of transmitting at least one of the following information to an external terminal 20 and / or server 30 via the communication network 10: flood damage-related information data for the specific region collected from the data collection module 100; flood damage location and / or damage extent information data for the specific region according to the accumulated precipitation extracted from the data extraction module 150; flood damage prediction analysis model information data generated from the data analysis module 200; cumulative precipitation range information data for each flood damage level stage set from the flood damage category setting module 250; summary result information data for the summarized information data from the data summarization module 350; preprocessing result information data preprocessed from the data preprocessing module 400; flood damage extent information data for the specific region categorized from the data categorization module 450; and / or flood damage location and / or damage extent information data for the specific region by accumulated precipitation visualized from the data visualization module 500; and / or unique specific region identification information and / or device identification information set in advance, together with at least one of the following information: flood damage-related information data for the specific region collected from the data collection module 100;

[0088] Here, the unique specific area identification information preferably includes at least one of the following information: a name of a specific area, an address of a specific area, a password of a specific area, a serial number of a specific area, a Media Access Control (MAC) address of a specific area, a unique Internet Protocol (IP) address of a specific area, a private key of a specific area, or authentication information of a specific area generated by a PKI-based private key, but is not limited thereto and may include all specific area identification information capable of identifying a specific area.

[0089] The unique device identification information preferably includes at least one of the following information, for example: device name, device password, device serial number, device type, device manufacturer, device Media Access Control (MAC) address, device unique Internet Protocol (IP) address, device model and version, device private key, or device authentication information generated by a PKI-based private key, but is not limited thereto, and may include all device identification information that can identify the flood damage prediction analysis device based on ordered logistic regression analysis according to one embodiment of the present invention.

[0090] In addition, when the data communication module 650 uses a wireless communication method, it can use a wireless Internet communication method such as WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), low power wireless communication (Wireless Personal Area Network, WPAN), or a short-range wireless communication method such as Beacon, ZigBee, Bluetooth (registered trademark), UWB (Ultra Wideband), RFID (Radio Frequency Identification), or infrared (IR) communication.

[0091] On the other hand, the communication network 10 is a communication network that is a high-speed backbone network of a large communication network capable of large-capacity, long-distance voice and data services, and may be a next-generation wireless communication network including WiFi, WiGig, Wireless Broadband Internet (Wibro), Wimax (World Interoperability for Microwave Access), etc. for providing the Internet or high-speed multimedia services.

[0092] The Internet refers to a global open computer network structure that provides TCP / IP protocols and various services existing in higher layers thereof, i.e., HTTP (Hyper Text Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service), NIS (Network Information Service), etc., and provides an environment in which the data communication module 650 can connect to an external terminal 20 and / or server 30. Meanwhile, the Internet may be a wired or wireless Internet, or may be a core network integrated with a wired public network, a wireless mobile communication network, or a mobile Internet.

[0093] If the communication network 10 is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. An example of the asynchronous mobile communication network is a WCDMA (Wideband Code Division Multiple Access) (registered trademark) type communication network. In this case, although not shown in the drawings, the mobile communication network may include, for example, an RNC (Radio Network Controller). Meanwhile, although the WCDMA network is given as an example, it may be a next-generation communication network such as a cellular-based 3G network, an LTE network, a 4G network, or a 5G network, or another IP-based IP network. Such a communication network 10 serves to transmit signals and data between the data communication module 650 and an external terminal 20 and / or a server 30.

[0094] The external terminal 20 and / or server 30 receive, via a pre-installed flood damage-related application service, at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, cumulative precipitation range information for each flood damage degree stage, summary result information, pre-processing result information, categorized information, and / or visualized information transmitted from the data communication module 650, along with preset unique specific region identification information or device identification information, and based on this, can display or output on a display screen or sound so that a user can visually and / or audibly confirm at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, cumulative precipitation range information for each flood damage degree stage, summary result information, pre-processing result information, categorized information, and / or visualized information.

[0095] In addition, the external terminal 20 and / or server 30 can receive preset unique specific region identification information or device identification information along with at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and cumulative precipitation range information for each flood damage degree stage, summary result information, pre-processing result information, categorized information, and / or visualized information transmitted from the data communication module 650 via a pre-installed flood damage-related application service, and based on this, can provide a service to store and manage at least one of the flood damage-related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, cumulative precipitation range information for each flood damage degree stage, summary result information, pre-processing result information, categorized information, and / or visualized information in a database (DB) in a separate storage module (not shown).

[0096] Meanwhile, the external terminal 20 is preferably composed of at least one mobile terminal system of a smart phone, a smart pad, and / or a smart note that communicates via wireless Internet or mobile Internet, and may also refer to all wired and wireless home appliances / communication systems having a user interface for connecting to the data communication module 700, such as a Palm PC, a mobile game console, a DMB (Digital Multimedia Broadcasting) phone with communication function, a tablet PC, an iPad (registered trademark), etc.

[0097] Although a preferred embodiment of the flood damage prediction analysis device based on ordered logistic regression analysis according to the present invention has been described above, the present invention is not limited thereto and can be implemented in various modified forms within the scope of the claims, detailed description of the invention and the attached drawings, which also belong to the present invention. [Explanation of symbols]

[0098] 100 Data Collection Modules 150 Data Extraction Module 200 Data Analysis Module 250 Flood damage category setting module 300 Power Supply Module 350 Data Summary Module 400 Data Pre-Processing Module 450 Data Categorization Module 500 Data Visualization Module 550 Flood damage classification module 600 Data Storage Module 650 Data Communication Module

Claims

1. a data collection module for collecting flood damage-related information data including accumulated precipitation and flood damage history data for a specific area from an external source; a data extraction module that receives flood damage-related information data of the specific region collected from the data collection module and extracts flood damage location and damage extent data of the specific region according to accumulated precipitation based on the received flood damage information data; a data analysis module that receives data on flood damage location and damage extent of the specific area according to the accumulated precipitation extracted from the data extraction module, and generates a flood damage prediction analysis model for predicting a flood damage risk of the specific area according to the accumulated precipitation using a preset ordered logistic regression analysis technique based on the data; A flood damage prediction and analysis device based on ordered logistic regression analysis, comprising: a flood damage category setting module that predicts the probability that each cumulative precipitation amount falls into a preset flood damage level category using a flood damage prediction analysis model generated from the data analysis module, and sets a cumulative precipitation range for each flood damage level stage according to the predicted probability value.

2. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, further comprising a data summarization module that receives flood damage related information data for the specific region collected from the data collection module, summarizes the flood damage related information data for the specific region according to accumulated precipitation using pre-set data column names, formats and feature elements based on the received flood damage related information data, and transmits the results of the summarized information data to the data extraction module.

3. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 2, characterized in that the data extraction module extracts flood damage location and damage extent data for the specific region according to the accumulated precipitation based on the results of summarized information data for flood damage-related information data for the specific region transmitted from the data summarization module.

4. 3. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 2, characterized in that the names of the pre-set data columns include at least one column name of the date and time of receipt of the flood damage, the address of the flood damage area, the details of the flood damage, and the extent of the flood damage.

5. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, characterized in that the degree of flood damage in the specific area extracted from the data extraction module is composed of a first stage of "minor" when the flood damage is very little or only on the surface, a second stage of "normal" when the flood damage is moderate and affects surrounding facilities, and a third stage of "serious" when the damage is severe and large-scale flooding causes loss of life and serious damage.

6. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis of claim 1, further comprising a data pre-processing module that receives flood damage related information data for the specific region collected from the data collection module, and based on the received information data, if information data for a column of the degree of flood damage among the names of preset data columns is empty, extracts keyword information related to preset flood damage from the information data for a column of preset flood damage contents in order to process missing data values ​​for the column of the degree of flood damage, and inserts the extracted keyword information into the information data for the empty column of the degree of flood damage.

7. The flood damage prediction and analysis device based on ordered logistic regression analysis of claim 6, characterized in that the data pre-processing module converts and extracts the address value of the flood damage area into a longitude and latitude value using information data for a column of flood damage area addresses among pre-set data column names based on flood damage related information data for the specific area collected from the data collection module.

8. 7. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 6, characterized in that the data pre-processing module compares the degree of flood damage in the specific region and the accumulated precipitation value in the specific region based on the flood damage related information data of the specific region collected from the data collection module using a predetermined quartile approach method, and if a predetermined abnormal value is found, removes the abnormal value.

9. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, further comprising a data categorization module that categorizes the degree of flood damage in the specific region using flood damage degree data in the specific region according to the cumulative precipitation extracted from the data extraction module, and transmits the categorized flood damage degree data in the specific region to the data analysis module.

10. The data analysis module receives flood damage locations of the specific area according to the accumulated precipitation extracted from the data extraction module and flood damage extent data of the specific area categorized from the data categorization module, and based on this, generates a flood damage prediction analysis model for predicting the flood damage risk of the specific area according to the accumulated precipitation using a preset ordered logistic regression analysis technique.

11. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as claimed in claim 1, further comprising a data visualization module that receives data on the location and extent of flood damage in the specific area according to the accumulated precipitation extracted from the data extraction module and visualizes the location and extent of flood damage in the specific area by accumulated precipitation based on a predetermined legal cave boundary.

12. The flood damage prediction and analysis device based on ordered logistic regression analysis of claim 11, characterized in that the data visualization module further uses at least one of pre-stored information data of the population information and land compaction degree information data of the specific area to visualize the location and extent of flood damage in the specific area by cumulative precipitation.

13. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, further comprising a flood damage degree classification module that classifies the level of flood damage according to the real-time cumulative precipitation value of the specific area using the range of cumulative precipitation for each flood damage level set from the flood damage category setting module.

14. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as claimed in claim 1, further comprising a data storage module that receives at least one of flood damage related information data for the specific region collected from the data collection module, flood damage location and damage extent information data for the specific region according to the accumulated precipitation extracted from the data extraction module, flood damage prediction analysis model information data generated from the data analysis module, and accumulated precipitation range information data for each flood damage level stage set from the flood damage category setting module, and stores at least one of flood damage related information, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage in a database (DB) based on the received information.

15. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, further comprising a data communication module that transmits predetermined unique specific area identification information or device identification information to an external terminal or server via wired or wireless communication together with at least one of flood damage related information data for the specific area collected from the data collection module, flood damage location and damage extent information data for the specific area according to the accumulated precipitation extracted from the data extraction module, flood damage prediction analysis model information data generated from the data analysis module, and accumulated precipitation range information data for each flood damage degree stage set from the flood damage category setting module.

16. The external terminal or server receives preset unique specific region identification information or device identification information along with at least one of the flood damage related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage transmitted from the data communication module via a pre-installed flood damage related application service, and displays or outputs as sound on a display screen based on the received information so that a user can visually or audibly confirm at least one of the flood damage related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage.

17. The external terminal or server receives preset unique specific region identification information or device identification information along with at least one of the flood damage related information for each specific region, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage transmitted from the data communication module via a pre-installed flood damage related application service, and provides a service to store and manage at least one of the flood damage related information, flood damage location and damage extent information, flood damage prediction analysis model information, and accumulated precipitation range information for each flood damage level stage in a database (DB) in a separate storage module based on the above.

18. 2. The flood damage prediction and analysis device based on ordered logistic regression analysis as described in claim 1, characterized in that the flood damage category setting module sets the cumulative precipitation amount with the smallest difference in predicted probability value for moving from the Nth stage (N = 0, 1, 2, 3, ...) of flood damage level to the next Mth stage (M = 1, 2, 3, ...) of flood damage level as the reference range of cumulative precipitation amount for each flood damage level.

Images