KR20230022604A - Method and system for estimating real estates prices - Google Patents

Abstract

A real estate price estimation method according to an embodiment of the present invention is a method in which a real estate price estimation application executed by at least one processor of a terminal estimates a real estate price. The real estate price estimation method comprises the steps of: collecting price time series data that arranges trends of actual transaction price data for each of a plurality of affiliated complexes belonging to an entire complex in a first zone according to the passage of time; preprocessing the collected price time series data; determining at least one affiliated complex among the plurality of affiliated complexes as a leading complex that leads real estate prices in the first zone based on the preprocessed market price time series data; detecting a target complex having a missing value that actual transaction price data corresponding to at least one period is absent among the plurality of affiliated complexes based on the preprocessed price time series data; interpolating the missing value for the target complex based on the time series data of the determined leading complex; and calculating current price information for the entire complex based on price time series data with the missing values interpolated. Accordingly, a current real estate price for a plurality of complexes in one area can be estimated.

Description

Real estate price estimation method and its system {METHOD AND SYSTEM FOR ESTIMATING REAL ESTATES PRICES}

The present invention relates to a method and system for estimating real estate prices. More specifically, based on time series data representing the real estate market price flow of a specific complex representing a certain area, a predetermined real estate market price missing value in the area is interpolated, and current real estate market prices for a plurality of complexes in the area are estimated and provided. It relates to a method and system for estimating real estate prices.

In general, most of the current real estate market prices depend on a market price input method based on subjective judgment by a real estate agent designated for each region or collected by a researcher who investigates real estate market prices.

However, the above conventional market price estimation method raises a problem in its reliability in that subjective judgment of a person is inevitably involved.

In addition, there is also a lack of criteria for determining the accuracy of whether the estimated real estate market price truly reflects the current actual transaction price.

Therefore, it is necessary to introduce a technology for constructing and providing real estate quote data based on reliable ground data rather than human heuristic judgment as in the prior art.

On the other hand, conventionally, information related to a specific real estate market price is obtained by visiting a real estate agency individually or using magazines, newspapers, or the Internet related to real estate sales.

However, in the case of visiting each real estate brokerage agency, considerable time and money are consumed until the desired market price information is obtained, and there is a problem that a lot of money and effort are required. There is a limit that is virtually impossible to access.

Therefore, in most recent cases, people try to obtain real estate market price information using the Internet, but various data collected through Internet searches (e.g., publicly announced land price, real estate sale price, jeonse price, monthly rent price, auction information, and/or auction information) etc.) to estimate desired real estate market price information.

For the purpose of solving these difficulties, the Ministry of Land, Infrastructure and Transport is currently providing real estate transaction data.

In other words, the Ministry of Land, Infrastructure and Transport, etc., in accordance with Article 7 Paragraphs 1 and 2 (Public Publication of Administrative Information) of the "Act on Information Disclosure of Public Institutions" for real estate for which a real estate transaction report has been reported and a fixed date The actual transaction price for the granted real estate is disclosed, and this information is systematically disclosed through the "actual transaction processing disclosure system (http://rt.molit.go.kr/)" or "public data portal (https://www. data.go.kr/)" can be obtained for free.

However, since the above actual transaction price information provided by the Ministry of Land, Infrastructure and Transport is disclosed with the exact transaction date or exact address such as lot number deleted due to privacy issues, there is a limit to using useful information.

KR 10-2021-0027776 A

The present invention has been made to solve the above-described problems, and is a method for estimating real estate market prices that interpolates missing values of predetermined real estate prices in a specific zone based on time-series data representing the flow of real estate market prices in a specific complex representing a specific zone. and to provide the system.

In addition, the present invention is to provide a real estate market price estimating method and system for estimating the current real estate market price for a plurality of complexes in the zone.

In addition, the present invention is to provide a real estate market price estimation method and system for providing visualized data based on the estimated current real estate market price.

However, the technical problems to be achieved by the present invention and the embodiments of the present invention are not limited to the technical problems described above, and other technical problems may exist.

A method for estimating real estate market prices according to an embodiment of the present invention is a method for estimating real estate market prices by a real estate market price estimation application executed by at least one processor of a terminal, wherein each of a plurality of affiliated complexes belonging to all complexes in a first zone Collecting market price time-series data in which the trends of the actual transaction data are arranged according to the lapse of time; performing pre-processing on the collected time-series data; determining at least one affiliated complex among the plurality of affiliated complexes as a major complex leading the real estate market price in the first zone based on the preprocessed market price time series data; detecting a target complex including a missing value in which there is no actual transaction price data corresponding to at least one period among the plurality of affiliated complexes based on the preprocessed market price time series data; interpolating a missing value for the target complex based on the time-series data of the determined blacksmith complex; and calculating current market price information for the entire complex based on the market price time-series data interpolated with the missing values.

In this case, the market price time-series data is data representing trends of actual transaction price data for each of a plurality of households in the plurality of affiliated complexes based on the affiliated complex and a predetermined equilibrium in a time series format.

In addition, the step of performing preprocessing on the collected time series data includes the step of removing the time series data of the target complex including a predetermined number or more missing values from the time series data, and the removing time series data from the market price time series data; removing time series data of a complex to which the number of actual transaction price data is equal to or less than a reference value from the market price time series data; At least one step of removing or altering.

In addition, the step of determining the housing complex leading the real estate market price in the first zone is based on at least one of the number of actual transaction price data, the number of households, the standard deviation of the actual transaction price data, and whether or not new construction is performed for each of the plurality of affiliated complexes. and determining at least one affiliated complex among the plurality of affiliated complexes as the managerial complex.

In addition, the step of determining at least one affiliated complex among the plurality of affiliated complexes as a large business complex, based on at least one of the administrative district, area, and population within the first zone, a plurality of managerial complexes for the first zone. The step of determining whether or not to determine is further included.

In addition, the step of interpolating the missing value for the target complex is based on the time series data of the target complex when the ratio of the number of missing values to the number of total actual transaction price data included in the time series data of the target complex is equal to or less than a predetermined reference value. and interpolating missing values using a linear interpolation method.

In addition, the step of interpolating the missing value for the target complex includes determining a core blacksmith complex having the greatest influence on the real estate market price of the target complex when a plurality of blacksmith complexes are determined for the first zone. .

In addition, the step of determining the core blacksmith complex includes the steps of detecting a blacksmith complex included in the same administrative district as the target complex, and detecting a blacksmith complex located within a predetermined radius based on the target complex; The method may include detecting a blacksmithing complex having the highest real estate market price average among the plurality of blacksmithing complexes, and determining the core blacksmithing complex based on the detected at least one or more blacksmithing complexes.

In addition, the step of determining the core blacksmithing complex includes determining a blacksmithing complex having time-series data that meets a predetermined similarity with the time-series data of the target complex as the core blacksmithing complex.

In addition, the step of interpolating the missing value for the target complex interpolates the missing value according to a dynamic time warping (DTW) algorithm based on the time series data of the determined core blacksmith complex and the time series data of the target complex Include more steps.

In addition, the step of calculating current market price information for the entire complex includes existing market price time series data including actual transaction price data from before a predetermined period to the present based on the market price time series data in which the missing value is interpolated and a predetermined value from the present. Obtaining predicted market price time series data including actual transaction price data predicted until after the period; It includes the step of estimating for each equilibrium of .

In addition, the calculating of the current market price information for all complexes further includes re-estimating the estimated actual transaction price data at the current time based on the surrounding environmental conditions for each of the plurality of affiliated complexes.

In addition, the real estate market price estimation method according to an embodiment of the present invention generates a market price visualization graph that visualizes time series data of a specific belonging complex and a specific equilibrium based on the calculated current market price information and the market price time series data in which the missing value is interpolated. and providing.

Meanwhile, a real estate market price estimation system according to an embodiment of the present invention includes at least one or more displays outputting a market price visualization graph; at least one memory; and at least one processor; Including, at least one application that is stored in the memory and executed by the processor to estimate the market price of real estate, wherein the at least one application is an actual transaction for each of a plurality of affiliated complexes belonging to all complexes in the first zone. Collecting market price time series data in which data trends are arranged according to the lapse of time, performing preprocessing on the collected market price time series data, and at least one belonging among the plurality of affiliated complexes based on the preprocessed market price time series data Determining the complex as the ledger complex leading the real estate market price in the first zone, and based on the preprocessed market price time series data, the actual transaction corresponding to at least one period among the plurality of affiliated complexes includes a missing value in which there is no data Detecting a target complex, interpolating a missing value for the target complex based on the time series data of the determined large book complex, calculating current quote information for the entire complex based on the quoted time series data in which the missing value is interpolated, Based on the calculated current market price information and the market price time series data in which the missing value is interpolated, the market price visualization graph visualizing the time series data of a specific belonging complex and a specific equilibrium is created and provided.

A real estate market price estimation method and system according to an embodiment of the present invention interpolate a missing real estate market price value in a specific area based on time series data representing the flow of real estate market prices in a specific complex representing a specific area, real estate within a specific period Even in the case of a complex lacking an actual transaction history, it is possible to compensate for the absence of real estate market price data based on the lack of history based on reliable ground data, and through this, the missing value for specific real estate market price data for all complexes in the zone There is an effect of building a database based on time series data in a complete form without data.

In addition, the real estate market price estimation method and system according to an embodiment of the present invention interpolate a predetermined real estate market price missing value in the zone based on time-series data representing the flow of real estate market prices in a specific complex representing a certain zone, Based on credible ground data rather than heuristic judgment, there is an effect of automatically supplementing the real estate market price data lacking in the above district.

In addition, the method and system for estimating real estate market prices according to an embodiment of the present invention estimate current real estate market prices for a plurality of complexes in the zone based on the time series data in which the missing values are interpolated, so that actual transactions for a specific period of time are performed. Even in the case of a complex lacking a history, it is possible to estimate the current real estate market price in a state supplemented with reasonable real estate market price data, thereby improving the accuracy and reliability of the estimated current real estate market price and at the same time enhancing the fairness of real estate transactions. can

In addition, the real estate market price estimation method and system according to an embodiment of the present invention provide visualized data based on the estimated current real estate market price, so that users can individually search for real estate agencies or magazines and newspapers related to real estate for sale. There is an effect of reducing the effort or cost consumed to acquire the desired real estate market price information, such as performing analysis by searching the Internet or the like.

In addition, the real estate market price estimation method and system according to an embodiment of the present invention provide visualized data based on the estimated current real estate market price, so that the user intends real estate market price information quickly and intuitively in a form that is easy to recognize. There is an effect that can be provided.

However, the effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood from the description below.

1 is a conceptual diagram of a real estate market price estimation system according to an embodiment of the present invention.
2 is an internal block diagram of a terminal according to an embodiment of the present invention.
3 is a flowchart of a method for estimating real estate market prices according to an embodiment of the present invention.
4 is an example of a diagram for explaining a DTW-BI process based on a Dynamic Time Warping (DTW) algorithm according to an embodiment of the present invention.
5 are examples of market price visualization graphs according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and methods for achieving them will become clear with reference to the embodiments described later in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms. In the following embodiments, terms such as first and second are used for the purpose of distinguishing one component from another component without limiting meaning. Also, expressions in the singular number include plural expressions unless the context clearly dictates otherwise. In addition, terms such as include or have mean that features or elements described in the specification exist, and do not preclude the possibility that one or more other features or elements may be added. In addition, in the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, since the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of description, the present invention is not necessarily limited to the illustrated bar.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when describing with reference to the drawings, the same or corresponding components are assigned the same reference numerals, and overlapping descriptions thereof will be omitted. .

1 is a conceptual diagram of a real estate market price estimation system according to an embodiment of the present invention.

Referring to FIG. 1, the real estate market price estimation system 10 according to an embodiment of the present invention calculates the real estate market price of a specific complex representing a certain area (eg, a predetermined eup/myeon/dong/si/gun/gu, etc.) It is possible to implement a real estate market price estimating service that interpolates a predetermined missing real estate market price value in the zone based on time series data representing a flow, and estimates and provides current real estate market prices for a plurality of complexes in the zone.

In an embodiment, the real estate market price estimation system 10 providing the above real estate market price estimation service may include a terminal 100, a real estate market price estimation server 200, and a network 300 (Network).

At this time, the terminal 100 and the real estate market price estimation server 200 may be connected through the network 300 .

Here, the network 300 according to the embodiment refers to a connection structure capable of exchanging information between nodes such as the terminal 100 and/or the real estate market price estimation server 200, and such a network 300 An example of 3GPP (3rd Generation Partnership Project) network, LTE (Long Term Evolution) network, WIMAX (World Interoperability for Microwave Access) network, Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network) ), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

Hereinafter, the terminal 100 and the real estate market price estimating server 200 implementing the real estate market price estimation system 10 will be described in detail with reference to the accompanying drawings.

- Terminal (100: Terminal)

The terminal 100 according to an embodiment of the present invention may be a predetermined computing device in which a real estate market price estimation application (hereinafter, an estimation application) providing a real estate market price estimation service is installed.

In detail, further referring to FIG. 1 , from a hardware point of view, the terminal 100 may include a mobile type computing device 100-1 and/or a desktop type computing device 100-2 in which an estimation application is installed. .

Here, the mobile type computing device 100 - 1 may be a mobile device such as a smart phone or a tablet PC in which an estimation application is installed.

For example, the mobile type computing device 100 - 1 is a smart phone, a mobile phone, or a digital broadcasting terminal 100 , such as a personal digital assistant (PDA), a portable multimedia player (PMP), or a tablet PC (tablet PC). PC), etc. may be included.

In addition, the desktop type computing device 100-2 provides a real estate quote estimation service based on wired/wireless communication, such as a fixed desktop PC, a laptop computer, and a personal computer such as an ultrabook with an estimation application installed thereon. It may include a device in which a program for executing is installed.

Also, according to embodiments, the terminal 100 may further include a predetermined server computing device that provides a real estate market price estimation service environment.

2 is an internal block diagram of a terminal 100 according to an embodiment of the present invention.

Meanwhile, referring to FIG. 2 , from a functional point of view, the terminal 100 includes a memory 110, a processor assembly 120, a communication module 130, an interface module 140, an input system 150, and a sensor system 160. ) and a display system 170 . These components may be configured to be included in the housing of the terminal 100 .

In detail, the estimation application 111 is stored in the memory 110 , and the estimation application 111 may store any one or more of various application programs, data, and commands for providing a real estate market price estimation service environment.

That is, memory 110 may store instructions and data that may be used to create a real estate quote service environment.

Also, the memory 110 may include a program area and a data area.

Here, the program area according to the embodiment may be linked between an operating system (OS) that boots the terminal 100 and functional elements, and the data area may be data generated according to the use of the terminal 100. can be stored.

In addition, the memory 110 may include at least one or more non-transitory computer-readable storage media and temporary computer-readable storage media.

For example, the memory 110 may be various storage devices such as ROM, EPROM, flash drive, hard drive, etc., and web storage that performs the storage function of the memory 110 on the Internet can include

The processor assembly 120 may include at least one or more processors capable of executing instructions of the estimation application 111 stored in the memory 110 to perform various tasks for creating a real estate quote service environment.

In an embodiment, the processor assembly 120 may control overall operations of components through the estimation application 111 of the memory 110 to provide a real estate market price estimation service.

The processor assembly 120 may be a system on chip (SOC) suitable for the terminal 100 including a central processing unit (CPU) and/or a graphics processing unit (GPU), and an operating system stored in the memory 110. (OS) and/or application programs may be executed, and components mounted in the terminal 100 may be controlled.

In addition, the processor assembly 120 may communicate internally with each component through a system bus, and may include one or more predetermined bus structures including a local bus.

In addition, the processor assembly 120 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and controllers. ), micro-controllers, microprocessors, and electrical units for performing other functions.

The communication module 130 may include one or more devices for communicating with external devices. This communication module 130 may communicate through a wireless network.

In detail, the communication module 130 may communicate with the terminal 100 storing a content source for implementing a real estate market price estimation service environment, and may communicate with various user input components such as a controller that receives a user input.

In an embodiment, the communication module 130 may transmit and receive various data related to the real estate market price estimation service to and from other terminals 100 and/or external servers.

This communication module 130, technical standards or communication schemes for mobile communication (eg, LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G NR (New Radio), WIFI) Alternatively, data may be transmitted and received wirelessly with at least one of a base station, an external terminal 100, and an arbitrary server on a mobile communication network constructed through a communication device capable of performing a short-distance communication method.

The sensor system 160 may include various sensors such as an image sensor 161, a position sensor (IMU) 163, an audio sensor 165, a distance sensor, a proximity sensor, and a contact sensor.

Here, the image sensor 161 may capture an image and/or video of a physical space around the terminal 100 .

In an embodiment, the image sensor 161 may obtain an image related to the real estate market price estimation service (eg, an image captured in the first area).

In addition, the image sensor 161 may be disposed on the front or/or rear side of the terminal 100 to acquire an image by photographing the direction side of the terminal 100, and may acquire a physical image through a camera disposed toward the outside of the terminal 100. space can be photographed.

The image sensor 161 may include an image sensor device and an image processing module. In detail, the image sensor 161 may process still images or moving images obtained by an image sensor device (eg, CMOS or CCD).

In addition, the image sensor 161 may extract necessary information by processing a still image or moving image obtained through an image sensor device using an image processing module, and transmit the extracted information to a processor.

The image sensor 161 may be a camera assembly including one or more cameras. The camera assembly may include a general camera that captures a visible light band, and may further include a special camera such as an infrared camera and a stereo camera.

In addition, the image sensor 161 as described above may be included in the terminal 100 and operated according to embodiments, or may be included in an external device (eg, an external server, etc.) to perform the above-described communication module 130 and/or Alternatively, it may operate through interworking based on the interface module 140 .

The position sensor (IMU) 163 may detect at least one of motion and acceleration of the terminal 100 . For example, it may be made of a combination of various position sensors such as accelerometer, gyroscope, and magnetometer.

In addition, the location sensor (IMU) 163 may recognize spatial information about a physical space around the terminal 100 by interworking with the location communication module 130 such as GPS of the communication module 130 .

The audio sensor 165 may recognize sounds around the terminal 100 .

In detail, the audio sensor 165 may include a microphone capable of detecting a user's voice input using the terminal 100 .

In an embodiment, the audio sensor 165 may receive voice data necessary for a real estate market price estimation service from a user.

The interface module 140 may communicatively connect the terminal 100 with one or more other devices. Specifically, interface module 140 may include wired and/or wireless communication devices compatible with one or more different communication protocols.

Through this interface module 140, the terminal 100 can be connected to various input/output devices.

For example, the interface module 140 may output audio by being connected to an audio output device such as a headset port or a speaker.

Although it has been described that the audio output device is connected through the interface module 140 as an example, an embodiment installed inside the terminal 100 may also be included.

Also, for example, the interface module 140 may obtain a user input by being connected to an input device such as a keyboard and/or a mouse.

Although it has been described that the keyboard and/or mouse are illustratively connected through the interface module 140, an embodiment installed inside the terminal 100 (100) may also be included.

The interface module 140 connects a device having a wired/wireless headset port, an external charger port, a wired/wireless data port, a memory card port, and an identification module. Ports, audio I/O (Input/Output) ports, video I/O (Input/Output) ports, earphone ports, power amplifiers, RF circuits, transceivers and other communication circuits It may be configured to include at least one of.

Input system 150 may detect user input (eg, gestures, voice commands, button actuations, or other types of input) related to the real estate quote service.

In detail, the input system 150 may include a button, a touch sensor, and/or an image sensor 161 that receives a user motion input.

In addition, the input system 150 may be connected to an external controller through the interface module 140 to receive a user's input.

The display system 170 may output various information related to the real estate market price estimation service as a graphic image.

In an embodiment, the display system 170 may display a market price visualization graph or the like that visualizes the change flow of data of a specific actual transaction.

Such displays include a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. , a 3D display, and an e-ink display.

The components may be disposed in the housing of the terminal 100, and the user interface may include a touch sensor 173 on the display 171 configured to receive a user touch input.

In detail, the display system 170 may include a display 171 that outputs an image and a touch sensor 173 that detects a user's touch input.

For example, the display 171 may be implemented as a touch screen by forming a mutual layer structure or integrally with the touch sensor 173 . Such a touch screen may function as a user input unit providing an input interface between the terminal 100 and the user, and may provide an output interface between the terminal 100 and the user.

Meanwhile, the terminal 100 according to an embodiment of the present invention may perform deep learning required for a real estate price estimation service in conjunction with a deep-learning neural network.

Here, the deep learning neural network according to the embodiment may include a deep learning neural network based on a deep learning model such as Bidirectional Recurrent Imputation for Time Series (BRITS), GP-GAE, and/or E ² GAN.

Also, depending on the embodiment, the terminal 100 may further perform at least a part of the functional operation performed by the real estate price estimation server 200 to be described later.

- Real estate price estimation server (200: Real estate price estimation server)

Meanwhile, the real estate market price estimation server 200 according to an embodiment of the present invention may perform a series of processes for providing a real estate market price estimation service.

In detail, in the embodiment, the real estate market price estimating server 200 provides the real estate market price estimation service by exchanging data necessary for driving the real estate market price estimation process in an external device such as the terminal 100 with the external device. can provide

In more detail, in the embodiment, the real estate price estimation server 200, in an external device (in the embodiment, the mobile type computing device 100-1 and/or the desktop type computing device 100-2, etc.), estimates the application ( 111) can provide an environment in which it can operate.

To this end, the real estate price estimation server 200 may include an application program, data, and/or instructions for the estimation application 111 to operate, and may transmit/receive data based thereon with the external device.

In addition, in an embodiment, the real estate market price estimation server 200 may acquire actual transaction price data based on sales by predetermined period, by zone, by complex, by size, and/or by floor.

As an embodiment, the real estate price estimation server 200 collects the above-described actual transaction price data based on linkage with external servers (eg, KB Real Estate, Korea Appraisal Board and / or Ministry of Land, Infrastructure and Transport servers, etc.) and / or user input can do.

In addition, in an embodiment, the real estate market price estimation server 200 may perform a preprocessing process of correcting (filtering) the actual transaction price data according to a predetermined criterion.

In addition, in the embodiment, the real estate market price estimation server 200 may set a blacksmith complex, which is a complex that leads the market price in a predetermined area, based on the actual transaction price data.

In addition, in the embodiment, the real estate price estimation server 200, based on the actual transaction price data, for a specific point in time (eg, a specific year, month, and/or date, etc.) among at least one or more complexes existing in a predetermined area It is possible to set a target complex, which is a complex containing missing values in which actual transactions do not have data.

In addition, in an embodiment, the real estate price estimation server 200 may perform a missing value processing process of interpolating the missing value of the target complex based on the actual transaction price data.

Further, in an embodiment, the real estate price estimation server 200 may generate current price information for at least one complex existing in a predetermined area based on the actual transaction price data to which the missing value processing is applied.

Here, the current market price information according to an embodiment may be information obtained by estimating actual transaction price data at the current time point based on the at least one complex and/or equilibrium. A detailed description of this will be described in a method for estimating real estate market prices to be described later.

In addition, in the embodiment, the real estate price estimation server 200 visualizes and represents a trend of change in the actual trade price data for each of the at least one complex and/or equilibrium based on the actual trade price data and the current price information, and is a market price visualization graph. can be created and provided.

In addition, in an embodiment, the real estate price estimation server 200 may perform deep learning required for a real estate price estimation service in conjunction with a predetermined deep-learning neural network.

In detail, in the embodiment, the real estate price estimation server 200 reads a predetermined deep learning neural network driving program built to perform the deep learning from a memory module, and transfers the read predetermined deep learning neural network system to the program. The deep learning described below can be performed.

Here, the deep learning neural network according to the embodiment may include a deep learning neural network based on a deep learning model such as Bidirectional Recurrent Imputation for Time Series (BRITS), GP-GAE, and/or E ² GAN.

At this time, depending on the embodiment, the above deep learning neural network is directly included in the real estate price estimation server 200 or implemented as a device and/or server separate from the real estate price estimation server 200 to provide the real estate price estimation service. Deep learning can be performed for

In the following description, it is described that the deep learning neural network is included and implemented in the real estate price estimation server 200, but is not limited thereto.

In addition, in the embodiment, the real estate price estimation server 200 may store and manage various application programs, commands, and/or data for implementing the real estate price estimation service.

As an embodiment, the real estate price estimation server 200 stores at least one or more market price time series data, bookkeeping complex information, target complex information, missing value information, current price information, market price visualization graph, and/or a predetermined deep learning model, and the like. can manage

On the other hand, further referring to FIG. 1, in the embodiment, the real estate price estimation server 200 as described above includes at least one processor module (210) for data processing and at least one processor module for exchanging data with an external device. A predetermined computing device including one or more communication modules (220: Communication Module) and at least one or more memory modules (230: Memory Module) storing various application programs, data and/or instructions for providing a real estate quote estimation service. can be implemented as

Here, the memory module 230 may store any one or more of an operating system (OS), various application programs, data, and instructions for providing a real estate market price estimation service.

Also, the memory module 230 may include a program area and a data area.

Here, the program area according to the embodiment may be linked between an operating system (OS) that boots the terminal 100 and functional elements, and the data area may be data generated according to the use of the terminal 100. can be stored.

In an embodiment, the memory module 230 may be a variety of storage devices such as ROM, RAM, EPROM, flash drive, hard drive, etc., and a web device that performs the storage function of the memory module 230 on the Internet. It may also be web storage.

Also, the memory module 230 may be a recording medium detachable from the terminal 100 .

Meanwhile, the processor module 210 may control the overall operation of each unit described above in order to implement the real estate market price estimation service.

The processor module 210 may be a system on chip (SOC) suitable for the terminal 100 including a central processing unit (CPU) and/or a graphics processing unit (GPU), and is stored in the memory module 230. It can execute an operating system (OS) and/or an application program, and can control each component mounted on the terminal 100 .

In addition, the processor module 210 may communicate internally with each component through a system bus, and may include one or more predetermined bus structures including a local bus.

In addition, the processor module 210 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and controllers. ), micro-controllers, microprocessors, and electrical units for performing other functions.

In the above description, it has been described that the real estate price estimation server 200 according to the embodiment of the present invention performs the functional operations as described above, but at least some of the functional operations performed by the real estate price estimation server 200 according to the embodiment may be performed in an external device (eg, terminal 100, etc.), and at least a part of the functional operation performed in the external device may be further performed in the real estate price estimation server 200. It could be possible.

- How to estimate real estate market price

Hereinafter, a method of estimating real estate prices by the estimation application 111 executed by at least one processor of the terminal 100 according to an embodiment of the present invention will be described in detail with reference to FIGS. 3 to 5 attached.

In an embodiment of the present invention, at least one processor of the terminal 100 may execute at least one estimation application 111 stored in at least one memory 110 or operate in a background state.

Hereinafter, the at least one or more processors operate to execute commands of the estimation application 111 to perform the method of providing the above-described real estate market price estimation service, which is shortened to that the estimation application 111 performs. do.

3 is a flowchart of a method for estimating real estate market prices according to an embodiment of the present invention.

Referring to FIG. 3, in an embodiment, the estimation application 111, which is executed by at least one processor of the terminal 100 or operates in a background state , collects and pre-processes market price time-series data for the entire complex in the first zone. can do. (S101)

Here, a 'complex' according to an embodiment may mean a certain area in which a certain residential space (eg, an apartment and/or an officetel, etc.) forms a group.

In addition, the 'entire complex' according to the embodiment may include at least one affiliated complex, and the affiliated complex may include a plurality of households of each type.

In addition, the 'quote time series data' according to the embodiment is time series data showing trends in actual transaction price data based on sales for the entire complex over time, and in detail, for a plurality of households in the entire complex The flow of actual transaction price data may be data represented in a time series format following a predetermined period by dividing the flow of data based on the affiliated complex and the household equilibrium.

That is, in the embodiment, the market price time series data divides the flow of actual transaction price data based on sales for each of a plurality of households in the entire complex by first grouping by the affiliated complex, and within the first grouped group It may be data presented in a time series format after being divided into a second group based on the equilibrium by generation.

In detail, in the embodiment, the estimation application 111 interlocks with an external server (eg, KB Real Estate, Korea Appraisal Board, and/or Ministry of Land, Infrastructure and Transport servers, etc.) to obtain market prices for all complexes in the first zone for a predetermined period of time. Time series data can be collected.

For example, the estimating application 111 converts market price time series data based on actual transaction prices of apartments generated during a predetermined period (eg, March 2003 to March 2021, etc.) for the first zone to KB Real Estate and/or Alternatively, it can be obtained by receiving it from the Korea Appraisal Board server.

In addition, in the embodiment, the estimation application 111 may perform preprocessing of correcting the collected time-series data as above.

In detail, the estimation application 111 is the time series data for each of the at least one belonging complex included in the quote time series data (ie, the actual transaction based on the sales in a time series format divided based on the equilibrium by a plurality of households in the belonging complex) Based on the missing value ratio in data representing ), preprocessing may be performed on the time series data.

In more detail, the estimating application 111 follows a predetermined period (eg, March 2003 to March 2021, etc.) on the time series data representing the flow of actual transactions in the first affiliated complex, a specific value within the predetermined period. The number of missing values for which there is no actual transaction data corresponding to a time point (eg, a specific year, month, and/or date) may be counted.

In addition, the estimation application 111 may calculate a proportion of the counted missing values compared to the predetermined period to derive a missing value ratio for the first belonging complex.

In addition, in the embodiment, the estimation application 111, if the missing value ratio derived as above satisfies a predetermined criterion (eg, a predetermined percentage (%) unit value or higher, etc.), the time series data for the affiliated complex is It can be excluded from the market price time series data for Zone 1.

For example, if the predetermined criterion for the missing value ratio is '25% or more' and the missing value ratio for the first affiliated complex is '30%', the estimating application 111 determines the time series for the first affiliated complex. Data may be excluded from the market price time series data for the first zone.

In addition, in an embodiment, the estimation application 111 may perform pre-processing on the market price time series data based on the total number of households in the affiliated complex.

In detail, the estimation application 111, when the total number of new generations in the affiliated complex meets a predetermined criterion (eg, a predetermined number of households (eg, 100 households, etc.) or less, etc.), the time series data for the affiliated complex It can be excluded from the market price time series data for Zone 1.

In addition, in the embodiment, the estimation application 111 may perform pre-processing on the quote time-series data based on the number of actual transaction price data for the affiliated complex.

In detail, the estimation application 111, when the number of actual transaction data for the affiliated complex meets a predetermined criterion (eg, less than or equal to a predetermined number), the time series data for the affiliated complex for the first zone Price can be excluded from time series data.

In addition, in an embodiment, the estimation application 111 may perform pre-processing on the market price time-series data based on the time-series data for a household corresponding to a predetermined number of floors.

In detail, the estimation application 111 may exclude time-series data for low-rise households corresponding to a predetermined number of floors (eg, first to third floors, etc.) from the market price time-series data for the first zone.

Alternatively, the estimation application 111 applies a predetermined operation (eg, 1.2 magnification, etc.) to time-series data for low-rise households corresponding to a predetermined number of floors (eg, 1st to 3rd floors, etc.) to apply a predetermined operation to the first zone. You can calibrate quote time series data for .

Also, in an embodiment, the estimation application 111 may perform pre-processing on the time series data based on the time series data for the generation corresponding to the preset exception type.

As an embodiment, the estimation application 111 converts time series data for households corresponding to the preset exception type (eg, special residential space households such as penthouses in the affiliated complex) to market price time series data for the first zone. can be excluded from

In this way, the estimating application 111, within the market price time series data, has an excessively large number of missing values of a specific affiliated complex, an excessively small number of households, or a situation requiring separate exception processing, etc., in a predetermined special situation. In the case of actual transaction price data corresponding to , it is possible to perform a separate correction process to improve the quality of basic data that is the basis of the process described later, and various data generated based on this (examples, current market price information and / or a market price visualization graph, etc.) can also be improved.

In addition, in the embodiment, the estimation application 111 may set the ledger of the first zone based on the pre-processed time-series data as above. (S103)

Here, the 'daejang complex' according to the embodiment may refer to an affiliated complex selected as a complex leading the market price of the first zone among at least one affiliated complexes in the first zone.

In detail, in the embodiment, the estimation application 111 selects at least one blacksmithing complex for the first zone, based on the preprocessed time series data (hereinafter referred to as preprocessed time series data) obtained as above for the first zone. can do.

In more detail, in an embodiment, the estimation application 111 may set a belonging complex that meets a predetermined number of households (eg, 1000 households, etc.) or more in the preprocessing time series data as the managerial complex.

In another embodiment, the estimation application 111 may set a belonging complex that meets a predetermined actual transaction volume or more in the pre-processed time series data as the bookcase.

In another embodiment, the estimation application 111, within the pre-processed time series data, may set a belonging complex having actual transaction price data that meets a predetermined standard deviation as the bookcase.

Depending on the embodiment, the estimation application 111 determines whether or not a new construction is performed for each affiliated complex included in the preprocessing time series data in conjunction with an external server (eg, KB Real Estate, Korea Appraisal Board and / or Ministry of Land, Infrastructure and Transport server, etc.), Based on this, the blacksmithing site may be set.

Specifically, the estimation application 111, based on the new construction data for each affiliated complex obtained from the external server, determines the newly built affiliated complex within a predetermined period (eg, 5 years, etc.) as a new affiliated complex, and The belonging complex determined as the belonging complex may be set as the manager complex.

In addition, according to the embodiment, the estimation application 111, in conjunction with an external server (eg, KB Real Estate, Korea Appraisal Board and / or Ministry of Land, Infrastructure and Transport servers, etc.), ledger for the first zone preset by the external server Only information may be obtained, and based on this, the blacksmithing site may be set.

In the above, the embodiments in which the estimation application 111 sets the blacksmithing are classified and described as described above for effective description. Various embodiments may also be possible.

At this time, in the embodiment, the estimation application 111 may set a bookstore for each administrative district (eg, eup / myeon / dong / city / county / gu, etc.) included in the first district.

In detail, the estimating application 111 may set the ledgers mapped for each administrative district in the first district according to the above-described method.

That is, the estimation application 111, when a plurality of administrative districts exist within the first district, may set a plurality of ledgers for the first district.

In addition, in the embodiment, the estimation application 111 determines the first area and/or the first area according to the area and/or population of each administrative district included in the first area and/or the first area. It is also possible to set up a plurality of ledger complexes for each administrative district.

In an embodiment, the estimation application 111 may, if the area and/or population of the first area exceed a predetermined reference value, the first area and/or the first area includes the first area according to the degree of excess compared to the reference value. The number of blacksmith complexes for each administrative district can be increased.

At this time, in the embodiment, the estimation application may acquire and utilize data such as the administrative district, area, and/or population of the first district based on user input and/or interworking with an external server.

In this way, the estimation application 111 sets at least one ledger that is determined to lead the market price of the first zone in the manner described above, thereby recalling the missing value of actual transaction price data for the first zone later. It can be reinforced based on the time-series data of the blacksmithing complex that leads the market price of the first zone, and through this, the reliability of the correction of the missing value can be further guaranteed.

In addition, in the embodiment, the estimation application 111 considers that a large complex for a specific area may change according to environmental changes (eg, construction of a new affiliated complex and/or reorganization of administrative districts, etc.) for that area. To this end, as described above, the process of setting the ledger of the first section may be repeatedly performed at predetermined intervals (eg, every year or every month) to update the ledger of the first section.

In addition, in the embodiment, the estimation application 111 may set a target complex of the first zone based on the pre-processed time-series data. (S105)

Here, the 'target complex' according to the embodiment refers to at a specific point in time (eg, a specific year, month, and/or date) within a predetermined period following the preprocessing time series data, among at least one affiliated complex in the first zone. The corresponding real transaction may mean a belonging complex including a missing value that occurs when data is absent.

In detail, in the embodiment, the estimation application 111 analyzes the pre-processed time series data for the first zone to detect the missing value as described above that meets a predetermined criterion (eg, a predetermined number or more). can

In addition, the estimation application 111 may set the detected belonging complex as a target complex of the first zone.

At this time, the estimation application 111 may detect at least one belonging complex that meets the predetermined criterion, and may set at least one target complex for the first zone based on this.

In addition, in the embodiment, the estimation application 111 may perform missing value processing for the target complex set as above. (S107)

In detail, in the embodiment, the estimation application 111 is time-series data for the blacksmith complex set as described above (ie, data representing actual transactions based on sales in a time-series format divided based on equilibrium by a plurality of generations in the blacksmith complex) Based on , missing value processing for interpolating missing values for the target complex may be performed.

More specifically, in the embodiment, the estimation application 111 may select a core blacksmithing complex determined to have the greatest influence on the market price of the target complex, among at least one blacksmithing complex set for the first zone.

Specifically, the estimating application 111 may set, among the at least one blacksmith complex set for the first district, a blacksmith complex included in the same administrative district as the target complex as the first candidate estate.

In addition, the estimation application 111, a blacksmith complex located within a predetermined radius (eg, a radius of 10 km, etc.) based on a predetermined point (eg, a central point or an outer point, etc.) in the area occupied by the target complex is second. It can be set as a candidate site.

In addition, the estimating application 111 may set a blacksmith complex having the highest average market price among at least one blacksmith depository as a third candidate depository.

In addition, the estimation application 111 may select a core blacksmith complex for the target complex based on the first to third candidate complexes set as above.

In detail, in the embodiment, the estimating application 111 may select a blacksmith complex that is most overlapped and included on the first to third candidate complexes as a core blacksmith complex.

Alternatively, in an embodiment, the estimation application 111 may detect one candidate complex group including at least one bookkeeping complex according to preset priorities for the first to third candidate complexes.

In addition, the estimating application 111 may use a predetermined criterion (e.g., in order of highest number of households, in order of actual transaction volume, in order of low standard deviation, and/or in order of newest year of new construction) among at least one blacksmithing complex in the detected one candidate complex group. etc.) can be selected as the core blacksmith complex.

4 is an example of a diagram for explaining a DTW-BI process based on a Dynamic Time Warping (DTW) algorithm according to an embodiment of the present invention.

On the other hand, referring to FIG. 4, in another embodiment, the estimation application 111, among the at least one blacksmithing complex set for the first zone, time series data that meets a predetermined similarity with the time series data for the target complex. The branched blacksmith complex can be selected as the core blacksmith complex.

In detail, the estimation application 111, predetermined vector data for each of the time series data (hereinafter, target time series data) and the time series data (hereinafter, ledger time series data) for each of the at least one ledger complex for the target complex. can be obtained

Here, the vector data according to the embodiment may include a minimum value, a maximum value, an average value, a median value, a standard deviation value, a kurtosis value, a period length value, and/or the number of peaks based on a plurality of actual transaction price data in time series data. there is.

That is, the estimation application 111 may obtain target vector data for the target time-series data based on the plurality of actual transaction price data included in the target time-series data, and the plurality of actual transactions included in the ledger time-series data Based on the data, colon vector data for the colon time series data may be obtained.

In addition, the estimation application 111 may calculate cosine similarity (cosine 　similarity) using the target vector data and large intestine vector data obtained as above.

In detail, the estimation application 111 may execute an algorithm for calculating global features and cosine similarity by applying each vector value of the target vector data and large intestine vector data, through which the target vector data and large intestine Cosine similarity between vector data can be calculated.

Thus, the estimation application 111 may calculate a plurality of cosine similarities based on the at least one ledger vector data for each ledger complex and the target vector data of the target complex.

In addition, the estimation application 111, based on the plurality of cosine similarities calculated as above and a predetermined reference value (eg, a predetermined value, etc.), to select a first-order filtered first candidate complex from among the plurality of blacksmith complexes can

As an example, the estimation application 111 may detect at least one cosine similarity that satisfies a similarity equal to or greater than a predetermined reference value (eg, a predetermined value) from among the calculated plurality of cosine similarities.

In addition, the estimation application 111 may set a first candidate complex including at least one blacksmithing complex corresponding to the detected at least one cosine similarity.

In addition, the estimation application 111 performs a DTW-BI process based on the time-series data of each of the at least one blacksmith complex included in the set primary candidate complex, and any one of a plurality of blacksmith complexes in the primary candidate complex can be selected as the core blacksmith complex.

In detail, the estimation application 111 applies a dynamic time warping (DTW) algorithm to the time series data of each of the at least one ledger complex and the target time series data included in the set primary candidate complex, Any one of a plurality of blacksmith complexes in the primary candidate complex may be selected as the core blacksmith complex.

For reference, the dynamic time warping algorithm is an algorithm for measuring similarity between two different time sequences, and may be an algorithm for measuring wavelength similarity of time axes having different velocities.

In more detail, the estimation application 111 applies the dynamic time warping algorithm to each of the at least one colon time series data and the target time series data included in the primary candidate complex, so that the relationship between the colon time series data and the target time series data A plurality of DTW similarities may be acquired.

In addition, the estimation application 111 may detect the highest DTW similarity having the highest similarity value among the obtained plurality of DTW similarities.

In addition, the estimating application 111 may select a bookstore corresponding to the detected highest DTW similarity as a key bookstore for the target complex.

In addition, according to an embodiment, the estimation application 111 further considers other features (eg, number of households, location, and/or surrounding environmental conditions) having a significant influence on the market price of the target complex, and determines the first candidate complex. Any one of at least one blacksmithing complex within the blacksmithing complex may be selected as the core blacksmithing complex.

In the above, for effective explanation, the embodiments for selecting the core blacksmith complex for the target complex have been described separately as described above, but according to the embodiment, at least some of the above embodiments may be organically combined with each other and operated. Various embodiments may also be possible.

Thus, the estimating application 111 may select a core blacksmithing complex to be used for processing the missing value of the target complex from among at least one blacksmithing complex for the first zone.

In this way, the estimation application 111 selects the core blacksmith complex that is determined to provide the most useful time-series data for processing the missing value of the target complex in the manner described above, so that the actual transaction for the target complex is the most suitable for the data. Based on the time-series data that exerts a great influence, the missing value processing of the target complex can be performed and its accuracy can be increased.

Subsequently, in the embodiment, the estimation application 111 may detect time series data (hereinafter referred to as core time series data) for the core blacksmithing complex selected as above from the preprocessed time series data for the first zone.

In addition, the estimation application 111 may perform missing value processing for the target complex based on the detected core time series data.

At this time, depending on the embodiment, the estimation application 111 may perform pre-missing value processing on the missing value of the target complex.

Here, the 'preliminary missing value processing' according to the embodiment refers to determining whether the missing value satisfies a predetermined condition before performing the missing value processing for the target complex based on the core time series data, and If ? is satisfied, it may refer to a process of performing the missing value processing according to at least one of methods described below.

More specifically, in the embodiment, the estimation application 111 performs a linear interpolation method based on the target time series data of the target complex when the missing value of the target complex is less than a predetermined threshold (eg, 5% or less of the missing value). Missing value processing for the target complex may be performed using an interpolation method.

In addition, in the embodiment, the estimation application 111, when the missing value of the target complex is greater than or equal to a predetermined threshold, is a BRITS deep learning model specialized in univariate time series missing value interpolation and a generation model-based GP- Missing value processing for the target complex may be performed using a predetermined deep learning model, such as a GAE and/or an E2GAN deep learning model.

In addition, in the embodiment, the estimation application 111 performs missing value processing for the target complex through linkage with an external server (eg, KB Real Estate, Korea Appraisal Board and / or Ministry of Land, Infrastructure and Transport servers, etc.) according to user settings , Missing value processing for the target complex may be performed using actual transaction price data provided from the external server.

5% 범위 이내의 실거래가 데이터에 기초하여 상기 타겟단지에 대한 결측치 처리를 수행할 수 있다. For example, the estimation application 111, the actual transaction price data provided by the external server, before and after the moving average line based on a predetermined period (eg, 3 months, etc.)

Missing value processing for the target complex may be performed based on actual transaction data within the range of 5%.

In this way, the estimation application 111 may improve the efficiency of processing the missing value of the target complex by performing pre-processing on the missing value of the target complex according to a preset situation.

Returning again, in an embodiment, estimation application 111 may perform missing value processing for the target complex based on the core time series data described above.

In detail, further referring to FIG. 4, the estimation application 111 includes the core time series data, which is the time series data of the core blacksmith complex, the target time series data, which is the time series data of the target complex, and the dynamic time warping (DTW) algorithm Based on , the above-described DTW-BI process-based missing value processing may be performed.

In other words, the dynamic time warping algorithm is an algorithm for measuring the similarity of two different time sequences, and may be an algorithm for measuring the wavelength similarity of time axes having different velocities.

More specifically, in an embodiment, the estimation application 111 uses the dynamic time warping algorithm to compare changes in time series data between the core time series data and the target time series data during a predetermined period (eg, the last year, etc.). can do.

In an embodiment, the estimation application 111 applies the core time series data and the target time series data to the dynamic time warping algorithm, and the actual transaction price data (hereinafter referred to as core time series data included in the core time series data for the predetermined period). Actual transaction price data) and actual transaction price data included in the target time-series data for the predetermined period (hereinafter, target actual transaction price data) may be mutually compared.

In addition, in an embodiment, the estimation application 111 may obtain a market rate ratio between the core time series data and the target time series data following the predetermined period through a comparison based on the above dynamic time warping algorithm. .

Here, the 'market price ratio' according to the embodiment is determined by calculating a ratio between at least one core actual transaction price data and a corresponding target actual transaction price data value, and calculating an average value for the at least one or more calculated ratios. , an actual transaction between the core time series data and the target time series data during the predetermined period may be a ratio average.

In detail, the estimation application 111 is capable of cross-referencing within the core time series data and the target time series data, that is, at least one core actual transaction data without a missing value-target actual transaction price data pair (hereinafter, core-target actual transaction Data), at least one element ratio indicating a ratio between the core actual transaction price data and the corresponding target actual transaction price data value may be calculated.

In addition, the estimation application 111 may calculate a market rate between the core time series data and the target time series data by calculating an average value of the calculated at least one element ratio.

In addition, in an embodiment, the estimation application 111 may perform missing value processing for the target complex based on the market price ratio obtained as above.

In detail, the estimation application 111 may perform the missing value processing based on the market rate and surrounding data having a predetermined relationship with the missing value for the target complex.

Here, the 'surrounding data' according to the embodiment is the average value of a plurality of actual transaction data included in the month or year when the missing value exists and/or by a predetermined number of days based on the time point at which the missing value exists. A plurality of actual transactions belonging to the before and/or after period may include an average value of data, and the like.

More specifically, the estimating application 111 may obtain surrounding data as described above based on missing values for the target complex.

In addition, the estimation application 111 may obtain an interpolation value for the missing value by performing a predetermined operation based on the obtained surrounding data and the above-described market price ratio.

For example, the estimation application 111 may obtain an interpolation value for the missing value by performing a multiplication operation based on the surrounding data value and the market rate value.

In addition, the estimation application 111 may perform missing value processing for the target complex by replacing the missing value with the interpolation value obtained as above.

In the above, for effective description, the embodiments of processing missing values for the target complex have been separately described as described above, but depending on the embodiment, at least some of the above embodiments may organically combine with each other and operate in various ways. Examples may also be possible.

In this way, the estimation application 111 interpolates the missing value for the actual transaction data that occurs for reasons such as lack of real estate transaction history within a specific period, as described above, to all complexes within the corresponding area based on reasonable data. It is possible to obtain complete form of time series data that does not contain missing values, and later create current quotes and/or visualized data based on this form of time series data to improve the quality and reliability.

In addition, in the embodiment, the estimation application 111 that has performed the missing value processing for the target complex as described above may generate current market price information for all complexes in the first zone. (S109)

Here, the 'current market price information' according to the embodiment is based on actual transaction price data obtained from the past (hereinafter, existing actual transaction price data) and actual transaction price data predicted for the future (hereinafter, predicted actual transaction price data), etc. Actual transaction price data (hereinafter, current actual transaction price data) at the current time may be information estimated for each affiliated complex and each equilibrium included in the entire complex.

In detail, in the embodiment, the estimation application 111, based on the pre-processed time series data including the target time series data for which missing value processing has been performed as described above, from before a predetermined period to the present for the entire complex in the first zone Existing market price time series data, which is time series data including existing actual transaction price data, may be obtained.

In addition, in the embodiment, the estimation application 111, based on the pre-processing time series data, predicted actual transaction price data, which is predicted actual transaction data from the present to a predetermined period later for all complexes in the first zone. Predicted price time series data can be obtained.

Specifically, the estimation application 111, based on the existing actual transaction price data in the pre-processing time series data, it is possible to determine the price change trend of the actual transaction price data from before the predetermined period to the present.

In addition, the estimation application 111 may acquire the predicted actual transaction price data by predicting actual transaction price data until after the predetermined period based on the identified price change trend.

For example, the estimation application 111 may obtain the predicted actual transaction price data by performing a prediction simulation of actual transaction price change following the price change trend based on a predetermined simulation algorithm.

In addition, in the embodiment, the estimation application 111 may generate the current market price information based on the existing actual transaction price data and the predicted actual transaction price data obtained as above.

In detail, the estimation application 111 estimates the current actual transaction price data for each affiliated complex and each equilibrium included in the entire complex by reflecting the price change trend according to the obtained existing actual transaction price data and the predicted actual transaction price data Current price information, which is information, can be created.

For example, the estimation application 111 uses a deep learning neural network and/or an estimation algorithm that performs estimation based on predetermined input data (in the embodiment, the existing actual transaction price data and predicted actual transaction price data, etc.) Accordingly, current market price information generated by reflecting the above-described price change trend may be obtained.

In this way, the estimating application 111 can estimate current market price information based on time series data in which missing values by absent actual transaction price data are interpolated, measure and provide more accurate current real estate market prices, and real estate transactions through this. fairness can be further enhanced.

At this time, depending on the embodiment, the estimation application 111 may acquire the current market price information by further reflecting the surrounding environmental conditions for each belonging complex within the entire complex.

Here, illustratively, the surrounding environmental conditions are of the surrounding complexes located within a predetermined radius (eg, a radius of 3 km, etc.) based on a predetermined point (eg, a central point or an outer point, etc.) within the area occupied by each affiliated complex. It may include price change trends, favorable or unfavorable news (eg, reorganization of administrative districts, etc.) around the affiliated complex, and/or an increase or decrease in sales in the vicinity of the affiliated complex.

In detail, the estimating application 111 may calculate the degree of influence (eg, a predetermined value, etc.) of the actual transaction data for each affiliated complex by the surrounding environmental conditions for each affiliated complex within the entire complex.

For example, the estimating application 111, when the price of the surrounding complex for the first affiliated complex shows an increasing trend, the degree of influence on the first affiliated complex is added by a predetermined value in proportion to the increased ratio can

As another example, the estimation application 111 may increase or decrease the degree of influence on the first affiliated complex by a predetermined value based on the increase or decrease ratio when the number of items for sale around the first affiliated complex increases or decreases.

In addition, the estimation application 111, based on the degree of impact calculated for each affiliated complex as above, it is possible to estimate the current actual transaction price data for all complexes in the first zone.

In detail, the estimation application 111, by performing a predetermined operation based on the current actual transaction price data previously estimated in the above manner and the degree of influence, to estimate the current actual transaction price data further reflecting the surrounding environmental conditions .

For example, the estimation application 111 may calculate a predetermined percentage value based on the degree of influence (eg, if the degree of influence is '3', calculate the percentage value as '3%'), , The current actual transaction price data may be estimated by performing a predetermined operation (eg, multiplication operation, etc.) based on the calculated percentage value and the previously estimated current actual transaction price data.

In addition, the estimation application 111 may generate current market price information for the entire complex in the first zone based on the current actual transaction price data estimated by further reflecting the surrounding environmental conditions as above.

In this way, the estimating application 111 may estimate the current real estate market price for each affiliated complex in consideration of the surrounding environmental conditions specialized for each affiliated complex, and generate more detailed and accurate current market price information based on this.

Meanwhile, according to an embodiment, the estimation application 111 may set the current market price information for the basic equilibrium preset for each affiliated complex as current market price information representing the corresponding affiliated complex (hereinafter, representative market price information).

Here, the 'basic equilibrium' according to the embodiment may mean one equilibrium representing the affiliated complex among at least one different equilibrium included in the affiliated complex.

In detail, the estimation application 111 may preset any one equilibrium according to a predetermined criterion among at least one equilibrium included in each affiliated complex as the basic equilibrium for each affiliated complex.

For example, the estimation application 111, among the different equilibria of the first belonging complex composed of a plurality of households having any one equilibrium of 24 equilibrium, 32 equilibrium, or 54 equilibrium, the equilibrium with the highest actual transaction volume (eg , 32 equilibrium, etc.) may be preset as the basic equilibrium for the first affiliated complex.

In addition, the estimation application 111 may set the representative market price information for the affiliated complex in the current market price information generated as described above to the current market price information generated with respect to the basic equilibrium preset for each affiliated complex. .

That is, the estimation application 111 may set the current market price information for the basic equilibrium preset for each belonging complex as the current market price information representing the corresponding belonging complex.

Therefore, the estimation application 111 may generate current market price information for all complexes based on representative market price information for each affiliated complex, and through this, the current market price information may be more simplified and provided in an easy-to-understand form. there is.

In addition, according to the embodiment, the estimation application 111, as described above, the current actual transaction price data estimated for each affiliated complex and each equilibrium included in the entire complex, and further for each affiliated complex, each equilibrium, and each floor number. It can also be subdivided into estimates.

In addition, the estimation application 111 may generate current market price information for the entire complex in the first zone based on the current actual transaction price data estimated by further subdivision as above.

Accordingly, the estimation application 111 may provide more detailed and detailed estimated current quote information.

In addition, in an embodiment, the estimation application 111 may generate and provide a market price visualization graph based on the current market price information and pre-processed time series data for the entire complex in the first zone generated as described above. (S111)

5 are examples of market price visualization graphs according to an embodiment of the present invention.

Here, referring to FIG. 5 , the 'quote visualization graph' according to the embodiment may mean a graph that visualizes and represents the flow of actual transaction data for a specific affiliated complex and equilibrium during a predetermined period.

In detail, in the embodiment, the estimation application 111 may further include the generated current market price information for all complexes in the first zone in the preprocessing time series data for all complexes in the first zone.

In addition, the estimation application 111 may generate the market price visualization graph based on preprocessed time series data (hereinafter referred to as extended time series data) further including the current market price information.

In more detail, in the embodiment, the estimation application 111 may determine a period for displaying actual transaction price data (hereinafter, a display period) through the market price visualization graph based on user settings and/or a pre-built algorithm. .

In addition, the estimation application 111, on the basis of user settings and / or pre-built algorithms, etc., the affiliated complex and equilibrium (hereinafter, the displayed affiliated complex and equilibrium) to display the actual transaction price data through the market price visualization graph can decide

In addition, the estimation application 111 may extract time-series data (hereinafter referred to as display time-series data) corresponding to the determined display period, display affiliation, and equilibrium from the extended time-series data.

In addition, the estimation application 111 may generate the market price visualization graph based on the extracted display time series data.

In an embodiment, the estimation application 111 may configure a first axis of the time series graph based on the display period, configure a second axis of the time series graph based on the display time series data, and the like. , The shape of the time-series graph may be constructed based on the determined elements.

For example, the estimation application 111 divides and displays the display period at specific intervals on the horizontal axis of the market price time series graph, and divides the actual transaction data value into specific intervals on the vertical axis of the market price time series graph. A template of the quote time series graph can be constructed to display.

In addition, the estimation application 111, based on the template of the market price time series graph constructed as above, displays the time series data in a predetermined manner (eg, bar chart, line chart, aria chart ( area chart) and/or scatter plot, etc.).

For example, the estimation application 111 corresponds each of a plurality of actual transaction price data included in the display time series data based on the display period displayed on the horizontal axis of the template and the actual transaction price data value displayed on the vertical axis of the template. It can be displayed on a template of a time series graph.

Thus, the estimation application 111 may generate a market price visualization graph that visualizes the time series data for the equilibrium and the affiliated complex to check the actual transaction data flow for a specific period.

In the above, it has been described that the estimation application 111 generates the market price visualization graph in the above-described manner, but this is only an example, and other methods (eg, pie chart, bubble chart) depending on the embodiment ), a radar chart, a frame diagram, and/or a funnel plot, etc.) may generate the market price visualization graph.

Also, in the embodiment, the estimation application 111 may display and provide the market price visualization graph generated as above.

In this way, the estimation application 111 visualizes and provides trends in actual transaction data for a specific period, a specific affiliated complex, and/or a specific equilibrium, so that the trends in the actual transaction data can be recognized more easily and intuitively. .

As described above, the method and system for estimating real estate market prices according to an embodiment of the present invention interpolate a predetermined missing real estate market price value in a specific zone based on time-series data representing the flow of real estate market prices in a specific complex representing a specific zone, for a specific period of time. Even in the case of a complex lacking my real estate transaction history, it is possible to supplement the absence of real estate market price data by the lack of history based on reliable ground data, and through this, information on specific real estate market price data for all complexes in the zone There is an effect of constructing a database based on time series data in a complete form without missing values.

In addition, the real estate market price estimation method and system according to an embodiment of the present invention interpolate a predetermined real estate market price missing value in the zone based on time-series data representing the flow of real estate market prices in a specific complex representing a certain zone, Based on credible ground data rather than heuristic judgment, there is an effect of automatically supplementing the real estate market price data lacking in the above district.

In addition, the method and system for estimating real estate market prices according to an embodiment of the present invention estimate current real estate market prices for a plurality of complexes in the zone based on the time series data in which the missing values are interpolated, so that actual transactions for a specific period of time are performed. Even in the case of a complex lacking a history, it is possible to estimate the current real estate market price in a state supplemented with reasonable real estate market price data, thereby improving the accuracy and reliability of the estimated current real estate market price and at the same time enhancing the fairness of real estate transactions. can

In addition, the real estate market price estimation method and system according to an embodiment of the present invention provide visualized data based on the estimated current real estate market price, so that users can individually search for real estate agencies or magazines and newspapers related to real estate for sale. There is an effect of reducing the effort or cost consumed to acquire the desired real estate market price information, such as performing analysis by searching the Internet or the like.

In addition, the real estate market price estimation method and system according to an embodiment of the present invention provide visualized data based on the estimated current real estate market price, so that the user intends real estate market price information quickly and intuitively in a form that is easy to recognize. There is an effect that can be provided.

In addition, the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer readable recording medium. The computer readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine language codes generated by a compiler. A hardware device may be modified with one or more software modules to perform processing according to the present invention and vice versa.

Specific implementations described in the present invention are examples and do not limit the scope of the present invention in any way. For brevity of the specification, description of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection of lines or connecting members between the components shown in the drawings are examples of functional connections and / or physical or circuit connections, which can be replaced in actual devices or additional various functional connections, physical connection, or circuit connections. In addition, if there is no specific reference such as “essential” or “important”, it may not be a component necessarily required for the application of the present invention.

In addition, the detailed description of the present invention described has been described with reference to preferred embodiments of the present invention, but those skilled in the art or those having ordinary knowledge in the art will find the spirit of the present invention described in the claims to be described later. And it will be understood that the present invention can be variously modified and changed without departing from the technical scope. Therefore, the technical scope of the present invention is not limited to the contents described in the detailed description of the specification, but should be defined by the claims.

Claims (14)

A method for estimating a real estate market price by a real estate market price estimation application executed by at least one processor of a terminal,
Collecting market price time-series data in which trends in actual transaction price data for each of a plurality of affiliated complexes belonging to all complexes in the first zone are arranged according to the lapse of time;
performing pre-processing on the collected time-series data;
determining at least one affiliated complex among the plurality of affiliated complexes as a major complex leading the real estate market price in the first zone based on the preprocessed market price time series data;
detecting a target complex including a missing value in which there is no actual transaction price data corresponding to at least one period among the plurality of affiliated complexes based on the preprocessed market price time series data;
interpolating a missing value for the target complex based on the time-series data of the determined blacksmith complex; and
Comprising the step of calculating current market price information for the entire complex based on the market price time series data interpolated with the missing value
How to estimate real estate market value. According to claim 1,
The quote time series data,
Data showing the trends of the actual transaction price data for each of the plurality of households in the plurality of affiliated complexes based on the affiliated complex and a predetermined equilibrium in a time series format
How to estimate real estate market value. According to claim 1,
The step of performing preprocessing on the collected quote time series data,
removing time series data of a target complex including a predetermined number or more of missing values from the market price time series data;
removing time-series data of a complex belonging to a predetermined number of households or less from the market price time-series data;
removing the time series data of the complex to which the actual transaction price data is less than the reference value from the market price time series data;
Including at least one step of removing or changing actual transaction price data of a predetermined number of floors or less from the quote time series data
How to estimate real estate market value. According to claim 1,
The step of determining the blacksmith complex leading the real estate market price in the first zone,
Determining at least one affiliated complex among the plurality of affiliated complexes as the head complex based on at least one of the number of actual transaction price data, the number of households, the standard deviation of the actual transaction price data for each of the plurality of affiliated complexes, and whether or not they are newly built. containing
How to estimate real estate market value. According to claim 4,
The step of determining at least one belonging complex among the plurality of belonging complexes as a large estate complex,
Further comprising the step of determining whether to determine a plurality of blacksmith complexes for the first district based on at least one of the administrative district, area, and population in the first district
How to estimate real estate market value. According to claim 1,
The step of interpolating the missing value for the target complex,
If the ratio of the number of missing values to the number of total actual transactions included in the time series data of the target complex is less than or equal to a predetermined reference value, interpolating missing values using a linear interpolation method based on the time series data of the target complex Interpolating missing values
How to estimate real estate market value. According to claim 1,
The step of interpolating the missing value for the target complex,
When a plurality of blacksmith complexes are determined for the first zone, determining a core blacksmith complex that has the greatest influence on the real estate market price of the target complex
How to estimate real estate market value. According to claim 7,
The step of determining the core blacksmith complex,
Detecting a large intestine complex included in the same administrative district as the target complex;
Detecting a large intestine complex located within a predetermined radius based on the target complex;
Detecting a blacksmith complex that forms the highest real estate market price average among the plurality of blacksmith complexes;
Determining the core blacksmith site based on the detected at least one or more blacksmith sites
How to estimate real estate market value. According to claim 7,
The step of determining the core blacksmith complex,
Determining a blacksmith complex having time series data that meets a predetermined similarity with the time series data of the target complex as the core blacksmith complex
How to estimate real estate market value. According to claim 7,
The step of interpolating the missing value for the target complex,
Further comprising interpolating the missing value according to a dynamic time warping (DTW) algorithm based on the determined time series data of the core blacksmith complex and the time series data of the target complex
How to estimate real estate market value. According to claim 1,
Calculating the current market price information for the entire complex,
Based on the market price time series data in which the missing value is interpolated, existing market price time series data including actual transaction price data from before a predetermined period to the present and predicted market price time series data including actual transaction price data predicted from the present to a predetermined period later obtaining steps;
Estimating actual transaction price data at the current time for each equilibrium of each affiliated complex based on the obtained existing market price time series data and the predicted market price time series data
How to estimate real estate market value. According to claim 11,
Calculating the current market price information for the entire complex,
Further comprising the step of re-estimating the actual transaction price data at the estimated current time based on the surrounding environmental conditions for each of the plurality of affiliated complexes
How to estimate real estate market value. According to claim 1,
Generating and providing a market visualization graph visualizing the time series data of a specific affiliated complex and a specific equilibrium based on the calculated current market price information and the market price time series data interpolated with the missing value
How to estimate real estate market value. At least one display that outputs a market price visualization graph;
at least one memory; and
at least one processor; including,
at least one application stored in the memory and executed by the processor to estimate a real estate market price, the at least one application comprising:
Collecting market price time-series data in which trends in actual transaction price data for each of a plurality of affiliated complexes belonging to all complexes in the first zone are arranged according to the lapse of time,
Perform preprocessing on the collected time series data,
Based on the preprocessed market price time series data, at least one affiliated complex among the plurality of affiliated complexes is determined as a large complex that leads the real estate market price in the first zone,
Based on the preprocessed market price time series data, detecting a target complex including a missing value in which there is no actual transaction price data corresponding to at least one period among the plurality of affiliated complexes;
Interpolating missing values for the target complex based on the time series data of the determined blacksmith complex;
Calculate current market price information for the entire complex based on the market price time series data interpolated with the missing values;
Generating and providing the market price visualization graph visualizing the time series data of a specific belonging complex and a specific equilibrium based on the calculated current market price information and the market price time series data in which the missing value is interpolated
Real Estate Price Estimation System.

Images