KR20210114903A - System for estimating market price of real estate and method - Google Patents

Abstract

The present invention relates to a real estate market price estimation system capable of accurately extracting an address of a target real estate property and precisely estimating a market price of the real estate property based on the same, and a method thereof. The system includes: an information providing server regularly providing information disclosed by the nation; a management server estimating an appropriate market price of a target real estate property by extracting a reference real estate property based on information about a land register, land characteristic information, a building register, and an erasure register, provided by the information providing server; a database storing the information about the land register, the land characteristics, the building register, and the erasure register as real estate information regarding detached/multi-household houses, land, commercial/business buildings, apartment buildings, studio flats and ownership, provided by the information providing server; and a user terminal receiving appropriate market price information of the target real estate property estimated by the management server. The management server extracts an address of each real estate property in accordance with the information about the land register, the land characteristics, the building register, and the erasure register, and extracts similarity about a real sale price of the reference real estate property adjacent to the target real estate property to calculate the appropriate market price of the target real estate property and transmit the appropriate market price information to the user terminal, thereby precisely estimating the market price of the target real estate property.

Description

Real estate price estimation system and method

The present invention relates to a real estate market price estimation system and method, in particular, a real estate market price estimation system capable of accurately extracting actual transaction information using real estate-related information disclosed by the state, such as the Ministry of Land, Infrastructure and Transport, and estimating the market price of a target real estate accordingly and methods.

In general, if you want to get information on real estate prices, you can go to a real estate agent one by one to get information, or you can get information about real estate sales through magazines, newspapers, or the Internet. If you try to find information by visiting real estate agencies, it takes a long time to get the information you want and requires a lot of money and effort, and it is virtually impossible to obtain accurate information through magazines or newspapers about real estate sales did. The method through the Internet is to access each site that provides real estate information and search for free or paid information to obtain the official land price, real estate sale price, jeonse price, monthly rent price, public sale information and auction information, but collect and analyze each information. There are inconveniences to be had. In other words, the searcher could obtain the intended information only by collecting and collating the information one by one.

Meanwhile, although the Ministry of Land, Infrastructure and Transport provides real estate transaction data, it does not provide the exact transaction date or exact address to protect personal information.

In other words, real estate transaction information is basically based on the actual transaction price of real estate provided by the Ministry of Land, Infrastructure and Transport, and the Ministry of Land, Infrastructure and Transport is based on Article 7 (1) and (2) (publication of administrative information) of the "Act on Information Disclosure of Public Institutions". Actual transaction price is disclosed for real estate that has reported real estate transaction under /)" or "public data portal (https://www.data.go.kr/)", and the original provider is the Ministry of Land, Infrastructure and Transport.

However, the actual transaction price information provided by the Ministry of Land, Infrastructure and Transport is disclosed with the actual address deleted due to personal information issues, so useful information cannot be used. In other words, only single/multi-family, land, and commercial/business addresses cannot be identified, and lot numbers are disclosed for apartments/units/officetels.

As described above, although the Ministry of Land, Infrastructure and Transport provides actual transaction data, there is a problem in that an accurate address such as a transaction date or lot number is not provided to protect personal information.

An example of a technique for solving this problem is disclosed in Documents 1 to 3 and the like.

For example, in Patent Document 1 below, the real transaction price providing server of the Ministry of Land, Infrastructure and Transport that provides first information on the administrative district, transaction amount, contract date, and area of the real estate for which the real transaction was made, the administrative district for the real estate, the lot number and the area A real estate database having a second information on the real estate, by matching the first information with the second information, collects real estate registration information from a real estate information providing server and a real estate registration server that provide a real estate transaction amount for the lot number, and the real estate A real estate information providing system comprising a real estate registration information collection server for storing in a database, wherein the real estate information providing server registers the real estate within a predetermined period based on a contract date among the first information when the first information and the second information match Disclosed is a system for providing real estate information, characterized in that it determines whether the registration reception date of Gap-gu belongs among the information.

In addition, in the following Patent Document 2, the step of confirming the area of the real estate to be analyzed in the actual land transaction price information, the land item, the city-gun-gu, and the use area, the area, the land item, the city-gun-gu, and the use area on the individual land characteristic information are all the same as those of the real estate to be analyzed Searching for matching real estate, detecting the address of all matching real estate as the address of the real estate to be analyzed, confirming the area, title, city, county, and use area of the real estate to be analyzed from the actual land transaction price information, individual land characteristics It is disclosed for a real estate information purification method comprising the steps of searching for real estate in which the area, title, city, county, and use area on the information match all those of the real estate to be analyzed, and generating a candidate list with all matching real estate. have.

On the other hand, in the following Patent Document 3, the official price of the real estate to be evaluated, the actual transaction information acquisition unit for acquiring the actual transaction price and the official land price of the real transaction real estate located within a predetermined area based on the real estate to be evaluated, the actual transaction price and the official land price of the acquired real estate a reference value generator for generating a reference value for each real transaction real estate based on the reference value and a market price estimation unit for estimating the market price of the real estate to be assessed by applying the generated reference value to the official land price of the real estate to be assessed, and generating the reference value Part is disclosed for a real estate market price estimation apparatus using the actual transaction price and the official land price to generate the reference value based on at least one of a difference and a ratio between the actual transaction price and the official land price of the real transaction real estate.

Republic of Korea Patent Publication No. 10-1847774 (registered on April 4, 2018) Republic of Korea Patent Publication No. 10-1904190 (registered on September 27, 2018) Republic of Korea Patent Publication No. 10-1773911 (registered on August 28, 2017)

In the technology disclosed in Patent Document 1 as described above, the real estate information collection server stores the second information collected by various real estate studies in the real estate database, and the real estate information providing server matches the first information and the second information to the lot number. Although it provides real estate transaction amount for Korea, there was a problem that it was impossible to match past transactions because the real estate study did not include a closed platoon ledger.

In addition, the technology disclosed in Patent Document 2 has a problem in that accurate real estate information cannot be collected because it is limited only to actual land transaction information. In addition, in Patent Document 2, the address of the target real estate is extracted by matching the land characteristic information in which the address, part of the lot number, road name, site area, total area, etc. are described with the information on the building ledger, but in the case of a new building, the There was also a problem that the extraction of the target real estate could not be executed accurately because the information was not registered in the building register.

On the other hand, in Patent Document 3, a reference value is generated using the official land price in the ratio to the branch, but there is a problem that the reference value is meaningless when the transaction time is different from each other, In the case of estimating the market price as of the present year, if the real estate (B1) was transaction information in 2010 and the real estate transaction (B2) was transaction information in 2018, the timing of the real estate to be evaluated (A) is not considered. There was a problem that the reference value used had no meaning. In addition, in Patent Document 3, the ratio of the reference value is extracted with reference to the official land price and the actual transaction value, but the official land price represents the land price and the actual transaction price is the sum of the land and the building, so there is a problem that the extraction of such a ratio is incorrect.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a real estate market price estimation system and method capable of accurately estimating the market price of a target real estate by evaluating the degree of similarity.

Another object of the present invention is to provide a real estate market price estimation system and method capable of providing objective information on real estate sales prices to sellers and buyers of target real estate.

Another object of the present invention is to provide a system and method for estimating real estate prices that can improve the reliability of providing collateral for a target real estate.

In order to achieve the above object, the real estate market price estimation system according to the present invention is an information providing server 100 that regularly provides information publicly disclosed by the state, land ledger, land characteristic information, building ledger and closure cancellation provided by the information providing server. Management server 200 that extracts reference real estate based on the information in the ledger and estimates the appropriate market price of the target real estate, single/multi-family, land, commercial/business building, apartment, officetel, real estate related to sale rights supplied from the information providing server As information, a database 300 for storing land ledger, land characteristic information, building ledger and closed cancellation ledger information, and a user terminal 400 for receiving appropriate market price information of the target real estate estimated from the management server, The management server 200 is an address extraction module 230 for extracting an address for each real estate based on the information of the land ledger, land characteristic information, building ledger and closed closure ledger stored in the database, the target from each real estate A similar sale real estate selection module 240 that selects the reference real estate by extracting information on the actual transaction similar sale real estate corresponding to the real estate, and extracts the similarity with the target real estate for the reference real estate selected in the similar sale real estate selection module and a similarity extraction module 250, a weight calculation module 270 for calculating a weight for the similarity of the reference real estate extracted by the similarity extraction module 250, and the similarity extraction module 250 is the target real estate. The straight line distance from to the reference real estate (m), the difference between the land area (m2) and the total floor area (m2) between the target real estate and the reference real estate, the individual official land price (m2) between the target real estate and the reference real estate According to the difference value, the difference value of the construction year between the target real estate and the reference real estate, the similarity is extracted by analyzing and estimating the degree of comparison by the learning method by artificial intelligence, and the weight is calculated by the following formula (1)

{Sum of similarity of reference real estate/sum of similarity of multiple reference real estate} … Formula (1)

is carried out according to the following formula (2)

{weight of reference real estate × comparative price of reference real estate} … Equation (2)

It is characterized in that it is executed according to

In addition, in the real estate market price estimation system according to the present invention, the management server 200 includes a comparative market price calculation module 260 for calculating a comparative market price for the target real estate with the transaction price extracted from the similar sale real estate selection module, the weight It characterized in that it further comprises an appropriate price determination module 280 for determining the appropriate market price of the target real estate with the weight calculated by the calculation module and the comparative price calculated by the average of the comparison price calculation module.

In addition, in the real estate price estimation system according to the present invention, the similar sale real estate selection module 240 is within a radius of 3 km around the target real estate and within 5 years, single/multi-family, land, commercial/business buildings, apartments, It is characterized in that the similar sale real estate sold in the same type is selected according to the actual transaction information of each reference real estate for which the officetel and sale right are sold.

In addition, in the real estate market price estimation system according to the present invention, the comparative market price calculation module 260 divides the building price and the land price among the transaction prices based on the transaction price of the reference real estate, and among them, the building price is the building ledger information or the closing cancellation. It is characterized in that the building price is calculated using the information, and the land price is calculated in two stages: the characteristics of the land and the time of the transaction.

In addition, in order to achieve the above object, the real estate market price estimation method according to the present invention (a) regularly collects and processes related data based on the information disclosed by the state in the address extraction module 230 of the management server 200 to obtain real estate Step of extracting the address for each real estate in real transaction, (b) extracting information on real transaction similar real estate corresponding to the target real estate from each real estate in the similar sale real estate selection module 240 of the management server 200, selecting a reference real estate, (c) a straight line distance (m) from the target real estate to the reference real estate in the similarity extraction module 250 for the reference real estate selected in step (b), the target real estate and the reference real estate According to the difference value of land area (m2) and gross floor area (m2) with Extracting the degree of similarity through analysis and estimation of the degree of comparison by an artificial intelligence learning method, (d) of the target real estate in the comparative market price calculation module 260 at the time of the transaction price of the reference real estate selected in the step (b) Calculating a comparative price, (e) calculating a weight in the weight calculation module 270 for the degree of similarity of the reference real estate extracted in steps (c) and (d), (f) in the step (d) determining the appropriate market price of the target real estate in the appropriate market price determination module 280 by calculating a weighted average with the calculated comparative price and the weights extracted in (e), (g) the target real estate determined in the step (f) Transmitting the appropriate price information of the management server 200 to the user terminal 400,

The weight is calculated by the following formula (1)

{Sum of similarity of reference real estate/sum of similarity of multiple reference real estate} … Formula (1)

is carried out according to the following formula (2)

{weight of reference real estate × comparative price of reference real estate} … Equation (2)

It is characterized in that it is executed according to

In addition, in the method of estimating the real estate market price according to the present invention, the step (a) is (a1) land characteristic information service and address related to the address and land area according to the continuous change of land and building information provided by the information providing server 100 and collecting land and building information at regular intervals through the building information service on the total floor area of the building, (a2) a part of the address provided by the information providing server 100 (provided by the city/gun/gu/dong name), the transaction land area , providing the total floor area, collecting monthly real estate transaction information through the real estate transaction information service regarding the year and month of the transaction, (a3) refining the list of land that matches the new transaction information address and land area in the address extraction module 230, If there is more than one land list, the address is checked by whether the total building area is the same, the actual transaction information is refined, and the actual transaction information is automatically generated by address, (a4) new transaction information address and land in the address extraction module 230 Refine the land list with the same area, and if there is more than one land list, check the address by whether the total building area is the same, and if there is no details, whether it is the same as the closed platoon ledger provided by the information providing server 100 It is characterized in that it comprises the steps of verifying the address with the address, refining the actual transaction information, automatically generating the actual transaction information for each address, and (a5) collecting the real estate monthly sale price index provided from the information providing server 100 .

In addition, in the real estate market price estimation method according to the present invention, the step (b) is within a radius of 3 km from the target real estate in the similar sale real estate selection module 240 and within 5 years, single/multi-family, land, commercial / Select a similar real estate for sale of the same type according to the actual transaction information of each reference real estate for which commercial buildings, apartments, officetels, and sale rights were purchased, classify land and building prices among the transaction prices, and compare land and target land for similar transactions of reference real estate It is characterized in that the price is calculated by reflecting the characteristics of , and the price is calculated and selected by reflecting the characteristics of the past transaction time and the present time point of the reference real estate.

As described above, according to the real estate market price estimation system and method according to the present invention, the management server extracts the address for each real estate according to the information of the land ledger, land characteristic information, building ledger, and closed cancellation ledger, and the target real estate By extracting the degree of similarity to the actual transaction price of the reference real estate adjacent to , and transmitting the appropriate market price information to the user terminal by calculating the appropriate market price of the target real estate, objective information on the sale price of the target real estate can be provided. The effect that can be obtained is obtained.

In addition, according to the real estate market price estimation system and method according to the present invention, it is possible to accurately estimate the market price of a target real estate by providing a weighted average calculation module that calculates a weighted average for the similarity of the reference real estate extracted from the similarity extraction module. effect is obtained.

1 is a block diagram of a real estate market price estimation system according to the present invention;
Figure 2 is a configuration diagram of the management server shown in Figure 1;
3 is a block diagram of the database shown in FIG. 1;
4 is a process diagram for explaining the process of estimating the real estate market price by the real estate market price estimation system according to the present invention;
5 is a map showing the target real estate and similar sales locations;
6 to 15 are views each showing a degree of similarity between a target real estate and a reference real estate.

The above and other objects and novel features of the present invention will become more apparent from the description of the present specification and accompanying drawings.

As used herein, the term "announced market price" refers to the unit area of standard land announced by the Minister of Land, Infrastructure and Transport every year after reviewing and adjusting the price of standard land selected as representative land nationwide by the Minister of Land, Infrastructure and Transport (m ² ) The per price, and “actual real estate transaction price” is a real estate created based on Article 7 of the “Act on Information Disclosure of Public Institutions” by the Ministry of Land, Infrastructure and Transport to objectively grasp the general real estate transaction status and average actual transaction price through data disclosure. It is the actual transaction price of real estate disclosed by the actual transaction price disclosure system, and the "land ledger" is a type of cadastral study and is a book created to clarify the actual situation of the land. It is distinguished from the land registry, and the "building ledger" is a management system that registers and manages matters related to the indication of buildings, such as the location, area, structure, use, and number of floors of the building, and the status of the owner, such as the name, address, and ownership interest of the owner of the building. It means the ledger, which can be identified through http://apis.data.go.kr, and “closed platoon ledger” is a case in which all or part of a building is lost due to demolition or destruction, etc. It means a building ledger that has been marked with " and is no longer in use, and can be identified through http://apis.data.go.kr.

In addition, the term "target real estate" used in the present invention means a real estate for estimating an appropriate market price according to a customer's request, "customer" means a seller, a buyer, or a collateral evaluator, and "reference real estate" is a It refers to real estate applied to extract similarity to determine an appropriate market price.

On the other hand, although the actual transaction price information provided by the Ministry of Land, Infrastructure and Transport can be used to generate real estate transaction information by address, as shown in Table 1 below, the actual address is disclosed as a personal information issue, and useful information cannot be used. Only single/multi-family, land, and commercial/business use addresses cannot be identified.

Accordingly, the actual address must be inferred based on the publicly available information.

In the process of inferring the actual address, several methods are used to increase the accuracy. In the case of using the land area, the address of the same land area is extracted by using the land ledger and land characteristic information provided by the Ministry of Land, Infrastructure and Transport. The first method or the second method of extracting a street address with the same total floor area in the same city, county, or gu may be applied by using the building register provided by the Ministry of Land, Infrastructure and Transport.

In general, in the case of the first method, extraction is impossible when the site area is the same in the same city, county, and district, and in the case of the second method, the extraction accuracy is higher because there are few cases where the total floor area of the building is the same.

However, the building register only targets buildings maintained at the present time, and cannot be extracted in the case of buildings that have been closed or canceled in the past. For example, if a building was purchased in 2006 and a building was built in 2015, it is impossible to search for the total floor area of 2006 transaction information as of 2019.

Therefore, in the present invention, single/multi-households, land, commercial/business buildings, apartments, officetels, and sale rights among the actual transaction information of the Ministry of Land, Infrastructure and Transport are targeted. In addition, the precision is improved by adding the closed and deleted ledger in addition to the existing land (land ledger, land characteristic information) and buildings (building ledger) among the real estate information provided by the state.

Hereinafter, an embodiment according to the present invention will be described with reference to the drawings.

1 is a configuration diagram of a real estate market price estimation system according to the present invention, FIG. 2 is a configuration diagram of the management server shown in FIG. 1, and FIG. 3 is a configuration diagram of the database shown in FIG.

As shown in FIG. 1, the real estate market price estimation system according to the present invention includes an information providing server 100 that regularly provides information disclosed by the state, a land ledger provided by the information providing server 100, land characteristic information, Management server 200 for estimating the appropriate market price of the target real estate by extracting reference real estate based on the information of the building ledger and closing closure ledger, single/multi-family, land, commercial/business buildings supplied from the information providing server 100, As real estate information about apartments, officetels, and sales rights, the database 300 for storing land ledger, land characteristic information, building ledger, and closing and cancellation ledger information, and the appropriate market price information of the target real estate estimated from the management server 200 and a user terminal 400 for receiving, wherein the management server 200 extracts addresses for each real estate according to the information of the land ledger, land characteristic information, building ledger, and closed cancellation ledger, and is adjacent to the target real estate. By extracting a degree of similarity to the actual transaction price of the reference real estate, an appropriate market price of the target real estate is calculated, and appropriate market price information is transmitted to the user terminal 400 .

The information providing server 100 is, for example, a server managed by the Ministry of Land, Infrastructure and Transport, "real transaction disclosure system (http://rt.molit.go.kr/)" or "public data portal (https://www .data.go.kr/) provides real estate-related information, and public data includes actual land transaction price information, real estate transaction price information, individual land characteristics information, building ledger information, land ownership history information, land movement history information, and construction Includes permission information and building closure and cancellation information.

The land real transaction price information includes, for example, information such as city, gun-gu (legal dong), land title, use area contract year, transaction amount, etc. Provide the transaction amount reported to the government and the contract date. In general real estate sales information service, the real estate owner provides the desired price, that is, the asking price information, whereas this actual transaction price information is based on the amount reported as the actual transaction amount and is displayed only up to the "city, county, and district" of the real estate traded. The address of the property is unknown.

Individual land characteristic information can be used to estimate accurate address information by using it as it provides information on city, county, mountain division, main number, and sub-number. Each government evaluates and announces the real estate price across the country, and this official land price is the information used as a basis for real estate-related tax imposition. Therefore, the address can be estimated by using the actual transaction price information, which provides only transaction information of real estate with transactions, and individual land characteristic information provided for all real estate even if there is no transaction.

Building ledger information includes information related to the structure of a building, such as the main structure, site area, building area, gross floor area, exclusive area, floor area ratio, and date of approval for use, and the head of a Mayor, Gun, or Gu may check the ownership and use status of the building or construct Information on the current status of buildings and sites to be used as basic data for policy.

Land ownership history information is updated when there is a change in the ownership-related history of land, and includes information such as address, ownership classification, cause of change, and ownership change date. and building permit information is information related to building permits, such as area, building permit date, and use approval date.

Information on building closure and cancellation is applied when all or part of a building is lost due to demolition or destruction, etc.

As described above, actual land transaction price information, real estate transaction price information, individual land characteristic information, building ledger information, land ownership history information, land movement history information, building permit information, and building closure provided by the information providing server 100 as described above Each of the erasure information is processed by the management server 200 and stored in the database 300 .

The management server 200 is a normal server that is connected to the network to provide the appropriate market price information of the target real estate desired by the customer to the user terminal 400, and as shown in FIG. 2, the transmission/reception module 210, member management Module 220, address extraction module 230, similar sale real estate selection module 240, similarity extraction module 250, comparative price calculation module 260, weight calculation module 270, appropriate price determination module 280 includes The management server 200 is preferably constructed to serve as a kind of web server, web service server, mobile web server or application server. In addition, a web page is provided for providing the user terminal 400 with information on the appropriate market price of the target real estate.

The transmission/reception module 210 is made of a normal transmission/reception module, and is provided to transmit or receive information via wire or wireless with the user terminal 400 and the database 300 , and provides the user terminal 400 with appropriate market price information of the target real estate. It is provided so as to perform transmission and reception of information about the same, and is not limited to a specific communication module.

The member management module 220 is provided to manage the name, address, phone number, paid member, free member, membership subscription period, etc. of the user using the user terminal 400 stored in the database 300 .

The address extraction module 230 extracts addresses for real estate in each actual transaction information database based on the information of the land ledger, land characteristic information, building ledger, and closed cancellation ledger stored in the database 300, and each extracted The actual transaction information is updated and stored in the database 300 . According to the present invention, since the building information of the past time on the new building missing from the land ledger, land characteristic information or building book is utilized, it is possible to find the correct address for each real estate and provide it to the user.

The similar sale real estate selection module 240 selects a reference real estate by extracting information on the real transaction similar sale real estate corresponding to the target real estate from the information about each real estate stored in the database 300 . That is, the similar sale real estate selection module 240 is within a radius of 3 km from the target real estate, and within 5 years, individual/multi-family, land, commercial/business buildings, apartments, officetels, and sales rights are sold for each reference real estate. According to the actual transaction information of

The similarity extraction module 250 is a straight-line distance from the target real estate for the reference real estate selected in the similar sale real estate selection module 240 described above, land area, gross floor area, individual official land price (m2), individual house price, month of use , the similarity is extracted according to the area of use.

The comparative price calculation module 260 first determines a building price and a land price among the transaction prices at the time based on the transaction price of the reference real estate extracted by the similarity extraction module 250 . Among them, the building price is the building price calculated by applying land characteristics, building ledger information, and closing and cancellation information based on the standard price of new buildings disclosed by relevant institutions {building price standard × structure index × use index × location index × Residual price ratio by elapsed years × adjustment ratio according to the characteristics of individual buildings}, and the land price is determined by excluding the calculated building price from the transaction price. Then, in order to calculate the comparative market price based on the transaction price at the time of the reference real estate, the land characteristics and the second-stage market price at the time of the transaction are calculated. First, in order to reflect the difference in land characteristics in the first stage, the ratio of the land price among the transaction prices at the time is applied based on the official land price at the present time, and in the second stage, to reflect the difference between the past transaction and the current transaction, the real estate sales index apply the ratio of The price of the land calculated in this way and the building price calculated using the building ledger information or closing and cancellation information of the target real estate {building new construction price standard × structure index × use index × location index × residual price ratio by elapsed years × adjustment rate according to the characteristics of individual buildings } to calculate the current price of the target real estate based on the past transaction price of the reference real estate.

The weight calculation module 270 calculates a weight according to Equation (1) below by using the similarity of the reference real estate extracted by the similarity extraction module 250 .

{Sum of similarity of reference real estate/sum of similarity of multiple reference real estate} … Formula (1)

The appropriate price determination module 280 calculates as a weighted average using the weight calculated by the weight calculation module 270 and the comparative price of the reference real estate extracted from the comparative price calculation module 260 . That is, the appropriate market price calculation module 280 determines the appropriate market price by the summation of weights for each reference real estate (2).

{weight of reference real estate × comparative price of reference real estate} … Equation (2)

As shown in FIG. 3 , the database 300 includes a user member information database 310 , a land information database 320 , a building information database 330 , a closed building information database 340 , and an actual transaction information database 350 . , a price information database 360, and the like.

The user member information database 310 contains the user's member information including the name, gender, phone number of the user terminal 400 and location information of the user terminal 400 of the user who is a customer of the system according to the present invention. is saved

The land information database 320 stores information on the location, number, type, structure, floor space, address, and name of the building provided by the information providing server 100 , and the land information database 320 includes Information on the land title, area, use area, district, other public restricted areas, land shape and orientation, topography, land use status, road conditions, etc. provided by the information providing server 100 is stored, and the building information database ( In 330), at least one information of whether the building provided by the information providing server 100 is underground, floor, area, structure, gross floor area, floor area ratio, year of construction, number of households, number of parking spaces per household, and number of elevators is stored, and the closed building information The database 340 stores attribute information such as a general title part, a title part, an outline for each floor, annexed lot number, an exclusive common area, a sewage treatment facility, an exclusive title part, a house price, a local district area provided by the information providing server 100 .

The real transaction information database 350 stores real transaction information of real estate obtained from the real transaction price disclosure system of the Ministry of Land, Infrastructure and Transport or a public data portal. In general, since the specific address of the actual transaction real estate is expressed in the form of "1*", for example, the actual transaction information is stored by estimating the address using the land ledger and building ledger, etc., and completely updating the actual transaction information. That is, firstly, the real transaction information of real estate for which the address of the address obtained from the real transaction processing material system of the Ministry of Land, Infrastructure and Transport or the public data portal is unconfirmed is stored in the actual transaction information database 350 as actual transaction information, and secondarily, the address extraction module 230 is used. By checking the unconfirmed lot number, the actual transaction information of real estate consisting of "si, gun-gu / street address / housing type / road condition / total floor area / site area / contract year / contract date / transaction amount / construction year / road name", etc. 350) is updated. Thereafter, the similar sale real estate selection module 240 may use this actual transaction information to inquire a comparison target.

The market price information database 360 stores appropriate price information determined as a weighted average {weight of reference real estate × comparative price of reference real estate} of the target real estate according to the weight calculated by the weight calculation module 270 .

Such a configuration of the database 300 is only a preferred embodiment, and in developing a specific device, it may be configured in a different structure according to the database construction theory in consideration of the ease and efficiency of access and search.

The network is for establishing wireless communication between the management server 200 and the user terminal 400, and includes a wireless LAN (WLAN), a digital living network alliance (DLNA), a wireless broadband (Wibro), and a WiMAX. (World Interoperability for Microwave Access: Wimax), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), broadband wireless mobile communication Service (Wireless Mobile Broadband Service: WMBS), 5G mobile communication (IMT-2020), etc. can be applied. However, the present invention is not limited thereto, and various applications may be made according to the development of wireless communication technology.

The user terminal 400 basically performs data communication with the management server 200 through a camera function capable of generating user image information, an audio output function capable of outputting personal health status information by voice, and the network, respectively. As a device having a communication function that can (Telematics) terminal, navigation terminal, personal computer, notebook computer, slate PC, tablet PC, ultrabook, wearable device, for example , watch-type terminal (Smartwatch), glass-type terminal (Smart Glass), HMD (Head Mounted Display), etc.), Wibro terminal, IPTV (Internet Protocol Television) terminal, smart TV, digital broadcasting terminal, AVN (Audio) It can be applied to various terminals, such as a video navigation) terminal, an A/V (Audio/Video) system, and a flexible terminal.

Next, a method for estimating the real estate market price according to the present invention will be described with reference to FIGS. 4 to 15 .

4 is a flowchart for explaining a process of estimating the real estate market price by the real estate market price estimation system according to the present invention.

First, as shown in FIG. 4 , the real estate market price estimation system according to the present invention periodically collects and processes related data based on information disclosed by the state to extract the addresses of each real estate transaction. That is, the address extraction module 230 extracts address information for each real estate based on the information of the land information database 320 , the building information database 330 , and the closed building information database 340 , and the extracted address information is updated and stored in the actual transaction information database 350 (S10).

The above-mentioned extraction of addresses for each real estate collects land and building information at regular intervals through the land characteristic information service on the address and land area and the building information service on the address and the total floor area of the building according to the continuous change of land and building information. In addition, real estate transaction information is collected monthly through real estate transaction information service on part of the address (provided by city/gun/gu/dong name), transaction land area, total floor area, and date of transaction, and the new transaction information address matches the land area By refining the list of land to be used, and if there is more than one land list, by verifying the address by whether the total building area is the same, refining the actual transaction information, automatically updating the actual transaction information by address, and collecting the real estate monthly sale price index can be executed

On the other hand, when the customer requests the price information of the real estate desired by the customer through the user terminal 400 , the member management module 220 determines whether the member is a member through the user member information DB 310 , and then the real estate market price estimation system according to the present invention An application for realizing , etc. may be executed in the user terminal 400 .

Accordingly, the management server 200 receives the lot number address of the target real estate from the user terminal 400 through the transmission/reception module 210 . For example, the address of the target real estate that the customer wants to sell or buy is "385-21 Bukgajwa-dong, Seodaemun-gu, Seoul (road name address; 16, Susaek-ro 8-gil, Seodaemun-gu, Seoul)".

In this regard, general information, land information, and building information of the target real estate as shown in Table 2 below are extracted from the database 300 and transmitted to the user terminal 400 ( S20 ).

In addition, land information as shown in Table 3 below may be extracted and transmitted to the user terminal 400 .

In addition, as shown in Table 4 below, building information and price information on individual public notices may be extracted and transmitted to the user terminal 400 .

Next, the similar sale real estate selection module 240 selects a reference real estate by extracting information on the real transaction similar real estate corresponding to the target real estate from each real estate (S30). The similar sale real estate (A to J in FIG. 5 ) selected in step S30 may represent, for example, ten real estate locations as shown in FIG. 5 . 5 is a map showing a target real estate and similar sales locations.

The step S30 is the same type according to the actual transaction information of each reference real estate in which a single/multi-family, land, commercial/business building, apartment, officetel, and sale right were sold within a radius of 3 km centered on the target real estate and within 5 years Select a similar property for sale of to calculate and select a price.

Table 5 below shows similar sales with target real estate showing actual transaction information (A to J in FIG. 5 ) of 10 real estate sold within 3 km of the center of analysis and within 5 years from the actual transaction price in the database 300 . is a list

As shown in FIGS. 6 to 15 for the similar sale list selected in step S30, the similarity extraction module 250 extracts the similarity with the target real estate (single house) (S40).

6 shows the similarity of real estate A shown in FIG. 5, FIG. 7 shows the similarity of real estate B shown in FIG. 5, FIG. 8 shows the similarity of real estate C shown in FIG. 5, and FIG. 9 shows FIG. Shows the similarity of real estate D shown in Fig. 10 shows the similarity of real estate E shown in Fig. 5, Fig. 11 shows the similarity of real estate F shown in Fig. 5, and Fig. 12 shows real estate G shown in Fig. 5 13 shows the similarity of the H real estate shown in FIG. 5, FIG. 14 shows the similarity of the I real estate shown in FIG. 5, and FIG. 15 shows the similarity of the J real estate shown in FIG.

In addition, the proportion of similarity is set according to the straight-line distance from the target real estate, land area, gross floor area, individual official land price (㎡), individual housing price, month of use, and area of use. That is, the similarity extraction module 250 is, as shown in FIGS. 6 to 15, the straight line distance (m) from the target real estate to the reference real estate, the land area between the target real estate and the reference real estate (m2), and The similarity can be extracted according to the difference value of the total floor area (m2), the difference value between the individual official land price (m2) between the target real estate and the reference real estate, and the difference value between the construction year between the target real estate and the reference real estate.

In other words, as the current status of the target real estate, the land area of 121.9 m2, the total building area of 87.97 m2, the officially announced individual land price (m2) 3,0970,000 won, the information of July 18, 1975 and the reference real estate closest to the target real estate shown in FIG. As shown in FIG. 6 for A, the straight-line distance from the target real estate to the reference real estate is 26.7 m, the land area is 198.6 m², the total floor area is 447.69 m², and the individual official land price (m2) is 2,920,000 won, according to the information of the construction year 1992.12.21 The similarity can be extracted. Such similarity can be analyzed and estimated to the degree of comparison by the learning method by artificial intelligence, and can be represented by a pentagonal graph as shown in FIG. 6 .

Table 6 below is a list of similar sale indexes, but is not limited thereto, but is not limited thereto, and indexes of lot number, sale price, sale time, and similarity are created for the single-family house.

Next, a comparative market price is calculated based on each of the 10 past transaction details (S50), and the comparative market price of the target real estate is calculated as shown in Table 7 with the then-current transaction price of the reference real estate extracted in S50.

Thereafter, a weight is calculated for the degree of similarity of the extracted reference real estate (S60).

In step S60, for each reference real estate (A to J in FIG. 5 ), the weight of the reference real estate is calculated by {similarity of reference real estate/sum of similarity of multiple reference real estate}.

Next, according to the weight extracted in step S60, an appropriate market price may be determined as a weighted average {weight of reference real estate × comparative price of reference real estate} of the target real estate (S70).

As shown in Table 8 below, through the transmission/reception module 210, the appropriate market price information of the target real estate determined in step S70 is transmitted to the user terminal (S80).

The invention made by the present inventors has been described in detail according to the above embodiments, but the present invention is not limited to the above embodiments and various modifications can be made without departing from the gist of the present invention.

By using the real estate market price estimation system and method according to the present invention, it is possible to accurately estimate the market price of a target real estate.

100: information providing server
200: management server
300 : database
400: user terminal

Claims (7)

Information providing server 100 that regularly provides information disclosed by the state;
A management server 200 for estimating the appropriate market price of a target real estate by extracting a reference real estate based on the information of the land ledger, land characteristic information, building ledger, and closed cancellation ledger provided from the information providing server;
Database 300 for storing information on land ledger, land characteristic information, building ledger and closed closure ledger as real estate information on single/multi-family homes, land, commercial/business buildings, apartments, officetels, and sales rights supplied from the information providing server (300) ,
and a user terminal 400 for receiving appropriate market price information of the target real estate estimated from the management server,
The management server 200 is an address extraction module 230 for extracting an address for each real estate based on the information of the land ledger, land characteristic information, building ledger and closed closure ledger stored in the database, the target from each real estate A similar sale real estate selection module 240 that selects the reference real estate by extracting information on the actual transaction similar sale real estate corresponding to the real estate, and extracts the similarity with the target real estate for the reference real estate selected in the similar sale real estate selection module a similarity extraction module 250, and a weight calculation module 270 for calculating a weight for the similarity of the reference real estate extracted by the similarity extraction module 250,
The similarity extraction module 250 calculates the linear distance (m) from the target real estate to the reference real estate, the difference between the land area (m2) and the total floor area (m2) between the target real estate and the reference real estate, and the target real estate Extract the similarity by analyzing and estimating the degree of comparison by the learning method by artificial intelligence according to the difference value of the individual official land price (㎡) with the reference real estate and the difference value of the construction year between the target real estate and the reference real estate,
The weight is calculated by the following formula (1)
{Sum of similarity of reference real estate/sum of similarity of multiple reference real estate} … Formula (1)
is carried out according to the following formula (2)
{weight of reference real estate × comparative price of reference real estate} … Equation (2)
Real estate price estimation system, characterized in that it is executed according to. In claim 1,
The management server 200 is
A comparative market price calculation module 260 for calculating a comparative market price for the target real estate with the transaction price extracted from the similar sale real estate selection module;
Real estate market price, characterized in that it further comprises an appropriate market price determination module 280 for determining the appropriate market price of the target real estate with the weight calculated by the weight calculation module and the comparative price calculated by the average of the comparison price calculation module estimation system. In claim 2,
The similar sale real estate selection module 240 is within a radius of 3 km from the target real estate and within 5 years of single/multi-family, land, commercial/business buildings, apartments, officetels, and sales rights of each reference real estate sold and sold. A system for estimating real estate prices, characterized in that the similar real estate sold in the same type is selected according to the actual transaction information. In claim 2,
The comparative market price calculation module 260 divides the building price and the land price among the transaction prices based on the transaction price of the reference real estate, and among them, the building price calculates the building price using the building book information or closing and cancellation information, and the land price is Real estate market price estimation system, characterized in that it is calculated in two stages at the time of the transaction and the characteristics of the land. (a) periodically collecting and processing related data based on the information disclosed by the state in the address extraction module 230 of the management server 200 to extract the address for each real estate transaction;
(b) selecting the reference real estate by extracting information on the real transaction similar real estate corresponding to the target real estate from each real estate in the similar sale real estate selection module 240 of the management server 200;
(c) the straight line distance (m) from the target real estate to the reference real estate in the similarity extraction module 250 for the reference real estate selected in step (b), and the land area between the target real estate and the reference real estate (m2) And according to the difference value of the total floor area (㎡), the difference value of the individual official land price (㎡) between the target real estate and the reference real estate, and the difference value between the construction year between the target real estate and the reference real estate, the learning method by artificial intelligence extracting the degree of similarity by analyzing and estimating the degree of comparison by
(d) calculating the comparative market price of the target real estate in the comparative market price calculation module 260 with the then-current transaction price of the reference real estate selected in step (b);
(e) calculating a weight in the weight calculation module 270 for the degree of similarity of the reference real estate extracted in steps (c) and (d);
(f) determining the appropriate market price of the target real estate in the appropriate market price determination module 280 by calculating a weighted average using the comparative price calculated in step (d) and the weight extracted in (e);
(g) transmitting the appropriate market price information of the target real estate determined in step (f) from the management server 200 to the user terminal 400,
The weight is calculated by the following formula (1)
{Sum of similarity of reference real estate/sum of similarity of multiple reference real estate} … Formula (1)
is carried out according to the following formula (2)
{weight of reference real estate × comparative price of reference real estate} … Equation (2)
A method of estimating the real estate market price, characterized in that it is carried out according to In claim 5,
The step (a) is
(a1) Land and building information at regular intervals through the land characteristic information service on the address and land area and the building information service on the address and the total floor area of the building according to the continuous change of land and building information provided by the information providing server 100 collecting steps,
(a2) Monthly real estate transaction information is collected through the real estate transaction information service regarding part of the address provided by the information providing server 100 (provided by city/gun/gu/dong name), transaction land area, total floor area, and date of transaction step to do,
(a3) In the address extraction module 230, the new transaction information address and the land area match the land list, and if there is more than one land list, the address is checked by whether the total building area is the same, and the actual transaction information is refined, automatically generating real transaction information by address;
(a4) In the address extraction module 230, the new transaction information address and the land list matching the land area are refined, and if there is more than one land list, the address is checked by whether or not the total building area is the same, The step of refining the actual transaction information by verifying the address by whether it is the same as the closed platoon ledger provided by the information providing server 100, and automatically generating the actual transaction information for each address;
(a5) Real estate market price estimation method comprising the step of collecting the real estate monthly sale price index provided by the information providing server (100). In claim 5,
In the step (b), single/multi-family, land, commercial/business buildings, apartments, officetels, and sale rights are sold and sold within a radius of 3 km centered on the target real estate in the similar sale real estate selection module 240 and within 5 years. Select the same type of similar real estate for sale according to the actual transaction information of each reference real estate, classify the land and building prices among the transaction prices, calculate the price by reflecting the characteristics of the similar transaction land and the target land of the reference real estate, and refer A method of estimating the real estate market price, characterized in that the price is calculated and selected by reflecting the characteristics of the past transaction time and the present time of the real estate.

Images