KR102245888B1 - System and method of building big data for estimating house price using space information - Google Patents

Abstract

Disclosed is a system and method for constructing big data for estimating a house price using spatial information. A real estate data collection/purification module that collects data affecting the formation of housing prices from at least one database, and refines data errors between the collected data through spatial attribute values; A big data construction module for constructing big data by linking data for which data errors are refined in the real estate data collection/purification module according to a real estate level; Construct a house price formation information extraction module that extracts information on housing price formation that affects the formation of house prices from the big data built in the big data construction module. According to the big data construction system and method for estimating housing price using the above-described spatial information, it is configured to collect various physical, social, regional price formation factors, etc. from various databases and refine the errors to build big data, Using big data, there is an effect of increasing the accuracy of housing price estimation by considering various factors such as area, building itself, education, and transportation in a complex manner.

Description

Big data construction system and method for estimating house price using spatial information {SYSTEM AND METHOD OF BUILDING BIG DATA FOR ESTIMATING HOUSE PRICE USING SPACE INFORMATION}

The present invention relates to a house-related big data construction system and method, and more specifically, to a big data construction system and method for estimating a house price using spatial information.

Various algorithms for estimating house prices have been disclosed.

Housing prices are estimated from various perspectives, and most of them consider factors such as the location of the housing and the individual characteristics of the housing against the background of an economic theory that is determined by supply and demand. This factor is called a price-forming factor, and collecting these price-forming factors and estimating the price of one house appropriately is a very complex and difficult task.

However, in estimating housing prices, it is not possible to simply consider one price-forming factor. Physical, regional, social, and educational factors are compounding housing prices.

However, there is no database for estimating housing prices by considering these price-forming factors from various viewpoints. In addition, there is a possibility that data of various databases may have errors, and there is no means to refine and utilize these errors.

In addition, these price-forming factors are scattered in various databases, and the task of collecting accurate price-forming factors is also very important.

It is necessary to collect and utilize various information such as the land register, the building register, and the site right register, as well as location coordinates and traffic information.

10-1773911 10-1764834

An object of the present invention is to provide a big data construction system for estimating a house price using spatial information.

Another object of the present invention is to provide a big data construction method for estimating a house price using spatial information.

The big data construction system for estimating house price using spatial information according to the object of the present invention as described above collects data affecting the formation of house price from at least one database, and uses the collected data as a spatial attribute value. A real estate data collection/purification module for refining data errors between each other through a medium; A big data construction module for constructing big data by linking data for which data errors are refined in the real estate data collection/purification module according to a real estate level; It may be configured to include a house price formation information extraction module for extracting the house price formation information that affects the house price formation from the big data built in the big data construction module.

Here, the spatial attribute value is information capable of specifying the location or limiting the range of the real estate, and at least one of spatial coordinates, lot number, road name address, administrative area name, complex name, administrative area name and complex name, administrative area name, and business name. It can be configured to include.

In addition, the real estate data collection/refining module is configured to collect big data by searching the real estate land register, property right register, building ledger, housing public price database, land use plan database, school database, longitude and latitude coordinate database, and news article database. Can be.

In addition, the real estate data collection/refining module uses information on the number of floors, exclusive ownership, and area listed in the building register of the house, and includes information on housing type classification and real housing consisting of single, double, mixed, mixed and categorized. A housing type analysis unit that generates and outputs area information; A site right extraction unit for generating and outputting site right information using land-related information, the housing complex information, the information and the number information of the land register and site right registration unit; A housing usage classification unit for generating and outputting housing usage classification information using the title portion information of the building ledger and the published housing price information; A special housing classification unit for generating and outputting information on a special house classified as one of a general house, a luxury house, or a special house by using the published housing price information and the housing type classification information and real housing area information output from the housing type analysis unit; A maintenance housing classification unit that generates and outputs redevelopment housing information or redevelopment housing information and corresponding business stage information by using land use plan information; An education district classification unit that generates and outputs information on education districts classified into general school districts and premium Korea by using information on surrounding schools centered on the housing lot number; A complex classification unit that generates and outputs complex classification information classified into general complexes and similar complexes by using the longitude and latitude coordinates of the house, the general heading of the building ledger, the heading of the building ledger, and the published price of the house; It may be configured to include at least one or more of a real estate article collection and classification unit that automatically collects, classifies, and outputs data related to real estate from a news article.

And the real estate level may be configured to include at least one or more of a local level, a complex level, a same level, and a ho level.

And the big data construction module, the housing type classification information and real housing area information, the land rights information, the housing use classification information, the special housing information, the redevelopment housing information or reconstruction housing information and corresponding business stage information, the education School district information and the above complex classification information are classified into information that is commonly applied to the corresponding area of the housing, information that is applied to the relevant complex, information that is applied to the relevant lot, information that is applied to the relevant building, and information that is applied to the relevant issue. It can be configured to build data.

In the big data construction method for estimating house price using spatial information according to another object of the present invention described above, the real estate data collection/refining module collects data affecting the formation of house price from at least one database, and And refining data errors between the collected data through spatial attribute values; Constructing big data by linking, by a big data construction module, data for which data errors are purified in the real estate data collection/purification module according to real estate levels; The house price formation information extraction module may be configured to include the step of extracting house price formation information that affects the formation of house prices from the big data built in the big data construction module.

Here, the spatial attribute value is information capable of specifying the location or limiting the range of the real estate, and at least one of spatial coordinates, lot number, road name address, administrative area name, complex name, administrative area name and complex name, administrative area name, and business name. It can be configured to include.

In addition, the real estate data collection/refining module collects data that affects the formation of housing prices from at least one database, and refines the data errors between the collected data through spatial attribute values, the land register of real estate. , A property register, a building register, a housing public price database, a land use plan database, a school database, a longitude and latitude coordinate database, and a news article database to collect big data.

In addition, the real estate data collection/refining module collects data affecting the formation of housing prices from at least one database, and refines the data errors between the collected data through spatial attribute values, the residential type analysis unit Generating and outputting housing type classification information and real housing area information composed of single type, double storey type, mixed type, mixed type, and bisexual type using information on the number of floors, exclusive ownership, and area described in the building register of the house; Generating and outputting the site rights information by using the site-related information, the housing complex information, the information and the number information of the land register and the site right registration unit by the site right extraction unit; Generating and outputting the housing usage classification information by using the title portion information of the building ledger and the published housing price information by the housing usage classification unit; The step of generating and outputting special housing information classified as one of general housing, luxury housing, or special housing by using the published housing price information by the special housing classification unit and the housing type classification information and actual housing area information output from the housing type analysis unit. ; Generating and outputting redevelopment housing information or redevelopment housing information and corresponding business stage information by using the land use plan information by the maintenance housing classification unit; Generating and outputting information on education districts classified as general school districts and premium Korea by using the information on surrounding schools centered on the housing lot number by the education district classification unit; Generating and outputting complex classification information classified into general complexes and similar complexes by using the complex classification unit's longitude and latitude coordinates, the general heading unit of the building ledger, the heading unit of the building ledger, and the published housing price; The real estate article collection and classification unit may be configured to include at least one or more of automatically collecting, classifying, and outputting data related to real estate from a news article.

And the real estate level may be configured to include at least one or more of a local level, a complex level, a same level, and a ho level.

In addition, the step of constructing big data by linking, by the big data building module, data for which data errors are refined in the real estate data collection/purification module according to the real estate level, comprises: the housing type classification information and real housing area information, and the site right information. , The housing use classification information, the special housing information, the redevelopment housing information or reconstruction housing information and the corresponding business stage information, the education school district information, the information commonly applied to the corresponding area of the housing complex, and the corresponding complex It can be configured to construct big data by classifying it into information that is applied, information that is applied to the parcel, information that is applied to the building, and information that is applied to the issue.

According to the big data construction system and method for estimating housing price using the above-described spatial information, it is configured to collect various physical, social, regional price formation factors, etc. from various databases and refine the errors to build big data, Using big data, there is an effect of increasing the accuracy of housing price estimation by considering various factors such as the area, the building itself, education, and transportation in a complex manner.

1 is a block diagram of a big data construction system for estimating a house price using spatial information according to an embodiment of the present invention.
2 is a detailed configuration diagram of a real estate data collection/purification module according to an embodiment of the present invention.
3 is a flowchart of a method of constructing big data for estimating a house price using spatial information according to an embodiment of the present invention.
4 is a detailed flowchart of a real estate data collection/purification step according to an embodiment of the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and will be described in detail in specific details for carrying out the invention. However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. In describing each drawing, similar reference numerals have been used for similar elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. It should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof does not preclude in advance.

Unless otherwise defined, all terms used herein including technical or scientific terms have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in the present application. Does not.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a big data construction system for estimating a house price using spatial information according to an embodiment of the present invention, and FIG. 2 is a detailed configuration of a real estate data collection/purification module according to an embodiment of the present invention It is a degree.

1, a big data construction system 100 for estimating a house price using spatial information according to an embodiment of the present invention includes a real estate data collection/purification module 110, a big data construction module 120, and a housing. It may be configured to include the price formation information extraction module 130.

Hereinafter, a detailed configuration will be described.

The real estate data collection/purification module 110 may be configured to automatically collect data affecting the formation of housing prices from at least one or more databases. It can be configured to collect periodic by a scheduler.

The real estate data collection/purification module 110 may be configured to collect real estate data from multiple databases.

As a database, building register (general title), building register (title section), building register (floor), building register (proprietary section), building register (area), housing published price database, land register, land right register, land use plan database, It may include a school database, a longitude and latitude coordinate database, a subway database, a news article database, and the like.

Databases can be scattered in several places. It can be a database operated by the Ministry of Land, Infrastructure, and Records, the Ministry of Education, etc.

Land use planning database School database, subway database, etc. can be configured to include not only current information but also future information, that is, future planning information on land use, school establishment schedule information, subway opening schedule information, and the like. Information can also be considered as a price shaping factor.

The real estate data collection/purification module 110 may be configured to collect real estate-related data among various pieces of information stored in a database using various data collection techniques such as text mining and data mining. .

The real estate data collection/purification module 110 may be configured to purify data errors of data collected from each other by using the data collected from various databases as a means of spatial attribute values. Even data for the same content may be stored as different data for each database, and may be configured to perform purification for such errors.

Here, the spatial attribute value is information capable of specifying the location or limiting the scope of the real estate, and whether the data collected through various databases are data related to the same content can be confirmed through the spatial attribute value.

The spatial attribute value may be configured to include at least one of spatial coordinates, lot numbers, road name addresses, administrative district names, complex names, administrative district names and complex names, administrative district names, and business names. Here, longitude and latitude coordinates and UTM coordinates may be used as spatial coordinates.

The real estate data collection/purification module 110 may be configured to correlate data collected through various routes through spatial attribute values to check and refine whether there are inconsistent or contradictory data.

For example, the sum of the area of each house of a specific building cannot exceed the sum of the area of each floor, but there may be contradictions or errors in the collected data. It can be configured to automatically refine these contradictions or errors according to a predetermined algorithm.

First, the data collected from various databases can be classified by checking whether it is accurate or inaccurate information, and the data identified as accurate information can be configured to be used for big data construction as it is. However, if the accuracy is very poor or the accuracy cannot be determined, it may be configured to be classified as an error.

Then, it may be configured to analyze an error pattern for the data classified as an error. If the error pattern corresponds to the past error pattern, in the case of an error pattern in which the error is resolved by using the past error pattern correction data, these past error pattern correction data are used to solve the error and use it to build big data. I can.

If it cannot be corrected by using the previous error pattern correction data, it can be classified as a new error pattern, stored, and configured to correct the error by the user. The new error pattern can be used again as data for correcting past error patterns and used for automatic correction of similar error patterns.

Meanwhile, referring to FIG. 2, the real estate data collection/purification module 110 includes a housing type analysis unit 111, a land area extraction unit 112, a housing use classification unit 113, a special housing classification unit 114, and maintenance. It may be configured to include a housing classification unit 115, an education district classification unit 116, a complex classification unit 117, a housing price estimation unit 118, and a real estate article collection and classification unit 119.

The housing type analysis unit 111 uses information on the number of floors, exclusive ownership, and area recorded in the building register of the house, and includes information on classifying the housing type, consisting of a single type, a multi-storey type, a mixed type, a mixed type, and a bisexual type. Can be configured to generate and output.

The site right extraction unit 112 may be configured to generate and output site right information by using land-related information, housing complex information, the same information, and number information of the land register and site right registration unit.

Here, only the information, the information, and the call information may be information collected by the real estate data collection/purification module 110.

The complex information can be the complex name, site area, building area, number of households, number of parking units, complex code, etc. The only code may be information on whether it is a general complex or a similar complex classified by the classification unit 117.

This information can be information about the name of the building, approval for use, the presence of elevators, the number of top floors, the structure/roof, and the EPI score.

The call information can be information on the name of the call, exclusive area, residential area, non-residential area, common area, land share, usage, special housing status, and type of house. The exclusive area, the residential area, the non-residential area, the common area, and the house type are information generated by the housing type analysis unit 111, and whether a special house may be information generated by the special housing classification unit 114.

The housing usage classification unit 113 may be configured to generate and output housing usage classification information using information on the title portion of the building ledger and the published housing price information.

Special housing classification unit 114 is classified as a general housing, luxury housing, or special housing information by using the housing type classification information and actual housing area information output from the published housing price information and the housing type analysis section 111. Can be configured to generate and output.

The maintenance housing classification unit 115 may be configured to generate and output redevelopment housing information or redevelopment housing information and corresponding business stage information by using land use plan information. Depending on the business stage, the impact of house prices by stage may be different.

The education district classification unit 116 may be configured to generate and output education district information classified into general school districts and premium Korea by using information on surrounding schools centered on the housing lot number.

The complex classification unit 117 may be configured to generate and output complex classification information classified into a general complex and a similar complex by using the long-latitude coordinates of the house, the general heading of the building ledger, the heading of the building ledger, and the published price of the house. The general complex and the similar complex can be identified by the complex code.

The real estate article collection and classification unit 119 may be configured to automatically collect, classify, and output data related to real estate from news articles. For example, a complex in a certain area is pursuing reconstruction, a subway or ring road is opened in a certain area, a specific public institution is established in a specific area, or moving into a redevelopment complex or redevelopment complex is initiated. Various real estate-related data can be collected.

The big data building module 120 may be configured to build big data by linking data for which data errors have been refined in the real estate data collection/purification module 110 according to real estate levels. Here, the real estate level means a level, unit, or phase, such as a local level, a complex level, a building level, a house level, and the like.

The big data building module 120 may be configured to classify the data collected by the real estate data collection/purification module 110 and purified by errors according to the real estate level.

Specifically, the big data construction module 120 includes housing type classification information and real housing area information, land area information, housing use classification information, special housing information, redevelopment housing information or reconstruction housing information and corresponding business stage information, education district information, To build big data by classifying the complex classification information into information commonly applied to the relevant area of the house, information applied to the relevant complex, information applied to the relevant lot, information applied to the relevant building, and information applied to the relevant issue. Can be configured.

The house price formation information extraction module 130 may be configured to extract house price formation information that affects the formation of house prices from the big data built in the big data construction module 120.

The house price formation information extraction module 130 is a house price estimation module by collecting data of a region level, a complex level, a building level, and a house level from big data and extracting the house price formation information that affects the formation of the housing price of a specific house. It may be configured to provide 200. The house price estimation module 200 may estimate the price of a corresponding house by using the house price formation information.

The house price estimation module 200 may apply various models for estimating house prices. Among them, it is possible to estimate the house price by applying weights to various information on the formation of house prices. In addition, various methods can be applied, such as estimating the estimated housing price by period in consideration of the expected timing of reconstruction, redevelopment, school establishment, and subway opening.

In addition, it is possible to apply price-forming factors according to demand/supply by taking into account the population inflow and outflow by region, age group, gender, etc. of the population inflow by region, or by calculating the housing supply rate by region.

3 is a flowchart of a method of constructing big data for estimating a house price using spatial information according to an embodiment of the present invention.

Referring to FIG. 3, the real estate data collection/purification module 110 collects data affecting the formation of housing prices from at least one database, and data errors between the collected data as a medium of spatial attribute values It is purified (S110).

Here, the spatial attribute value is information capable of specifying the location or limiting the scope of the real estate, and includes at least one of spatial coordinates, lot numbers, street names, addresses, administrative district names, complex names, administrative district names and complex names, administrative district names, and business names. Can be configured. Here, longitude and latitude coordinates and UTM coordinates may be used as spatial coordinates.

In addition, the real estate data collection/refining module 110 searches for a land register of a house, a property register, a building register, a housing public price database, a land use plan database, a school database, a long-latitude coordinate database, and a news article database to collect big data. Can be configured.

Next, the big data construction module 120 builds big data by linking the data for which data errors are purified in the real estate data collection/purification module 110 according to the real estate level (S120).

Here, the real estate level may be configured to include at least one of a local level, a complex level, a same level, and a ho level.

Next, the house price formation information extraction module 130 extracts house price formation information that affects the formation of house prices from the big data built in the big data construction module 120 (S130).

4 is a detailed flowchart of a step of collecting/purifying real estate data according to an embodiment of the present invention.

Referring to FIG. 4, the housing type analysis unit 111 classifies a house type consisting of a single type, a double storey type, a mixed type, a mixed type, and a bisexual type by using information on the number of floors, exclusive ownership, and area described in the building register of the house. Generates and outputs information and actual living area information.

In addition, the land right extraction unit 112 generates and outputs land right information using land-related information, housing complex information, the same information, and number information of the land register and land right register.

In addition, the housing usage classification unit 113 generates and outputs housing usage classification information using information on the title portion of the building ledger and the published housing price information.

And special housing classified as one of general housing, luxury housing, or special housing by the special housing classification unit 114 using the published housing price information and the housing type classification information and real housing area information output from the housing type analysis unit 111. Generate and print information.

Then, the maintenance housing classification unit 115 generates and outputs redevelopment housing information or redevelopment housing information and corresponding business stage information by using the land use plan information.

In addition, the education district classification unit 116 generates and outputs information on education districts classified as general school districts and premium Korea by using information on surrounding schools centered on the housing lot number.

In addition, the complex classification unit 117 generates and outputs complex classification information classified into a general complex and a similar complex by using the longitude and latitude coordinates of the house, the general heading of the building ledger, the heading of the building ledger, and the published price of the house.

In addition, the real estate article collection and classification unit 118 automatically collects, classifies, and outputs data related to real estate from the news article.

The step (S110) of constructing big data by linking the data for which the data error is refined in the real estate data collection/purification module 110 by the big data construction module 120 of FIG. 3 according to the real estate level (S110), includes a residential type analysis unit ( 111), the housing type classification information and the real housing area information, the land right information output from the land ticket extraction unit 112, the housing use classification information output from the housing use classification unit 113, and the special housing classification unit 114 Special housing information output, redevelopment housing information or reconstruction housing information output from the maintenance housing classification unit 115 and information on the corresponding business stage, education school district information output from the education district classification unit 116, and the complex classification unit 117 It may be configured to construct big data using at least one or more of the output complex classification information and data related to real estate classified by the real estate article collection and classification unit 118.

Here, it will be configured to construct big data by classifying it into information that is commonly applied to the corresponding area of the house, information that is applied to the relevant complex, information that is applied to the relevant lot, information that is applied to the relevant building, and information that is applied to the relevant issue. I can.

Although described with reference to the above embodiments, those skilled in the art can understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention described in the following claims. There will be.

110: Real estate data collection/purification module
111: housing type analysis unit
112: Earth sphere extraction unit
113: housing use classification unit
114: Special housing classification department
115: maintenance housing classification unit
116: Education District Classification Division
117: only classification unit
118: Real Estate Article Collection Classification
120: Big data building module
130: house price formation information extraction module
200: house price estimation module

Claims (1)

The real estate data collection/purification module collects data that affects the formation of housing prices from at least one database, and checks errors between the collected data through the spatial attribute value of the collected data to provide accurate information and Classifying as inaccurate information and automatically refining the data classified as inaccurate information;
The big data construction module connects the data classified as accurate information in the real estate data collection/purification module and the data automatically refined from errors according to the real estate level consisting of the local level, the complex level, the same level, and the house level. Building big data;
Extracting, by a house price formation information extraction module, house price formation information that affects formation of a house price from the big data built in the big data construction module;
A house price estimation module including the step of estimating a house price using the extracted house price formation information,
The real estate data collection/refining module collects data that affects the formation of housing prices from at least one database, and checks the errors between the collected data by using the collected data as a means of spatial attribute values to provide accurate and inaccurate information. Classifying as information and automatically purifying the data classified as inaccurate information,
Among the data collected from the database, it is determined according to a predetermined algorithm prepared in advance whether there is a contradiction between data of different attributes, and when it is determined that there is a contradiction between the data collected from the database, the corresponding data is automatically refined according to a predetermined algorithm. It is configured to be classified as an error when automatic purification cannot be performed,
The spatial attribute value,
As information capable of specifying the location or limiting the scope of the real estate, it is configured to include at least one of spatial coordinates, lot numbers, street names, addresses, administrative district names, complex names, administrative district names and complex names, administrative district names, and business names,
The real estate data collection/purification module collects data that affects the formation of housing prices from at least one database, and checks the errors between the collected data through the spatial attribute value of the collected data to ensure accurate and inaccurate information. Classifying as information and automatically purifying the data classified as inaccurate information,
An error pattern between the collected data is analyzed, and if the analyzed error pattern corresponds to a past error pattern, it is determined whether the error is corrected using the error pattern correction data for the past error pattern, and the result of the determination is corrected. If the error is not corrected as a result of the judgment, it is classified as a new error pattern so that the error can be refined by the user, and the error pattern correction data for the new error pattern is It is configured to be used as error pattern correction data for subsequent errors.
The real estate data collection/purification module collects data that affects the formation of housing prices from at least one database, and checks the errors between the collected data through the spatial attribute value of the collected data to ensure accurate and inaccurate information. Classifying as information and automatically purifying the data classified as inaccurate information,
It is configured to collect big data by searching real estate land register, property right register, building register, public housing price database, land use plan database, school database, longitude and latitude coordinate database, and news article database.
The real estate data collection/purification module collects data that affects the formation of housing prices from at least one database, and checks the errors between the collected data through the spatial attribute value of the collected data to ensure accurate and inaccurate information. Classifying as information and automatically purifying the data classified as inaccurate information,
The housing type analysis unit generates and prints information on housing type classification and actual housing area, which are composed of single, double, mixed, mixed, and bisexual, using the information on the number of floors, exclusive use, and area listed in the building register of the house. And the step of generating and outputting the site right information by using the site-related information, the housing complex information, the information and the number information of the land register and the property right register by the site right extraction unit, and the step of generating and outputting the site right information, and the housing use classification unit information on the title part of the building ledger. And generating and outputting the housing use classification information using the published housing price information, and the special housing classification unit uses the published housing price information and the housing type classification information and the actual living area information output from the housing type analysis unit. Steps for generating and outputting special housing information classified as one of housing, luxury housing, or special housing, and the maintenance housing classification unit generates and outputs redevelopment housing information or redevelopment housing information and corresponding business stage information using land use plan information. Steps, the education district classification unit generates and outputs information on education districts classified as general school districts and premium Korea by using the information of surrounding schools centered on the housing lot number, and the complex classification unit generates and outputs the longitude and latitude coordinates of the housing and the building register. Using the general heading, the heading of the building ledger, and the published price of the house to generate and output complex classification information classified into general complexes and similar complexes, the real estate article collection and classification unit automatically collects real estate-related data from news articles. It is configured to include at least one or more of the steps of classifying and outputting,
The step of constructing big data by linking, by the big data building module, data for which data errors are refined in the real estate data collection/purification module, according to the real estate level,
The housing type classification information and real housing area information, the land right information, the housing use classification information, the special housing information, the redevelopment housing information or reconstruction housing information and the corresponding business stage information, the education school district information, and the complex classification information It is configured to construct big data by classifying it into information commonly applied to the relevant area of the house, information applied to the relevant complex, information applied to the relevant lot, information applied to the relevant building, and information applied to the relevant issue,
The step of estimating, by the house price estimation module, a house price using the extracted house price formation information,
Each weight is applied to the housing price formation information according to the expected time of reconstruction, redevelopment, school establishment, or subway opening by considering the expected timing of reconstruction, redevelopment, school establishment, or subway opening. It is configured to estimate the housing price by applying the price-forming factors of supply and demand according to the housing supply rate by age group, gender, and region,
The step of estimating, by the house price estimation module, a house price using the extracted house price formation information,
The method of constructing big data for estimating house price using spatial information, characterized in that, when the reconstruction or redevelopment is performed, the house price is estimated by applying a price forming factor that varies for each project step.

Images