KR20190041439A - System of building big data for estimating house price using space information having function of data error correction - Google Patents

Abstract

Disclosed are a system for building big data for estimating a house price based on spatial information and a method thereof. According to the present invention, the system comprises: a real estate data collection/correction module collecting data affecting formation of a house price from one or more databases and correcting a data error of the collected data based on a spatial feature value; a big data building module linking the data whose error is corrected in the real estate data collection/correction module in accordance with a real estate level to build big data; and a house price formation information extraction module extracting house price formation information affecting formation of a house price from the big data built in the big data building module. Accordingly, various physical, social, and local price formation factors are collected from various databases, and an error in the collected data is corrected to build big data, thereby providing effects of complexly considering various factors such as a region, a building, education, transportation and the like, and increasing correctness in estimation of a house price based on the big data.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a system and method for estimating a house price with a data error correction function,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a system and method for building big data related to a house, and more particularly, to a system and method for building big data for estimating a house price using spatial information.

Various algorithms for estimating house prices are disclosed.

Housing prices are estimated from a variety of perspectives. Most of them take into consideration factors such as housing area, housing characteristics, etc., based on economic theory, which is determined by demand and supply. These factors are called pricing factors. It is a very complicated and difficult task to collect such price formation factors and to estimate one housing price properly.

However, in estimating the housing price, it is not possible to consider only one price formation factor. Housing prices are a combination of physical, regional, social and educational factors.

However, there is no database to estimate the price of housing considering various factors of price formation factors. In addition, there is a possibility that data of various databases may have mutual errors, and there is no means to refine and utilize these errors.

In addition, these pricing factors are scattered among various databases, and it is also important to collect accurate pricing information.

It is necessary to collect and utilize various information such as land register, building register, land register, as well as position 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.

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

A big data construction system for housing price estimation using spatial information according to an object of the present invention collects data affecting the formation of a house price in at least one database, A real estate data collection / refinement module to refine data errors between each other; A big data building module for building big data by linking the data whose data error has been corrected in the real estate data collection / refinement module according to the level of the real estate; And a home price formation information extraction module for extracting home price formation information that affects the formation of a home price from the big data constructed in the big data construction module.

Here, the spatial attribute value is at least one of space coordinates, lot number, street name address, administrative zone name, short name, administrative zone name and short name, administrative zone name and business name, . ≪ / RTI >

The real estate data collection / refinement module is configured to collect big data by searching the real estate land register, the land registry register, the building register, the housing disclosure price database, the land use planning database, the school database, the latitude and longitude coordinate database, .

The real estate data collection / refinement module may use the information on the number of floors, the total oil amount and the area listed on the building lot of the house to classify the housing type classification information composed of the single type, the double layer type, the mixed type, A housing type analyzer for generating and outputting area information; A land lot extraction unit for generating and outputting land lot right information using land related information of the land ledger and the land land register, the complex information of the house, the same information, and the call information; A housing usage classifying unit for generating housing usage classifying information using the title block information and the housing disclosure price information of the building ledger and outputting the classified information; A special housing classifying unit for generating and outputting special housing information classified as one of a general house, a luxury house or a special house using the housing disclosure price information and the housing type classification information and the actual housing area information outputted from the housing type analysis unit; A maintenance housing classifying unit for generating and outputting redevelopment housing information or reconstructed housing information and corresponding business stage information using land use planning information; The School District Classification Division generates and outputs the education district information classified into the general district and the premium Korea by using the surrounding school information centered on the district number of the house. A classification section for generating and outputting classification information classified into a general complex and a similar complex using the coordinates of the latitude and longitude of the house, the overall title of the building, the title of the building, and the published price of the house; And a real estate article collection classifier that automatically collects, classifies and outputs data related to real estate in a news article.

And the real estate level may be configured to include at least one of a local level, a merely level, a co-level, and a call level.

And the big data construction module is configured to store the housing type classification information and the actual housing area information, the land use right information, the housing usage classification information, the special housing information, the redevelopment housing information or the reconstruction housing information, School district information, and classification information are classified into information applied in common to the corresponding area of the house, information applied to the complex, information applied to the corresponding parcel, information applied to the corresponding parcel, Data. ≪ / RTI >

According to another aspect of the present invention, there is provided a method of building big data for estimating a house price using spatial information, the method comprising: a real estate data collection / refinement module collecting data influencing housing price formation in at least one database, , Refining the collected data with respect to each other through a spatial attribute value; The big data building module establishing big data by linking the data error corrected data in the real estate data collection / refinement module according to the level of the real estate; And a step of extracting the home price formation information extracting module from the big data constructed in the big data building module, the home price formation information influencing the formation of the home price.

Here, the spatial attribute value is at least one of space coordinates, lot number, street name address, administrative zone name, short name, administrative zone name and short name, administrative zone name and business name, . ≪ / RTI >

And the real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases, and the collected data is refinement of mutual data errors via spatial attribute values, , A land registry book, a building register, a housing disclosure price database, a land use plan database, a school database, a latitude and longitude coordinate database, and a news article database to collect big data.

And the real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases, and refining data errors among the collected data through spatial attribute values, Generating and outputting housing type classification information and actual housing area information, which are composed of a single type, a multi-layer type, a mixed type, a mixed type, and a positive type using the information on the number of stories, A land use right extracting unit for generating and outputting land use right information by using the land related information of the land ledger and the land tenure register, the complex information of the house, the same information, and the call information; Generating housing usage classification information using the title division information and the housing disclosure price information of the housing use classification additional building ledger; A step of generating and outputting special housing information classified as one of a general house, a luxury house or a special house by using the information on the sale price of the special house classification unit and the housing type classification information and the actual housing area information output from the housing type analysis unit ; Generating and outputting redevelopment housing information or reconstructed housing information and corresponding business stage information using the land use planning information of the maintenance house classification section; Generating and outputting the education district information classified into the general district and the premium Korea using the surrounding school information centered on the district number of the education district classification division; Generating and outputting classification information classified into a general complex and a similar complex using the latitude and longitude coordinates of the classification unit, the overall title of the building, the title of the building, and the published price of the house; And the real estate article collection category may automatically include at least one of collecting, sorting and outputting data related to real estate in the news article.

And the real estate level may be configured to include at least one of a local level, a merely level, a co-level, and a call level.

And the big data establishing module establishing the big data by linking the data error-refined data in the real estate data collecting / refining module according to the real estate level includes the housing type classification information, the real estate information, , Information on the classification of the housing for use, the special housing information, the redevelopment housing information or the reconstructed housing information and the corresponding business stage information, the education district information, and the classification information to the corresponding complex Information to be applied to the relevant parcels, information to be applied to the corresponding parcels, and information to be applied to the relevant call.

According to the system and method for building big data for estimating the house price using the spatial information, various physical, social, and local pricing factors are collected from various databases, and errors are refined to construct big data, By using Big Data, it is possible to consider various factors such as area, building itself, education, traffic, etc., and to improve the accuracy of house price estimation.

FIG. 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. Referring to FIG.
2 is a detailed configuration diagram of a real estate data collection / refinement 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 real estate data collection / refinement steps according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail to the concrete inventive concept. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

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

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, 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 this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

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

FIG. 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. FIG. 2 is a block diagram of a detailed structure of a real estate data collection / refinement module according to an embodiment of the present invention .

Referring to FIG. 1, a big data construction system 100 for housing price estimation using spatial information according to an embodiment of the present invention includes a real estate data collection / refinement module 110, a big data construction module 120, And a pricing formation information extraction module 130. [

Hereinafter, the detailed configuration will be described.

The real estate data collection / refinement module 110 may be configured to automatically collect data that affects housing price formation in at least one or more databases. And may be configured to collect the periodic by a scheduler.

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

The databases include the building title, the building title, the building ledger, the building ledger, the building ledger, the housing disclosure price database, the land register, the land register book, the land use planning database, A school database, a latitude and longitude coordinate database, a subway database, a news article database, and the like.

The database can be scattered in many places. It can be a database operated by the Ministry of Land, the Registry, and the Ministry of Education.

Land use planning database The school database and the subway database can be configured to include current information as well as future information such as future planning information about the land use, school building schedule information, and subway opening schedule information. Information can also be considered as a factor of price formation.

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

The real estate data collection / refinement module 110 may be configured to refine the data collected in the various databases and to correct data errors of the collected data with each other via the spatial attribute values. Data for the same contents can be stored as different data for each database, and can be configured to perform refinement for such errors.

Here, the spatial attribute value is information that can specify the location of the real estate or can limit the range, and whether the data collected through the various databases are data related to the same contents can be confirmed through the spatial attribute value.

The spatial attribute value may be configured to include at least one of space coordinates, lot number, street name address, administrative zone name, complex name, administrative zone name and complex name, administrative zone name, and business name. Here, latitude and longitude coordinates and UTM coordinates may be used as spatial coordinates.

The real estate data collection / refinement module 110 may be configured to correlate the data collected through the various routes with the spatial attribute values so as to check whether there is inconsistent or contradictory data among the mutual data.

For example, the sum of the area of each door in a particular building can not exceed the sum of the floor area, but the collected data may have contradictions or errors. And may be configured to automatically refine such inconsistencies or errors according to a predetermined algorithm.

First, the data collected from various databases is classified by confirming whether the information is correct or incorrect, and the data confirmed by the accuracy information is configured to be used for building big data as it is. However, if the accuracy is too low or the accuracy can not be determined, it can be configured to be classified as error.

And then analyze the error pattern for the data classified as error. If the error pattern corresponds to the past error pattern, if it is an error pattern in which the error is solved by using the past error pattern correction data, the past error pattern correction data can be used to solve the error and utilized in building big data .

If it is not possible to correct using the error pattern correction data of the past, it may be classified and stored as a new error pattern and corrected by the user. The new error pattern can be used as a correction data of past error patterns and can be used for automatic correction of similar error patterns.

2, the real estate data collection / refinement module 110 includes a housing type analysis unit 111, a land use right extraction unit 112, a housing usage classification unit 113, a special housing classification unit 114, A housing classifying section 115, a school education classifying section 116, a classifying section 117, a house price estimating section 118 and an estate article collection classifying section 119. [

The residential type analyzing unit 111 analyzes the information on the number of stories, the total oil level, and the area on the building ledger of the house to obtain housing type classification information and actual residence area information, which are composed of a single type, a double type, a mixed type, And output it.

The land use right extracting unit 112 may be configured to generate and output land use right information using the land related information of the land ledger and the land use land register, housing information, the same information, and call information.

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

The information can be just a name, a site area, a building area, a household number, a parking number, a complex code, and the like. Only the code may be information about whether it is a general complex or categorical complex classified by the classifier 117.

The information may be information on the name, use authorization, elevator availability, maximum number of floors, structure / roof, and EPI score.

The call information can be information about the name of the call, private area, residential area, non-residential area, public area, land ownership, use, special housing, and housing type. The private area, the residential area, the non-residential area, the common area, and the housing type are information generated by the residential type analyzing unit 111, and the special housing may be information generated by the special housing classifying unit 114.

The housing usage classifying unit 113 may be configured to generate housing usage classification information using the title block information and the housing disclosure price information of the building ledger and output it.

The special house classifying unit 114 classifies the special housing information classified into one of the general house, the luxury house or the special house by using the housing disclosure price information and the housing type classification information and the actual housing area information output from the housing type analysis unit 111 And output it.

The maintenance house classification unit 115 may be configured to generate and output redevelopment housing information or reconstructed housing information and corresponding business stage information using the land use planning information. Depending on the stage of the project, the effect of the housing price on the stage may be different.

The education classifier classifier 116 may be configured to generate and output the education classroom information classified into the general school district and the premium Korean class using the surrounding school information centered on the lot number of the house.

The classification section 117 may be configured to generate and output the classification information classified into the general complex and the similar complex by using the coordinates of the latitude and longitude of the house, the overall title of the building, the title of the building, and the published price of the house. Only ordinary complexes and similar complexes can be identified by code.

The real estate article collection classifying section 119 can be configured to automatically collect, classify and output data related to real estate in a news article. For example, if a jurisdiction is promoting reconstruction, or a metro or a ring road is established in a certain area, a specific public institution is established in a certain area, or a residential area is moved to a reconstruction or redevelopment complex Various real estate related data can be collected.

The big data construction module 120 can be configured to construct big data by linking the data error corrected data in the real estate data collection / refinement module 110 according to the level of the real estate. Here, the real estate level means a level, a unit, or a phase such as a local level, a merely level, a co-level, a call level, and the like.

The big data building module 120 can be configured to classify the error corrected data collected and collected by the real estate data collection / refinement module 110 according to the property level.

Specifically, the big data establishing module 120 may include information on the type of housing, classification of real estate, land use right information, housing use classification information, special housing information, redevelopment housing information or reconstructed housing information, Classification information should be classified into information applied in common to the relevant area of the house, information applied to the complex, information applied to the parcel, information applied to the parcel, Lt; / RTI >

The home price formation information extraction module 130 can be configured to extract the home price formation information that affects the formation of the home price from the big data constructed in the big data construction module 120. [

The home price formation information extraction module 130 collects the local level, the merely level, the same level, and the call level data from the big data to extract the housing price formation information affecting the housing price formation of the specific house, (Not shown). The housing price estimation module 200 can estimate the price of the corresponding house using the housing price formation information.

The home price estimation module 200 may apply various models for estimating the home price. The house price can be estimated by applying the weight to various housing price formation information. In addition, various methods can be applied such as estimating the housing price estimate based on the timing of reconstruction, redevelopment, school establishment, and opening of the subway.

In addition, it is possible to consider factors such as age and gender of population flow by region and the number of inhabitants in each region, or to estimate the housing supply rate by region and apply price formation factors according to demand / supply.

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 / refinement module 110 collects data affecting housing price formation in at least one or more databases, and collects the collected data as a data error (S110).

Here, the spatial attribute value may include at least one of space coordinates, lot number, street name address, administrative zone name, short name, administrative zone name and short name, administrative zone name and business name, Lt; / RTI > Here, latitude and longitude coordinates and UTM coordinates may be used as spatial coordinates.

The real estate data collection / refinement module 110 then collects the big data by searching the housing lot, the land register, the building register, the housing disclosure price database, the land use planning database, the school database, the latitude and longitude coordinate database, Lt; / RTI >

Next, the big data establishing module 120 constructs big data by linking the refined data with the data error in the real estate data collection / refinement module 110 according to the level of the real estate (S120).

Here, the real estate level may be configured to include at least one of a local level, a merely level, a co-level, and a call level.

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

4 is a detailed flowchart of real estate data collection / refinement steps according to an embodiment of the present invention.

4, the residential type analyzing unit 111 analyzes the information on the number of stories, the total oil level, and the area on the building main building of a house and classifies the type of the residential building, which is composed of a single type, a duplex type, a mixed type, Information and actual residential area information are generated and output.

Then, the land use right extracting unit 112 generates land use right information by using the land related information of the land ledger and the land use right register, housing information, the same information, and call information, and outputs it

The housing usage classification unit 113 generates housing usage classification information using the title portion information and the housing disclosure price information of the building ledger and outputs the same.

Then, the special housing classification unit 114 generates a special housing classified into a general house, a luxury house, or a special house using the housing disclosure price information and the housing type classification information and the actual housing area information output from the housing type analysis unit 111 And generates and outputs information.

The maintenance house classification unit 115 generates and outputs redevelopment housing information or reconstructed housing information and corresponding business step information using the land use plan information.

Then, the education district group classification unit 116 generates and outputs the education district information classified into the general district and the premium Korea using the surrounding school information centering on the lot number of the house.

Then, the classification unit 117 generates and outputs complex classification information classified into the general complex and the similar complex using the longitudinal direction coordinates of the house, the comprehensive heading of the building ledger, the title of the building ledger, and the published price of the house.

Then, the real estate article collection and classification unit 118 automatically collects and classifies the data related to the real estate in the news article.

The step S110 of building the big data by linking the data error-refined data according to the real estate level in the real data collection / refinement module 110 of the real data collection / refinement module 110 of FIG. Housing type classification information and actual residential area information outputted from the land use right extracting unit 112, land use right information outputted from the land use right extracting unit 112, housing use classification information outputted from the housing usage classifying unit 113, The redevelopment house information or reconstructed housing information output from the maintenance house classifying unit 115 and the corresponding business stage information, the education school district information output from the education school classifying unit 116, The real estate article collection classifier 118 classifies the real estate classified by the real estate article collection classifier 118 into at least one of the real estate classified by the real estate article collection classifier 118,

Here, information to be applied to the relevant area of the house, information to be applied to the complex, information to be applied to the parcel, information to be applied to the parcel, and information to be applied to the relevant call, .

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention as defined in the following claims. There will be.

110: Real Estate Data Collection / Refinement Module
111: Housing type analysis unit
112:
113: Home use classification section
114: Special housing classification division
115: Maintenance Housing Classification Division
116: School District Division Division
117:
118: Real Estate Article Collection Division
120: Big data construction module
130: house price formation information extraction module
200: Home price estimation module

Claims (8)

Collecting data affecting housing price formation in at least one or more databases, identifying errors between the collected data through the spatial attribute value of the collected data, classifying the collected data into accurate information and incorrect information, A real estate data collection / refinement module for automatically refining the data classified as inaccurate information;
A big data building module for building big data by linking data classified as accurate information and automatically corrected data in the real estate data collection / refinement module according to a level of a real estate;
And a home price formation information extracting module for extracting home price formation information that affects housing price formation in the big data constructed in the big data building module,
The real estate data collection /
Determining whether there is a contradiction between data of different attributes among the data collected in the database according to a predetermined algorithm prepared in advance; and if it is determined that there is a contradiction between the data, the data is automatically refined according to a predetermined algorithm And if the automatic refinement is not possible, it is classified as an error. The big data construction system for housing price estimation using spatial information having a data error correction function.
2. The method of claim 1,
When the number of floor information of a certain building is greater than the maximum number of floors of the building, the sum of the area of each floor of the predetermined floor exceeds the floor area of the floor, or the reconstruction / redevelopment project or the public facility project is due The system comprising: at least one of a plurality of data processing systems including a plurality of data processing systems;
The system of claim 1, wherein the real estate data collection /
Wherein the data error correcting function is configured to search the database of the real estate land register, the land registry register, the building register, the housing disclosure price database, the land use plan database, the school database, the latitude and longitude coordinate database, Big Data Construction System for Housing Price Estimation Using Spatial Information.
The system of claim 1, wherein the real estate data collection /
Housing type classification information composed of single type, double type, mixed type, mixed type and positive type by using the information on the number of stories, total oil level and area listed in the building of the house, and a housing type analysis part;
A land lot extraction unit for generating and outputting land lot right information using land related information of the land ledger and the land land register, the complex information of the house, the same information, and the call information;
A housing usage classifying unit for generating housing usage classifying information using the title block information and the housing disclosure price information of the building ledger and outputting the classified information;
A special housing classifying unit for generating and outputting special housing information classified as one of a general house, a luxury house or a special house using the housing disclosure price information and the housing type classification information and the actual housing area information outputted from the housing type analysis unit;
A maintenance housing classifying unit for generating and outputting redevelopment housing information or reconstructed housing information and corresponding business stage information using land use planning information;
The School District Classification Division generates and outputs the education district information classified into the general district and the premium Korea by using the surrounding school information centered on the district number of the house.
A classification section for generating and outputting classification information classified into a general complex and a similar complex using the coordinates of the latitude and longitude of the house, the overall title of the building, the title of the building, and the published price of the house;
And a real estate article collection classifier for automatically collecting and classifying data related to real estate in a news article and outputting the classified real estate article collection classifier. Data building system.
The method according to claim 1,
A local level, a merely level, a co-level, and a call level. The system for building big data for estimating a house price using spatial information having a data error correcting function.
The method of claim 4, wherein the big data construction module comprises:
The housing classification information and the actual residence area information, the land-ownership information, the housing usage classification information, the special housing information, the redevelopment housing information or the reconstruction housing information and the corresponding business stage information, the education school district information,
It is structured to construct big data classified into information applied in common to the relevant area of the house, information applied to the complex, information applied to the parcel, information applied to the parcel, and information applied to the call Big Data Construction System for Housing Price Estimation Using Spatial Information with Data Error Correction Function.
A real estate data collection / refinement module collects data affecting the formation of a house price in at least one database, identifies errors between the collected data through the spatial attribute value of the collected data, Automatically classifying data classified as inaccurate information and automatically classifying data classified as inaccurate information;
The big data establishing module associates the data classified with accurate information and the automatically corrected data with the real estate level composed of the local level, the merely level, the same level, and the call level in the real estate data collection / refinement module Building big data;
The home price formation information extraction module extracts home price formation information that affects the formation of the home price in the big data constructed in the big data construction module,
Wherein the real estate data collection / refinement module collects data affecting housing price formation in at least one database and identifies errors between the collected data via spatial attribute values to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
Determining whether there is a contradiction between data of different attributes among the data collected in the database according to a predetermined algorithm prepared in advance; and if it is determined that there is a contradiction between the data, the data is automatically refined according to a predetermined algorithm And is configured to classify as an error if automatic refinement is not possible,
The contradiction between the data of the different attributes,
When the number of floor information of a certain building is greater than the maximum number of floors of the building, the sum of the area of each floor of the predetermined floor exceeds the floor area of the floor, or the reconstruction / redevelopment project or the public facility project is due And at least one of the cases,
Wherein the spatial attribute value comprises:
The information including at least one of space coordinates, lot number, street name address, administrative zone name, complex name, administrative zone name and complex name, administrative zone name and business name,
The real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases and identifies errors between the collected data via spatial attribute values of the collected data to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
And is configured to collect big data by searching the land register, the land registry book, the building register book, the housing disclosure price database, the land use planning database, the school database, the latitude and longitude coordinate database,
The real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases and identifies errors between the collected data via spatial attribute values of the collected data to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
Housing Type Analysis The house type classification information and the living room area information composed of the single type, the double type, the mixed type, the mixed type and the positive type are generated and outputted by using the information on the number of stories, A land use right extracting unit generating and outputting land use right information by using the land related information of the land ledger and the land use right register, the housing information of the house, the same information, and the call information, And generating and outputting housing use classification information by using the housing disclosure price information, and a step of generating and outputting housing usage classification information by using the housing disclosure price information and the housing type classification information and the actual housing area information output from the housing type analysis unit Generate and output special house information classified as one of houses, luxury houses or special houses A step of generating and outputting redevelopment housing information or reconstructed housing information and corresponding business step information using the land use planning information and the maintenance school classification information, A step of generating and outputting education district information classified into a general school district and a premium Korea; and a step of generating and outputting education district information classified as a general district and a premium Korea by using the coordinates of the latitude and longitude of the classification unit, the general title unit of the building, And a step of automatically collecting, classifying and outputting the data related to the real estate in the news article, and outputting the classified information,
Wherein the big data building module constructs big data by linking data refined data in the real estate data collection / refinement module according to a property level,
The housing classification information and the actual residence area information, the land-ownership information, the housing usage classification information, the special housing information, the redevelopment housing information or the reconstruction housing information and the corresponding business stage information, the education school district information, It is structured to construct big data classified into information applied in common to the relevant area of the house, information applied to the complex, information applied to the parcel, information applied to the parcel, and information applied to the call A method for constructing big data for estimating house price using spatial information with data error correction function.
A real estate data collection / refinement module collects data affecting the formation of a house price in at least one database, identifies errors between the collected data through the spatial attribute value of the collected data, Automatically classifying data classified as inaccurate information and automatically classifying data classified as inaccurate information;
Building big data by linking the data classified as accurate information and the automatically refined data in the real data collection / refinement module according to the level of the real estate;
The home price formation information extraction module extracts home price formation information that affects the formation of the home price in the big data constructed in the big data construction module,
Wherein the real estate data collection / refinement module collects data affecting housing price formation in at least one database and identifies errors between the collected data via spatial attribute values to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
Determining whether there is a contradiction between data of different attributes among the data collected in the database according to a predetermined algorithm prepared in advance; and if it is determined that there is a contradiction between the data, the data is automatically refined according to a predetermined algorithm And is configured to classify as an error if automatic refinement is not possible,
The contradiction between the data of the different attributes,
When the number of floor information of a certain building is greater than the maximum number of floors of the building, the sum of the area of each floor of the predetermined floor exceeds the floor area of the floor, or the reconstruction / redevelopment project or the public facility project is due And at least one of the cases,
Wherein the spatial attribute value comprises:
The information including at least one of space coordinates, lot number, street name address, administrative zone name, complex name, administrative zone name and complex name, administrative zone name and business name,
The real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases and identifies errors between the collected data via spatial attribute values of the collected data to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
If the analyzed error pattern corresponds to the past error pattern, it is determined whether the error is corrected using the error pattern correction data of the past error pattern, and if the error pattern is corrected, The error pattern correction data for the new error pattern is classified into a new error pattern so that the error can be refined by the user if the error is not corrected as a result of the determination, It is configured to use as an error pattern correction data for subsequent errors,
The real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases and identifies errors between the collected data via spatial attribute values of the collected data to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
And is configured to collect big data by searching the land register, the land registry book, the building register book, the housing disclosure price database, the land use planning database, the school database, the latitude and longitude coordinate database,
The real estate data collection / refinement module collects data affecting housing price formation in at least one or more databases and identifies errors between the collected data via spatial attribute values of the collected data to provide accurate and inaccurate information The step of automatically classifying data classified as inaccurate information comprises:
Housing Type Analysis The house type classification information and the living room area information composed of the single type, the double type, the mixed type, the mixed type and the positive type are generated and outputted by using the information on the number of stories, A land use right extracting unit generating and outputting land use right information by using the land related information of the land ledger and the land use right register, the housing information of the house, the same information, and the call information, And generating and outputting housing use classification information by using the housing disclosure price information, and a step of generating and outputting housing usage classification information by using the housing disclosure price information and the housing type classification information and the actual housing area information output from the housing type analysis unit Generate and output special house information classified as one of houses, luxury houses or special houses A step of generating and outputting redevelopment housing information or reconstructed housing information and corresponding business step information using the land use planning information and the maintenance school classification information, A step of generating and outputting education district information classified into a general school district and a premium Korea; and a step of generating and outputting education district information classified as a general district and a premium Korea by using the coordinates of the latitude and longitude of the classification unit, the general title unit of the building, And a step of automatically collecting, classifying and outputting the data related to the real estate in the news article, and outputting the classified information,
Wherein the big data building module constructs big data by linking data refined data in the real estate data collection / refinement module according to a property level,
The housing classification information and the actual residence area information, the land-ownership information, the housing use classification information, the special housing information, the redevelopment housing information or the reconstruction housing information and the corresponding business stage information, the education school district information, It is structured to construct big data classified into information applied in common to the relevant area of the house, information applied to the complex, information applied to the parcel, information applied to the parcel, and information applied to the call A method for constructing big data for estimating house price using spatial information with data error correction function.

Images