KR102329398B1 - Land value analysis service provision server - Google Patents

Abstract

The present invention relates to a server for providing a land finding and land value analyzing service, which provides a service for dividing a managed area into unit areas having a particular dimension and analyzing and predicting a land value of a target land to be simulated by utilizing structured data and unstructured data provided by an outer data server. The server of the present invention divides a whole national land into 25 m × 25 m cells, based on longitude and latitude coordinates and collects and manages data necessary for land value analysis for each cell. The server of the present invention comprises a database unit, a big data establishment unit, a service provision unit, and an input unit. Accordingly, the time and costs spent on analysis of a land value in order to find and develop a particular land and determine whether to perform investment can be greatly reduced and analysis of a land value is performed by utilizing unstructured data as well as structured data to enhance reliability.

Description

Land excavation and value analysis service provision server {Land value analysis service provision server}

The present invention relates to a land excavation and value analysis service providing server that receives external data necessary for land value analysis from an external data providing server and calculates the value of a specific land based on the external data.

With the advent of the digital and mobile era, the world is rapidly changing into a digital world. In accordance with these changes in the times, in the real estate field, in addition to traditional research and analysis methods such as statistical approaches, macroeconomic approaches, and life cycle approaches, it is necessary to develop and apply new analysis methods using big data in recent years.

Big data is defined as three dimensions of issues and opportunities following the rapid growth of data: the amount of data, the speed of data input/output, and the diversity of data types. It is expanding into a concept that includes value and accuracy.

Big data can be broadly divided into structured data and unstructured data. The standardized data is statistics published by government agencies such as the National Statistical Office, which means that it is mainly written in numbers. These are data in the form of texts, photos, emoticons, and the like.

Utilizing standardized big data, Republic of Korea Patent Registration No. 10-1825559 stores and manages national land space by time series in unit cells based on longitude and latitude coordinates composed of 25 m * 25 m grid units, and through this, analyzes the characteristics of each unit region and It discloses an urban research analysis service providing server that can simulate environmental changes in future urban planning by utilizing it.

However, the general phenomenon of real estate is made by the complex interaction of various factors. The Republic of Korea Patent Registration No. 10-1825559 analyzes and predicts the real estate market and price determination as standardized variables such as housing demand and supply and housing supply rate, but there are always limitations.

Republic of Korea Patent No. 10-1825559

The present invention was derived to solve the above problems, and by dividing the management area into unit areas of a specific size, using the structured data and unstructured data provided from the external data server, the simulation target site was developed for residential, commercial, and industrial use. It relates to a server that provides a land excavation and value analysis service that analyzes, evaluates, and predicts land value to discover valuable land.

The present invention provides a land excavation and value analysis service providing server that receives external data required for land value analysis from an external data providing server and calculates the value of a specific land based on the external data, in which a management area is divided based on latitude and longitude a database unit including at least one unit area data structure in which time-series data is stored corresponding to each of at least one or more unit areas; a big data construction unit for constructing the database unit by analyzing the external data; a service providing unit that receives basic data for land value analysis from the big data construction unit and provides a land value analysis service for at least one simulation target site; and an input unit for receiving the simulation target land, which is the land to be evaluated.

In addition, the external data includes fixed data, highway IC, location data of government offices including public transportation stops and city halls, auction real estate information provided by a public data portal, spatial big data and real estate transaction price information provided by the Ministry of Land, Infrastructure and Transport, Administrative plan data provided by the central and local governments, personal information non-identifying floating population/call volume data provided by mobile carriers, and personal information non-identifying card sales information provided by credit card companies.

In addition, the service providing unit calculates the value before and after development of the simulation target using the external data.

In addition, the external data further includes unstructured data for the management area.

In addition, the unstructured data includes real estate Internet articles related to the management area that can be searched by a search engine.

In addition, each of the at least one data structure of the unit area includes a header in which geographic identification information for each of the unit areas and basic information for land value analysis for the unit area are stored; and a plurality of unit cell records in which time-specific data for land value analysis items for the unit area are stored.

In addition, the big data construction unit data collection means for collecting the external data; data extraction means for extracting time-specific data on land value analysis items for at least one or more of the unit areas from the external data collected by the data collection means; a value item mapping means for mapping the data for each period of the value analysis items for the unit area extracted by the data extraction means to the database unit; and basic item analysis means for calculating geographic identification information for each unit area and basic information for land value analysis for the unit area for each unit area data structure.

In addition, the service providing unit, the base score calculation means for calculating the city value focal point by using the external data; a comprehensive score calculation means for calculating a comprehensive city value score by reflecting a weight on the city value focus score; and a final score calculation means for calculating a final value score by using the city value composite score, wherein the final value score and the current actual transaction price for the simulation target site are used to calculate the value before and after development of the simulation target site to provide

In addition, the city value focus score includes an accessibility score, a location score, and a target point by using basic factors that are divided into accessibility, location, and target site, and the city value composite score is weighted by development type to the city value focus score The city value composite score is calculated by reflecting It includes a comprehensive accessibility score calculated by reflecting the locationability score, a comprehensive locationability score calculated by reflecting a weight in the locationability score, and a comprehensive site intelligence score calculated by reflecting the weight in the siteability score, and the accessibility score is a highway with the target site It is calculated according to IC accessibility, public transportation accessibility, city hall location accessibility, and major national road accessibility, and the location score is calculated according to the degree of development around the target site, the existence of preferred or unpreferred facilities, and the urbanization rate, and the target point is the above It is calculated by using environmental factors including the slope of the site, ecological naturalness, and land environmental evaluation map, and the final value score is the average value of the comprehensive accessibility score, locationability score, and target site score included in the city value score. is defined as

In addition, the service providing unit calculates a trend value to be applied to at least one unit area selected as a simulation target, wherein the trend value is a first factor defined as [change in infrastructure, change in population] and [population, industry, administration], trend value calculation means for calculating the change value of the dependent variable by distance from the cause of the independent variable with respect to the change amount of the independent variable of any one of the second factors in the past period; a stereotype prediction means for calculating the amount of change for the future by performing a simulation for each distance from the source of the independent variable in at least one unit area selected as the simulation target using the trend value calculated by the trend value calculating means; A polarity value to be applied to at least one unit area selected as a simulation target is calculated, wherein the polarity value is a polarity value calculated as an average value of the basic polarity values corresponding to expressions included in Internet articles about the simulation target collected for a certain period calculation means; And using the polarity value calculated by the polarity value calculating means and the section reliability, simulation is performed for each distance from the source of the polarity value in at least one unit area selected as the simulation target, and the atypical value predicted value for the future It may further include atypical prediction means for calculating.

In addition, the data collection means includes collecting the unstructured data by web crawling from the external data providing server, and the data extraction means, from the structured data to the structured value analysis items for the unit area structured item extraction means for extracting star data; and an unstructured item extraction means for extracting time-wise data on the unstructured value analysis items for the unit area from the unstructured data, wherein the value item mapping means comprises: the unit area extracted by the structured item extraction means a fixed item mapping means for mapping the data for each period of the fixed value analysis items to the database unit; and an atypical item mapping unit for mapping the data for each period of the atypical value analysis items for the unit area extracted by the atypical item extraction unit to the database unit.

In addition, the basic item analysis means uses the fixed data to determine the land value of at least one of a fixed value level type calculated as a measure of land value increase and a fixed value level driven type calculated with respect to main factors of the fixed value level type Basic information for analysis may be stored in the header, and basic information for land value analysis including an atypical value level type calculated as a measure of land value increase by using the unstructured data may be further stored in the header.

In addition, the fixed value level type includes at least one of a value growth type, a value stability type, and a value decay type, and the fixed value level driven type is determined as a major factor among factors related to the determination of the fixed value level type, and the The atypical value level type is any one of a value increase type, a value maintenance type, and a value decrease type.

In addition, the atypical value level type is determined according to the polarity value calculated by the polarity value calculating means.

In addition, the service providing unit further includes a value prediction means for calculating the future value of the unit area.

In addition, the service providing unit is a specific reliability calculation means for calculating a specific reliability using the atypical value level type and the result of comparing the actual real estate transaction price information at the reference point with the actual real estate transaction price information of the real estate to be simulated after a specific period; include more

In addition, the trend value calculating means includes a fixed value level type, a fixed value level type probability, a fixed value level driven type, and a fixed value level driven type probability of the simulation target site when the past accumulated data of the simulation target site has not been accumulated for more than a certain period of time A trend value may be calculated from a region of the corresponding period by selecting any one of a plurality of other unit regions and reference years having at least two or more items similar to each other.

In addition, when the past accumulated data of the target site has not been accumulated for more than a certain period of time, the polarity value calculating means includes at least one of a fixed value level type, a fixed value level type probability, a fixed value level driven type, and a fixed value level driven type probability of the simulation target site A polarity value is calculated from the region at the time by selecting any one of a plurality of other unit regions and base years having similar two or more items.

In addition, the atypical value analysis item includes at least one major item among price, policy, and market.

In addition, the service providing unit further includes a section reliability calculation means for calculating the section reliability defined as the average value of the specific reliability for a specific period.

In addition, when the section reliability is positive, the atypical prediction means reflects the section reliability when calculating the atypical value predicted value for the simulation target site, and when the section reliability is 0 or negative, the atypical value predicted value for the simulation target site The section reliability is not reflected in the calculation.

The server for providing land excavation and value analysis service according to the present invention utilizes big data including structured data and unstructured data to analyze and predict land value according to the development type of the simulation target site, thereby providing high reliability when establishing a land development plan, It is possible to provide land value information according to the type of development and to discover land with high value accordingly.

1 is a schematic conceptual diagram for explaining the relationship between an external data providing server and a land excavation and value analysis service providing server according to an embodiment of the present invention.
2 is a conceptual diagram illustrating a land excavation and value analysis service providing server according to an embodiment of the present invention.
3 is a conceptual diagram illustrating external data.
4 is a schematic diagram illustrating a unit area data structure according to an embodiment of the present invention.
5 is a conceptual diagram illustrating a big data construction unit according to an embodiment of the present invention.
6 is a conceptual diagram illustrating a service providing unit according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The present invention is not limited to the embodiments disclosed below, but will be embodied in various different forms, and only these embodiments are intended to completely inform those of ordinary skill in the art to which the present invention pertains to the scope of the invention. It is provided for the purpose, and matters obvious to those of ordinary skill in the art of the present invention may be omitted. Also, the same reference numerals refer to the same members throughout each embodiment. On the other hand, each component shown in the drawings may have an exaggerated thickness or dimension for convenience of description, and does not mean that it should actually be configured in a ratio between the corresponding dimensions or components.

1 is a schematic conceptual diagram for explaining the relationship between an external data providing server 10 and a land excavation and value analysis service providing server 100 according to an embodiment of the present invention, and FIG. 2 is an embodiment of the present invention. It is a conceptual diagram showing the land excavation and value analysis service providing server 100 according to the

1 and 2, the server 100 for providing a land excavation and value analysis service according to the present invention receives the external data 11 necessary for land value analysis from the external data providing server 10 and constructs the big data. The database is converted into a database in the unit 12 and stored in the database unit 110 , the simulation target land that is the land to be evaluated is input through the input unit 150 , and the service provider 130 stores the database stored in the database unit 110 . (DB) will provide land excavation and value analysis services. That is, the server 100 for providing a land excavation and value analysis service according to this embodiment includes a database unit 110 , a big data unit construction unit 120 , an input unit 150 , and a service providing unit 130 utilizing the same. In addition, each of the database unit 110 , the big data construction unit 120 , and the service providing unit 130 may be implemented as a separate physical server, or may be implemented to be performed by one server. That is, the implementation method of the physical system as long as it performs the same function is independent of the technical characteristics of the invention. That is, in the following, each function will be described using terms such as the database unit 110, the big data construction unit 120, and the service providing unit 130 using the same. should be, and this does not mean that the servers must be physically separated. Meanwhile, here, the external data providing server 10 may be a system server that provides the structured data 11a and the unstructured data 11b for the management area as described above. The database unit 110 is a management area. At least one unit region data structure 111 in which time-series data is stored corresponding to each of at least one or more unit regions partitioned based on latitude and longitude may be provided.

The big data construction unit 120 may construct the database unit 110 by analyzing the external data 11 .

The input unit 150 may be physically included in the server for providing land excavation and value analysis services from the user, and may be a separately provided keyboard or terminal such as a smartphone. When the input unit 150 is a terminal such as a smartphone, the land excavation and value analysis service providing server of the present invention and the smartphone may be connected through a wired or wireless communication network such as an LTE network.

The land excavation and value analysis service providing server of the present invention receives a simulation target site, which is the land to be evaluated, through the input unit 150 .

The service providing unit 130 may receive basic data for land value analysis from the big data construction unit 120 and provide a land value analysis service for at least one or more of the simulation target sites. The configuration of the database unit 110 , the big data construction unit 120 , and the service provision unit 130 will be described in detail later.

3 is a conceptual diagram illustrating the external data 11 . Referring to FIG. 3 , the external data 11 may include structured data 11a and unstructured data 11b for the management area.

The structured data includes location information of public offices including highway ICs, public transportation stops and city halls, auction real estate information provided by public data portals, spatial big data and real estate transaction price information provided by the Ministry of Land, Infrastructure and Transport, central and local governments Administrative plan data to be used, personal information non-identifying floating population/call volume data provided from mobile communication companies, and personal information non-identifying card sales information provided from credit card companies may be included.

The unstructured data 11b may include real estate internet articles searchable by a search engine.

Utilizing real estate internet articles among the unstructured data 11b in the server 100 for providing land excavation and value analysis services according to an embodiment of the present invention is that news articles are information that the public should be interested in or should inform the public. This is because, as an expression of text, it can be said to be refined information about the explanation of various phenomena occurring in the real world and what changes will occur and proceed in the future in relation to politics, economy, society, and business in the future. Among them, articles uploaded on the Internet can be said to be reliable and important information among numerous information.

The reason why the unstructured data 11b, such as news articles, is considered together with the structured data 11a when analyzing the land value is because human psychological attitude can act as an important factor in real estate market changes, and only the structured data 11a This is because a more reliable land value analysis can be performed compared to the case where land value analysis is performed using

A structure of the database unit 110 according to an embodiment of the present invention will be described with reference to FIG. 4 . 4 is a schematic diagram illustrating a unit area data structure 111 according to an embodiment of the present invention.

The database unit 110 for land value analysis according to the present embodiment divides land space into unit areas based on latitude and longitude and includes time-series data corresponding to each unit area. For example, unit cells are divided for the entire Republic of Korea, i.e., Far East, Far West, Far South, and Far North, or South Korea, that is, Far East Road 131° 52′), Far West 125° 04′), Far North, and Far South. Unit cells can be classified as targets.

Meanwhile, the unit cell can be formed in various sizes. For example, it is possible to set each region by 25m × 25m, and it is also possible to set it using a longitude and latitude coordinate system. That is, when the longitude and latitude coordinate system is calculated in degrees, minutes and seconds, 1 second in longitude is about 25 m, and 1 second in latitude is about 30 m. It is also possible

In the case of dividing South Korea into unit cells in units of 25 m × 25 m, the area of South Korea is about 99,720 km2, so dividing this by 625 m2, which is the area of unit cells, gives 159,552,000 unit cells.

Specifically, as shown in FIG. 4 , the database unit 110 according to the present invention has a form including unit cell records 1112 in which unit cells of the land to be surveyed are time-series separated. For example, when South Korea is a management area, it is divided into about 160 million unit areas based on latitude and longitude, and a unit area data structure 111 for each unit area is constructed. Each unit area data structure 111 includes a header 1111 and unit cell records 1112 in which time-series data is stored.

Specifically, the unit area data structure 111 stores land value analysis data of a specific unit area based on latitude and longitude. In this case, the unit area data structure 111 is divided into a header 1111 and unit cell records 1112 divided in time series.

The header 1111 stores geographical identification information for each unit area and basic analysis data for future land value analysis or simulation, and in each unit cell record 1112, the fixed value analysis item 700 of the unit area. Alternatively, time-specific data for the atypical value analysis items 800 may be stored.

In the header 1111 of the unit area data structure 111, data for identification of a region and data for analysis of land value in the region are stored.

As data for regional identification, the 13-digit PNU unique number assignment rule is followed, but the last 8 digits are assigned a serial number for each administrative dong. This is to perform location-based analysis, not cadastral-based analysis.

The basic data for the land value analysis of the unit area stored in the header 1111 of the unit area data structure 111 may include the following contents. However, the basic data for the land value analysis of such a unit area may be calculated and stored in the system for building the database unit 110 in the database unit 110 construction and updating steps of each unit area record, but a simulation is performed later. It is also possible to calculate and utilize it in real time in a separate device for this purpose.

The basic data for the analysis of the unit area includes the value type. The growth type includes a fixed value level type (21) and a fixed value level driven type (22), and the calculated probabilities for them, that is, a fixed value level type probability (23) and a fixed value level driven type probability (24), etc. Basic analysis Data may be stored.

The fixed value level type 21 may be divided into a value growth type, a value stability type, and a value decline type. For example, as a relative evaluation method, the value growth type is a classification concept dealt with in the general urban planning field. It divides each variable in three categories, namely, [population, industry, administration] sector, and refers to the annual average growth rate of these first factors ( 320) If the average annual growth rate for the past five years in the [Population, Industry, and Administration] sector is about the top 20% of the total management area, it can be judged as a value growth type, or as an absolute evaluation method, three categories: population, industry, If the average annual growth rate of the administration for the last five years is higher than a predetermined increase rate based on the growth rate of the entire management area, it can be judged as a value growth type.

Population can be calculated by synthesizing the average annual growth rate of each of the floating population, resident population, full-time population, and visiting population, etc. . Administrative support is a matter related to the installation of infrastructure such as roads and parks, and the increase/decrease rate of administrative support matters compared to other analysis units is calculated.

In addition, it is also possible to simply judge through the independent variable 310 called [whether or not infrastructure is installed and changes in population]. It is possible to analyze the above three categories through the installation of infrastructure and changes in the population.

In a similar way, the value decay type is a relative evaluation method. If the average annual growth rate of each of the three categories of variables, i.e., population, industry, and administration, is less than or equal to the bottom 20% over the last five years, it can be judged as a value decline type, and also absolute evaluation. As a method, if the average annual growth rate of the three categories, ie, population, industry, and administration, for the past five years is less than a predetermined increase rate based on the growth rate of the entire management area, it is also possible to judge this as a value decline type. The value stabilization type is a case that does not fall under the above value growth type or value decline type.

Meanwhile, the average annual growth rate of each population, industry, and administration is added up to calculate the average value.

The fixed value level driven type 22 refers to a major factor contributing to determining the fixed value level type 21 . For example, the average annual growth rate of each population, industry, and administration is summed to calculate an average value, and when the fixed value level type 21 is determined based on the calculated average value, the fixed value level type 21 at this time is In the case of the value growth type, the factor with the highest average annual growth rate among the average annual growth rates of population, industry, and administration is the standard value level-driven type (22). A factor having an increase rate becomes the fixed value level driven type (22). In the case of the value stability type, the item with the smallest difference from the average value may be selected as the fixed value level driven type 22 .

The land value level type probability uses the average value of each factor as well as the calculated standard deviation value and/or the difference between the factor having the lowest value and the average value. For example, the probability for the fixed value level type 21 of the value growth type can be such that a value inversely proportional to it is calculated using only the standard deviation value, and the difference between the standard deviation value and the average value of the factors having the lowest value It is also possible to calculate a probability value that is inversely proportional to each weight. In the case of the decay type, only the standard deviation value is used, or the difference between the standard deviation value and the highest factor and the average value is weighted and summed, and then a value inversely proportional to this is calculated and reflected in the probability.

The fixed value level driven type probability 24 can also be calculated in a similar way. That is, the probability value may be calculated so as to be inversely proportional to the difference between the item selected as the fixed value level driven type 22 and the average value.

As the data storage method of the fixed value level type 21, it is also possible to store only the code corresponding to the specific fixed value level type 21, but it is better to store the probabilities calculated for each fixed value level type 21 together. desirable.

In addition, as the fixed value level driven type 22 data storage method, it is possible to store a code corresponding to a specific fixed value level driven type 22, but the probabilities calculated for each fixed value level driven type 22 are stored. It is preferable to do

The value type included in the basic data for analysis of the unit area may further include an atypical value level type 25 .

The atypical value level type 25 may be divided into a value increase type, a value maintenance type, and a value decrease type. For example, the atypical value level type 25 may be determined according to the polarity value 410 calculated by the service providing unit 130 . The polarity value 410 is a criterion for determining whether the Internet article for each unit area is positive or negative in relation to the land value. If the polarity value 410 is a positive number, the land value is positive in the Internet article for the unit area. If the polarity value 410 is 0, the land value is also positive in the Internet article for the unit area. It is not a negative case, and when the polarity value 410 is negative, it corresponds to a case where the land value appears negatively in the Internet article for the unit area.

The polarity value 410 is an average value of the basic polarity value 400 corresponding to the expression included in the Internet article for the unit area, and if the polarity value 410 for the unit area is 0.5 or more, the atypical value level type ( 25) becomes a value increase type, and when the polarity value 410 for the unit area is -0.5 or more and less than 0.5, it becomes a value maintenance type, and when the polarity value 410 for the unit area is less than -0.5, the value decreases. can be your brother

The basic polarity value 400 may be determined by the expressions included in the Internet article and the atypical value analysis item 800 .

As the data storage method of the atypical value level type 25, it is also possible to store only the code corresponding to the specific atypical value level type 25, but the polarity values 410 calculated for each atypical value level type 25 are It is preferable to store the average value together.

The derivation or calculation of basic information using the fixed value analysis item 700 or the atypical value analysis item 800 as described above may be implemented in the database unit 110 itself described above, and in the big data construction unit 120, the database It may be performed to build the database unit 110 at the request of the unit 110 or may be performed to provide information necessary for simulation in real time at the request of a server for providing land excavation and value analysis services.

In the unit cell records 1112 divided in time series, the fixed value analysis item 700 or the atypical value analysis item 800 corresponding to each unit area is stored in units of a predetermined period. On the other hand, factors and survey items required for land value analysis should be distinguished. For example, in natural factors, elevation and slope are necessary factors for land value analysis, but geology and soil data cannot be regarded as essential factors for land value analysis.

The standard value analysis items 700 can be selected based on 14 major items and 83 detailed items presented in Annex Table 1 of the urban master plan establishment guidelines. can be, as described in Tables 1 to 3 below.

<Table 1>

<Table 2>

<Table 3>

A method of mapping the fixed value analysis item 700 to each unit cell record 1112 provided in time series among the unit area data structures 111 is as follows.

First, a subject map is prepared to secure data to be stored in each unit cell record 1112 . Most of the thematic maps can be obtained from the national spatial information portal, and thematic maps such as the continuous cadastral map, the building status database unit 110, and the urban planning facility status are collected from the national spatial information portal.

Thematic maps are divided into coordinate-based thematic maps and non-coordinate-based thematic maps. Coordinate-based thematic maps include data based on specific unit areas, such as continuous cadastral maps and building status, and non-coordinate-based thematic maps include financial independence and revenue and expenditure. The non-coordinate-based data means general information of the local government, such as the degree of financial independence, and is stored in the unit cell record 1112 corresponding to the administrative district because it is not information based on specific coordinates. For subject maps that are not provided with analysis drawings such as elevation, slope, etc., analysis is performed based on the longitude and latitude coordinate-based cells.

For non-coordinate-based data such as fiscal independence and the current state of revenue and expenditure, data from local governments are obtained and coordinate-based thematic maps are prepared. By combining 60 thematic maps such as continuous cadastral map, building status, urban planning facility status, and financial independence degree by unit period to each unit area data structure 111 divided based on longitude and latitude coordinates, mapping of fixed value analysis items 700 is completed. . At this time, when there is a plurality of data in the same year in the same unit cell record 1112, an average value is calculated to simplify the data.

The atypical value analysis item 800 can be selected based on 3 major items, 19 detailed items, and 71 expressions. to as described in Table 6.

<Table 4>

<Table 5>

<Table 6>

Next, a method of mapping the atypical value analysis item 800 to each unit cell record 1112 provided in time series among the unit area data structures 111 is as follows.

In the first step, the big data building unit 120 collects and indexes unstructured data 11b including Internet news about real estate by web crawling from the external data providing server 10 . The collected internet news data can be classified by region, date, media, news type, etc.

The second step is emotional analysis by deriving lexical and semantic features of real estate internet news contents through morpheme analysis (Part-of-SpeechTagging) and dependency parsing, which are a series of language processing processes. Normalize to a form that is easy to For example, if the collected Internet articles contain the expression “price will rise”, the expression “price will rise” is “price”, “this”, “will increase”, and “.” can be analyzed.

The third step is to tag the basic polarity value 400 in each sentence based on the atypical value analysis item 800 . In the analyzed “price”, “this”, “will go up”, and “.”, “price” coincides with “price”, which is a detailed item of the atypical value analysis item 800, and “will go up” in the atypical value analysis Since it coincides with the expression “will go up” of the item 800, the expression “price will go up” of the corresponding Internet article may have a basic polarity value 400 of 1 can be calculated.

The fourth step divides the positive and negative basic polarity values 400 of real estate news by period and region by indexed real estate information, and calculates a polarity value 410 that can be utilized in real estate activities in various forms. For example, the basic polarity value 400 calculated according to the expression included in the Internet article is divided by period and region, and the average value of the sum of the basic polarity values 400 for each divided period and region is the polarity value ( 410) can be calculated.

5 is a conceptual diagram illustrating the big data construction unit 120 according to an embodiment of the present invention, and FIG. 6 is a conceptual diagram illustrating the service providing unit 130 according to an embodiment of the present invention. 5 and 6, the configuration of the big data building unit 120 and the service providing unit 130 according to an embodiment of the present invention and a method of simulating the future land value for at least one or more of the unit areas about it.

The land excavation and value analysis service providing server 100 according to the present embodiment receives a request from at least one of the big data building unit 120 and the service providing unit 130 and divides the management area into a unit area based on latitude and longitude. It may be an analysis server or system that analyzes the unit region data structure 111 defined as a set of time-series data provided for each.

The big data construction unit 120 according to the present embodiment builds the database unit 110 having the above-described characteristics. As described above, the land value systems according to the present invention can be implemented in various ways.

The database unit 110 for land value analysis according to the present embodiment may relate to a server or system for building and storing basic data used to simulate the value of a specific land in the service providing unit 130 .

As described above, the database unit 110 for land value analysis includes a unit area data structure 111 in which time series data is stored for each unit area partitioned based on latitude and longitude of the management area.

The big data building unit 120 receives data for land value analysis from the external data providing server 10 , and analyzes the transmitted data to build the database unit 110 . At this time, the big data construction unit 120 includes a data collection unit 121 , a data extraction unit 122 , a value item mapping unit 123 , and a basic item analysis unit 124 .

The data collection means 121 collects external data 11 including structured data 11a and unstructured data 11b required for land value analysis by using web crawling from the external data providing server 10 . The data extraction means 122 extracts the data for each period of the fixed value analysis items 700 or the atypical value analysis items 800 for the unit area from the collected external data 11, and the value item mapping means 123 ) is a structured item mapping means 1231 for mapping the data for each period of the fixed value analysis items 700 for the unit area extracted by the structured item extraction means 1221 to the database unit 110, 1231 and It includes an atypical item mapping unit 1232 for mapping the data for each period of the atypical value analysis items 800 for the unit area extracted by the atypical item extraction unit 1222 to the database unit 110 . .

The basic item analysis means 124 maps geographic identification information for each unit area and basic information for land value analysis for the unit area for each unit area data structure 111 .

At this time, as described above, each unit area data structure 111 includes a header 1111 in which geographic identification information for each unit area, basic information for land value analysis for the unit area is stored, and a value for the unit area. It includes a plurality of unit cell records 1112 in which data for each time period for analysis items is stored.

The basic item analysis means 124 utilizes the structured data 11a to determine the fixed value level type 21 calculated as a measure of land value increase, and the fixed value level calculated with respect to the main factors of the fixed value level type 21 . Basic information for the analysis of the land value of at least one of the initiative types 22 is stored in the header 1111 . At this time, the fixed value level type 21 includes at least one of a value growth type, a value stability type, and a value decay type, and the fixed value level driven type 22 is one of the factors related to the determination of the fixed value level type 21 . can be determined as a major factor.

In addition, the basic item analysis means 124 uses the unstructured data 11b to provide basic information for land value analysis including the unstructured value level type 25 calculated as a measure of land value increase in the header 1111. You can save more. In this case, the atypical value level type 25 may include at least one of a value increase type, a value maintenance type, and a value decrease type.

The method for determining the fixed value level type 21, the fixed value level driven type 22, and the atypical value level type 25 has been described above, and thus will be omitted.

That is, the server 100 for providing land excavation and value analysis service according to the present embodiment calculates geographic identification information for each unit area for each unit area data structure 111 and basic information for land value analysis for the unit area. It includes a basic item analysis means (124). At this time, as described above, the fixed value analysis item 700 includes natural environment, humanities environment, land use, population, housing, economy, transportation facilities, distribution/supply facilities, public/cultural and sports facilities, spatial facilities, environmental basic facilities, It may include at least one major item of health and sanitation facilities, disaster prevention facilities, and finance and detailed items belonging thereto.

In addition, as shown in Tables 4 to 6, the atypical value analysis item 800 may include at least one major item among price, policy, and state, and includes tax, successful bid price, jeonse price, sale price, house price, jeonse price, Price, regulation, qualification, requirement, auction, demand, investment, for sale, redevelopment, reconstruction, loan, transaction, may include at least one detailed item of the sale.

The basic item analysis means 124 is a fixed level type calculation means ( 1241), and a structured level-driven type calculating means 1242 for calculating a fixed-value level-led type 22 related to a major factor of a growth level.

Through this analysis, the land excavation and value analysis service providing server 100 assists the construction of the database unit of the big data construction unit 120 for land value analysis, or provides the service providing unit 130 with basic information necessary for analysis. By providing a simulation service, it is possible.

Referring to FIG. 6 , the service providing unit 130 according to the present embodiment is connected to the big data construction unit 120 for land value analysis as described above, and the management area for each unit area partitioned based on latitude and longitude. A header 1111 in which geographic identification information for each unit area and basic information for land value analysis for the unit area are stored, and data for each period of value analysis items for the unit area corresponding to the header 1111 A land value analysis service may be provided by using the database unit 110 having the unit area data structure 111 to be stored.

The service providing unit 130 according to the present invention includes a basic score calculation unit 131, a comprehensive score calculation unit 132, a final score calculation unit 133, a trend value calculation unit 134, a formal prediction unit 135, It may include a polarity value calculation means 136 , atypical prediction means 137 , a specific reliability calculation means 138 , a section reliability calculation means 139 , and a value prediction means 140 .

The basic score calculation means 131 receives the basic information necessary for analysis stored in the database unit and calculates the city value focal point 1311 for the simulation target site. The basic score calculation means 131 uses the basic factors that are divided into accessibility, location, and target location to obtain an accessibility score 1312, a location score 1313, and a city value basic score 1311 including the target point 1314. Calculate.

The accessibility score 1312 is calculated according to highway IC accessibility with the target site, public transportation accessibility, city hall location accessibility, and main national road accessibility, and the location score 1313 is the degree of development around the target site, preference or non-preferred facilities. It is calculated according to existence and urbanization ratio, and the number of target points 1314 is calculated by using environmental factors including the slope of the target site, ecological naturalness, and land environment evaluation map.

The comprehensive score calculation means 132 calculates the city value composite score 1321 by reflecting the weight according to the development type to the city value focus score 1311 . The development type is any one of the residential, commercial, and industrial, and the weight ranges from -2.0 to 2.0. That is, the comprehensive city value score 1321 calculated by the comprehensive score calculation means 132 reflects the weight in the accessibility score 1312, and the overall accessibility score 1322, which is calculated by reflecting the weight in the location score 1313. It includes the calculated location comprehensive score 1323, and the land intelligence composite score calculated by reflecting the weight in the land property score.

The final score calculation means 133 is a final value score (1331) defined as the average value of the comprehensive accessibility score 1322, the location location score 1323, and the target location score 1324 included in the city value composite score 1321. to calculate

In addition, the service providing unit may use the final value score 1331 and the current actual transaction price for the simulation target site to calculate and provide the value before and after development of the simulation target site.

The trend value calculating means 134 calculates a trend value 300 to be applied to at least one unit area selected as a simulation target among the unit areas. At this time, the trend value 300 is an independent variable ( 310) is calculated as the change value of the dependent variable 340 for each distance from the source of the independent variable 310 with respect to the amount of change in the past certain period. The cause of the independent variable 310 means a specific unit area where changes in infrastructure and population occur.

The formal prediction means 135 performs a simulation for each distance from the source of the independent variable 310 in at least one unit area selected as the simulation target by using the calculated trend value 300 to calculate the amount of change for the future. .

In addition, the service providing unit 130 according to the present embodiment may also include the functions of the land excavation and value analysis server.

The trend value calculating means 134 may calculate the trend value 300 by setting the distance range of 400 m to 600 m from the source of the independent variable 310 as the maximum range. Preferably, the trend value 300 is calculated with a maximum range of about 500 m, which is a living area.

At this time, the trend value calculating means 134 divides the sphere of influence of the independent variable 310 into a plurality of step-by-step influence spheres having a trend value 300 that is inversely proportional to the radius from the source of the independent variable 310 . In addition, the trend value calculating means 134 may limit the calculation of the trend value 300 according to the mutual influence between the independent variables 310 to one to three loop calculations.

In addition, when the trend value calculation means 134 is impossible to calculate the trend value 300 from the simulation target site, or the amount of change in the independent variable 310 value during the past predetermined period of the simulation target site fluctuates by more than a certain standard, the simulation target Any one of a plurality of other unit regions and base years in which at least two items of the spirit value level type, the fixed value level type probability (23), the fixed value level driven type (22), and the fixed value level driven type probability (24) are similar can be selected to calculate the trend value 300 from the region at the time.

The formal prediction means 135 assumes a change in the independent variable 310 of the simulation target using the calculated trend value 300 and calculates the amount of change in the dependent variable 340 according to the change in the independent variable 310. Calculate. The calculated change amount of the dependent variable 340 is provided to the user together with the probability for the independent variable 310 , that is, the probability for the fixed value level type 21 and the fixed value level driven type 22 .

The polarity value calculating means 136 may calculate a polarity value 410 to be applied to at least one unit region selected as a simulation target. As described above, the polarity value 410 may be calculated as an average value of the basic polarity value 400 corresponding to the expression included in the Internet article about the simulation target site collected for a certain period of time.

In addition, the atypical value level type 25 may be determined according to the polarity value 410 calculated by the polarity value calculating means 136 .

If the past accumulated data of the target site has not been accumulated for more than a certain period of time, the polarity value calculating means 136 determines the fixed value level type 21, the fixed value level type probability 23, the fixed value level driven type of the simulation target site ( 22) and the polarity value 410 of the target site by selecting any one of a plurality of other unit regions and the reference year in which at least two or more items are similar among the fixed value level-led type probability 24 and the polarity value 410 of the region at the time ) can be calculated. This is at least two or more of the fixed value level type (21), the fixed value level type probability (23), the fixed value level driven type (22), and the fixed value level driven type probability (24) analyzed using the structured data 11a If the items are similar, the polarity value 410 of the target site is calculated on the premise that the land value will be similar. Through this, it is possible to perform land value analysis using the unstructured data 11b even for areas that are not often covered in Internet articles such as rural areas.

In analyzing the value of a specific land using the unstructured data 11b including Internet news articles, the polarity value 410 derived by analyzing the unstructured data 11b to increase the reliability of the land value analysis is a specific land In some cases, there is no correlation with the present or near-future value of That is, in the case of a small house or real estate, which is mainly interested in young people who frequently access Internet news, the polarity value 410 of analyzing Internet news articles has some correlation in analyzing the land value, but through Internet news In the case of rural, regional, or medium-large or large real estate, which is difficult to obtain information or the elderly who are not familiar with are mainly interested in, the polarity value 410 that analyzed Internet news articles is not related to the analysis of land value. can occur Therefore, in analyzing the land value using the unstructured data 11b, it is possible to improve the reliability of the land value analysis by calculating the reliability at a specific period and reflecting it in the land value analysis. To this end, the service providing unit 130 of the present invention is provided with a specific reliability 1381 calculation means and a section reliability 1381 calculation means.

The specific reliability calculation means 138 compares the actual real estate transaction price information of the simulation target area with the real real estate transaction price information at the reference point after a specific period and the atypical value level type 25 to determine the specific reliability 1381 can be calculated.

The value of the specific credibility 1381 calculated by the specific credibility calculation means 138 is the atypical value level type 25 is a value-increasing type, and the actual real estate transaction price of the simulation target area after a specific period is the standard. It may be 1 if it is increased compared to the actual transaction price, and the atypical value level type 25 is a value increase type. If maintained, it may be 0, and if the atypical value level type 25 is a value increase type, and the actual real estate transaction price of the simulation target area after a specific period is lowered compared to the actual real estate transaction price at the time of reference - can be 1.

In addition, as for the specific reliability 1381 value calculated by the specific reliability calculation means 138, the atypical value level type 25 is a value maintenance type, and the actual real estate transaction price of the simulation target after a specific period is the standard If it rises compared to the actual real estate transaction price at the time, it may be 0, the atypical value level type 25 is a value maintenance type, and the actual real estate transaction price at the time when the actual real estate transaction price of the simulation target after a specific period becomes the standard It may be 1 if maintained compared with In this case, it can be 0.

In addition, as for the specific reliability 1381 value calculated by the specific reliability calculation means 138, the atypical value level type 25 is a depreciation type, and the actual real estate transaction price of the simulation target after a specific period is the standard. It may be -1 if it rises compared to the actual real estate transaction price at the time it becomes, the atypical value level type 25 is a declining type, and the actual real estate transaction price of the simulated site after a specific period becomes the standard. It may be 0 if maintained compared with the real real estate transaction price, the atypical value level type 25 is a declining value, and the real real estate transaction price at the time when the actual real estate transaction price of the simulated site after a specific period becomes the standard It may be 1 if it is lowered compared to .

The section reliability calculation means 139 may calculate the section reliability 1381 defined as an average value of the specific reliability 1381 for a specific period.

The atypical prediction means 137 uses the polarity value 410 calculated by the polarity value calculating means 136 and the section reliability 1381 in at least one unit region selected as the simulation target. The polarity value 410 It is possible to calculate the atypical value predicted value 500 for the future by performing a simulation for each distance from the source of . At this time, when the section reliability 1381 is positive, the atypical prediction means 137 reflects the section reliability 1381 when calculating the atypical value predicted value 500 for the simulation target site, and the section reliability 1381 When is 0 or a negative number, the section reliability 1381 may not be reflected when calculating the atypical value predicted value 500 for the simulation target site.

As for the atypical value predicted value 500 calculated by the atypical prediction means 137, the section reliability 1381 calculated by the section reliability calculation means 139 is a positive number, and the atypical value level type 25 is a value-increasing type It can be increased, and when the atypical reliability calculated by the reliability calculation means is positive and the atypical value level type 25 is a value maintenance type, the atypical value predicted value 500 calculated can be maintained, and the If the atypical reliability calculated by the reliability calculation means is positive and the atypical value level type 25 is a declining value, the calculated atypical value predicted value 500 may be decreased, and the section reliability calculation means 139 When the calculated interval reliability 1381 is 0 or a negative number, the atypical predicted value may not be reflected.

The unstructured data 11b that derives a meaningful result value for the land value analysis according to the specific reliability 1381 and the section reliability 1381 is utilized, and the unstructured data 11b that is not is utilized is not utilized. It can improve reliability.

The value prediction means 140 may calculate the future value of the unit area. The value prediction means 140 is a value growth type, a value growth certain type, a value growth potential type, a value growth prediction type, a value stability type, and a value stability using the fixed value level type 21 and the atypical value prediction value 500 . It is possible to calculate the value predicted value 600 having any one of a certain type, a value decline expected type, a value decay type, a value decay likely type, and a value decay certain type.

The value predicted value 600 calculated by the value prediction means 140 may be a value growth type when the fixed value level type 21 is a value growth type and the atypical value prediction value 500 is not reflected. When the level type 21 is a value growth type and the atypical value predicted value 500 is rising, it may be a value growth certain type, and the fixed value level type 21 is a value growth type and the atypical value predicted value 500 is maintained In this case, it may be a value growth potential type, and when the fixed value level type 21 is a value growth type and the atypical value predicted value 500 is declining, it may be a value growth expected type.

In addition, the value predicted value 600 calculated by the value prediction means 140 is a value stable type when the fixed value level type 21 is a value stable type and the atypical value predicted value 500 is not reflected, and the fixed value When the level type 21 is a value stable type and the atypical value predicted value 500 is rising, it is a value growth expected type. It is a value stability certain type, and when the fixed value level type 21 is a value stable type and the atypical value predicted value 500 is falling, it may be a stable expected type.

In addition, the value predicted value 600 calculated by the value prediction means 140 is a value decay type when the fixed value level type 21 is a value decay type and the atypical value predicted value 500 is not reflected. When the fixed value level type 21 is a value decay type and the atypical value predicted value 500 is rising, it becomes a value decline expected type, and the fixed value level type 21 is a value decline type and the atypical value predicted value 500 is In the case of maintenance, it may be a likely value decay type, and if the fixed value level type 21 is a value decay type and the atypical value predicted value 500 is falling, it may be a value decay certain type.

At this time, if the value predicted value 600 is a value growth type, a value growth certain type, or a value growth potential type, the value of the simulation target is expected to increase in the near future, and the value predicted value 600 is a value stable type and value stability certain type In the case of the type and stability prediction type, the value of the simulation target site is expected to remain unchanged in the near future, and the value predicted value (600) is a value decline type, value decline expected type, value decline potential type, and value decline certain type represents the expected decline in the value of the simulated site in the near future.

That is, finally, the value prediction means 140 can analyze and predict the value of a specific land by comprehensively using the structured data 11a and the unstructured data 11b. Through this, in analyzing the value of land, not only the structured data 11a but also the unstructured data 11b are used together, thereby improving the reliability of the analysis and the analysis of the expected land value.

Although preferred embodiments of the present invention have been described above, the technical spirit of the present invention is not limited to the above-described preferred embodiments, and may be variously implemented within the scope not departing from the technical spirit of the present invention embodied in the claims. have.

10: External data providing server
100: Server for providing land excavation and value analysis service
110: database unit
120: Big Data Construction Department
130: service provider

Claims (17)

In the land excavation and value analysis service providing server 100 that receives external data 11 necessary for land value analysis from the external data providing server 10 and calculates the value of a specific land based on the external data 11,
a database unit 110 having at least one unit area data structure 111 storing time-series data corresponding to each of at least one unit area partitioned based on latitude and longitude of the management area;
a big data construction unit 120 for constructing the database unit 110 by analyzing the external data 11;
a service providing unit 130 that receives basic data for land value analysis from the big data construction unit 120 and provides a land value analysis service for at least one simulation target site; and,
and an input unit 150 for receiving the simulation target land, which is the land to be evaluated,
The external data 11 is
Structured data such as highway IC, location data of public transport stops and city halls, auction real estate information provided by public data portals, spatial big data and real estate transaction information provided by the Ministry of Land, Infrastructure and Transport, information provided by central and local governments Administrative plan data, personal information non-identifying floating population/call volume data provided by mobile carriers, and personal information non-identifying card sales information provided by credit card companies,
The service providing unit 130,
Calculate the value before and after development of the simulation target site by using the external data 11,
The external data 11 further includes unstructured data 11b for the management area,
The unstructured data 11b includes real estate internet articles related to the management area searchable by a search engine,
Each of the at least one unit area data structure 111 includes: a header 1111 in which geographic identification information for each of the unit areas and basic information for land value analysis for the unit area are stored; and a plurality of unit cell records 1112 in which data for each time period for land value analysis items for the unit area are stored;
The big data construction unit 120,
data collection means (121) for collecting the external data (11);
a data extraction means (122) for extracting time-specific data on land value analysis items for at least one or more of the unit areas from the external data (11) collected by the data collection means (121);
a value item mapping means (123) for mapping the data for each period of the value analysis items for the unit area extracted by the data extraction means (122) to the database unit (110); and,
Basic item analysis means 124 for calculating geographic identification information for each unit area and basic information for land value analysis for the unit area for each unit area data structure 111;
The service providing unit 130,
a basic score calculation means 131 for calculating a city value focal point 1311 by using the external data;
a comprehensive score calculation means 132 for calculating a city value composite score 1321 by reflecting a weight on the city value focus score 1311; and
and a final score calculation means 133 for calculating a final value score 1331 by using the city value composite score 1321;
A land excavation and value analysis service providing server that calculates and provides the value before and after development of the simulation target by using the final value score 1331 and the current actual transaction price for the simulation target. delete delete delete According to claim 1,
The urban value focus score (1311) includes an accessibility score (1312), a location score (1313), and a target point score (1314) using basic factors that are divided into accessibility, location, and target location,
The city value composite score 1321 is calculated by reflecting the weight by the development type in the city value focus score 1311, and the city value composite score 1321 is calculated,
The development type is any one of residential, commercial, and industrial, and the weight has a range of -2.0 to 2.0,
The city value composite score 1321 is an accessibility composite score 1322 calculated by reflecting a weight in the accessibility score 1312, a location composite score 1323 calculated by reflecting a weight in the location score 1313, the Including the total intelligence score calculated by reflecting the weight in the target point number 1314,
The accessibility score 1312 is calculated according to the accessibility of the highway IC with the simulation target, the accessibility of public transportation, the accessibility of the city hall, and the accessibility of major national roads,
The location score 1313 is calculated according to the degree of development around the simulation target site, the presence of preferred or non-preferred facilities, and the urbanization rate,
The number of target points 1314 is calculated by using environmental factors including the slope of the simulation target site, ecological naturalness, and land environment evaluation map,
The final value score 1331 is a land excavation and value analysis service defined as the average value of the comprehensive accessibility score 1322, the comprehensive location score 1323, and the target site score 1324 included in the city value composite score 1321 serving server. 6. The method of claim 5,
The service provider,
A trend value 300 to be applied to at least one unit area selected as a simulation target is calculated, wherein the trend value 300 is a first factor 320 defined as [change in infrastructure, change in population] and [population, industry, administration], the change of the dependent variable 340 by distance from the cause of the independent variable 310 with respect to the amount of change of the independent variable 310 of any one of the second factors 330 in the past period a trend value calculating means 134 calculated as a value;
Using the trend value 300 calculated by the trend value calculating means 134, simulation is performed for each distance from the source of the independent variable 310 in at least one unit area selected as the simulation target, and Formal prediction means (135) for calculating the amount of change;
A polarity value 410 to be applied to at least one or more unit areas selected as a simulation target is calculated, wherein the polarity value 410 is a basic polarity value ( polarity value calculating means 136 calculated as the average value of 400; and,
The distance from the source of the polarity value 410 in at least one unit area selected as the simulation target using the polarity value 410 calculated by the polarity value calculating means 136 and the section reliability 1381 A server for providing land excavation and value analysis service further comprising; an atypical prediction means 137 for calculating an atypical value predicted value 500 for the future by performing a simulation for each. 7. The method of claim 6,
The data collection means 121 includes collecting the unstructured data 11b from the external data providing server 10 by web crawling,
The data extraction means 122,
a structured item extraction means 1221 for extracting data for each period of the structured value analysis items 700 for the unit area from the structured data 11a; and
and an unstructured item extraction means 1222 for extracting data for each period of the unstructured value analysis items 800 for the unit area from the unstructured data 11b,
The value item mapping means 123,
a structured item mapping means (1231) for mapping the data for each period of the fixed value analysis items (700) for the unit area extracted by the structured item extraction means (1221) to the database unit (110); and,
Atypical item mapping means 1232 for mapping the data for each period of the atypical value analysis items 800 for the unit area extracted by the atypical item extraction means 1222 to the database unit 110; A server that provides land excavation and value analysis services. 7. The method of claim 6,
The basic item analysis means 124 utilizes the structured data 11a to calculate the fixed value level type 21 calculated as a measure of land value increase and the fixed value level calculated with respect to the main factors of the fixed value level type 21 Basic information for land value analysis of at least one of the initiative types 22 is stored in the header 1111, and the unstructured value level type 25 is calculated as a measure of land value increase by using the unstructured data 11b. ), a land excavation and value analysis service providing server that further stores basic information for land value analysis, including in the header 1111. 9. The method of claim 8,
The fixed value level type 21 includes at least one of a value growth type, a value stability type, and a value decay type, and the fixed value level driven type 22 is one of the factors related to the determination of the fixed value level type 21 . determined as a major factor,
The atypical value level type 25 is a land excavation and value analysis service providing server that is any one of a value increase type, a value maintenance type, and a value decrease type. 9. The method of claim 8,
The atypical value level type (25) is a land excavation and value analysis service providing server that is determined according to the polarity value (410) calculated by the polarity value calculating means (136). 9. The method of claim 8,
The service providing unit 130 is a land excavation and value analysis service providing server further comprising a value prediction means 140 for calculating the future value of the unit area. 9. The method of claim 8,
The service providing unit 130 uses the result of comparing the actual real estate transaction price information of the simulation target area with the real real estate transaction price information at the reference point after a specific period and the atypical value level type 25 to obtain a specific reliability 1381 Land excavation and value analysis service providing server further comprising; specific reliability calculation means (138) to calculate. 7. The method of claim 6,
The trend value calculating means 134 is a fixed value level type 21, a fixed value level type probability 23, a fixed value level leading type of the simulation target site when the past accumulated data of the simulation target site has not been accumulated for more than a certain period of time. (22) and the fixed value level-led type probability (24) of at least two or more items similar to a plurality of other unit areas and base years by selecting any one of the region to calculate the trend value 300 from the region at the time excavation and Value analysis service providing server. 7. The method of claim 6,
The polarity value calculating means 136 is a fixed value level type 21, a fixed value level type probability 23, a fixed value level driven type 22 of the simulation target site when the past accumulated data of the target site has not been accumulated for more than a certain period of time. ) and a land excavation and value analysis that calculates a polarity value (410) from the region at the time by selecting any one of a plurality of other unit regions and the base year having at least two items similar to the fixed value level-led type probability (24) Serving Server. 8. The method of claim 7,
The atypical value analysis item 800 is a land excavation and value analysis service providing server including at least one major item of price, policy, and market. 13. The method of claim 12,
The service providing unit 130 further includes a section reliability calculation means 139 for calculating a section reliability 1381 defined as an average value of the specific reliability 1381 for a specific period. Land excavation and value analysis service providing server. 15. The method of claim 14,
The atypical prediction means 137 reflects the section reliability 1381 when calculating the atypical value predicted value 500 for the simulation target when the section reliability 1381 is a positive number, and the section reliability 1381 is 0 or a negative number, the server for providing a land excavation and value analysis service that does not reflect the section reliability 1381 when calculating the atypical value prediction value 500 for the simulation target site.

Images