Evaluation support system, evaluation support method, and evaluation support program

Abstract

To provide an evaluation support system, an evaluation support method, and an evaluation support program for accurately evaluating a value of an evaluation object.SOLUTION: A support server 20 includes: a control section 21; and a standard district information storage section 23 for recording evaluation information of a standard district. The control section 21 specifies a standard district within a region mesh to which an evaluation object belongs by using the standard district information storage section 23, and identifies local evaluation information regarding a first station for the standard district. The control section 21 identifies area evaluation information regarding a second station included in an area to which the evaluation object belongs. The control section 21 generates a prediction model for predicting value evaluation information from local evaluation information and area evaluation information of the evaluation object, using the local evaluation information and the area evaluation information of the standard district and the value evaluation information of the standard district as teacher information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an appraisal support system, an appraisal support method, and an appraisal support program for supporting land appraisal. [Background technology]

[0002] When determining the price of land, which is one type of real estate price, the actual price, the publicly announced land price, roadside land price, and fixed asset tax assessment value are used. The actual price is the price that is actually established in the market. The actual price is based on the publicly announced land price, but the price is determined based on the individual circumstances of the seller and buyer. The publicly announced land price is the price per square meter assessed based on the Land Price Disclosure Act. This publicly announced land price is published by the Ministry of Land, Infrastructure, Transport and Tourism. The roadside land price is the price announced by the National Tax Agency as the base price for calculating inheritance tax and gift tax on land. The fixed asset tax assessment value is the assessment value that serves as the basis for fixed asset tax calculated by each city, ward, town, and village. The roadside land price and fixed asset tax assessment value are calculated based on the publicly announced land price. In this way, the price of land is formed starting from the publicly announced land price.

[0003] A land valuation calculation device for calculating the land valuation of real estate is also under consideration (see, for example, Patent Document 1). The land valuation calculation device described in this patent document uses latitude and longitude to extract publicly announced land and reference land details that belong to a predetermined range. Next, from the publicly announced land and reference land details, a publicly announced land and reference land detail having the same zoning and distance from the nearest station as the zoning and distance from the nearest station in the collateral property registration data is selected for each property. Furthermore, from the selected publicly announced land and reference land details, a publicly announced land and reference land detail that has the shortest distance between the property and the publicly announced land or reference land is adopted for each property. Then, the land valuation of the property is calculated for each property based on the land unit price in the publicly announced land and reference land details for each property adopted and the assessed area of ​​the property. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2022-131425 Summary of the Invention [Problem to be solved by the invention]

[0005] As described in Patent Document 1, the distance from the nearest station is often used as an evaluation factor in land valuation. However, because there are many different types of stations, it is difficult to accurately evaluate the value of land by only evaluating the distance from the nearest station. [Means for solving the problem]

[0006] The evaluation support system for solving the above problem includes a control unit and a standard land information storage unit for recording evaluation information of a standard land. The control unit uses the standard land information storage unit to identify a standard land in a regional mesh to which an evaluation target belongs, to identify local evaluation information on a first station for the standard land, to identify area evaluation information on a second station included in an area to which the evaluation target belongs, and to generate a prediction model that predicts value evaluation information of the evaluation target from the local evaluation information and the area evaluation information of the evaluation target using the local evaluation information, area evaluation information, and value evaluation information of the standard land as teacher information. Effect of the Invention

[0007] According to the present disclosure, the value of an object to be evaluated can be accurately evaluated. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram of an evaluation support system according to an embodiment. [Diagram 2] FIG. 2 is an explanatory diagram of a hardware configuration of the embodiment. [Diagram 3] FIG. 2 is an explanatory diagram of a processing procedure according to an embodiment. [Figure 4] FIG. 2 is an explanatory diagram of a processing procedure according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] An embodiment of an evaluation support system, an evaluation support method, and an evaluation support program will be described with reference to Figures 1 to 4. In this embodiment, it is assumed that evaluation information (land price) is predicted using evaluation information (land price) of the surroundings of an evaluation target and attribute information of the land. As shown in FIG. 1, the evaluation support system of this embodiment uses a user terminal 10 and a support server 20.

[0010] (Hardware configuration example) FIG. 2 shows an example of the hardware configuration of an information processing device H10 that functions as the user terminal 10, the support server 20, and the like.

[0011] The information processing device H10 includes a communication device H11, an input device H12, a display device H13, a storage device H14, and a processor H 15. Note that this hardware configuration is an example, and the information processing device H10 may include other hardware.

[0012] The communication device H11 is an interface that establishes a communication path with another device and transmits and receives data, and is, for example, a network interface or a wireless interface.

[0013] The input device H12 is a device that accepts input from a user, etc., and is, for example, a mouse, a keyboard, etc. The display device H13 is, for example, a display or a touch panel that displays various information.

[0014] The storage device H14 is a storage device that stores data and various programs for executing various functions of the user terminal 10 and the support server 20. Examples of the storage device H14 include a ROM, a RAM, and a hard disk.

[0015] The processor H15 controls each process in the user terminal 10 and the support server 20 using the programs and data stored in the storage device H14. Examples of the processor H15 include a CPU and an MPU. The processor H15 expands a program stored in a ROM or the like into a RAM and executes various processes corresponding to various processes. For example, when an application program in the user terminal 10 or the support server 20 is started, the processor H15 operates a process that executes each process described below.

[0016] The processor H15 is not limited to a processor that performs software processing for all of the processes it executes. For example, the processor H15 may be provided with a dedicated hardware circuit that performs hardware processing for at least a part of the processes it executes. That is, the processor H15 may be configured as follows.

[0017] (1) One or more processors operating according to a computer program (software) (2) One or more dedicated hardware circuits that perform at least some of the processes; or (3) A circuit that includes a combination of these. The processor includes a CPU and memory, such as RAM and ROM, that stores program codes or instructions configured to cause the CPU to execute processes. Memory, i.e., computer-readable media, includes any available media that can be accessed by a general-purpose or special-purpose computer.

[0018] (Functions of each information processing device) The functions of the user terminal 10 and the support server 20 will be described with reference to FIG. The user terminal 10 is a computer terminal used by a user who uses this system.

[0019] The support server 20 is a computer system that generates evaluation information for an evaluation target. The support server 20 includes a control unit 21, a map information storage unit 22, a standard land information storage unit 23, a route information storage unit 24, a teacher information storage unit 25, and a learning result storage unit 26.

[0020] The control unit 21 performs processes (including an acquisition stage, a learning stage, a prediction stage, etc.) described below. By executing an evaluation support program for this purpose, the control unit 21 functions as an acquisition unit 210, a learning unit 211, a prediction unit 212, etc.

[0021] The acquisition unit 210 executes a process of acquiring evaluation target information and information related to the reference land from the user terminal 10. The learning unit 211 generates teacher information and executes a process of generating a land price prediction model for predicting the land price of the evaluation target. The prediction unit 212 executes a process for predicting the land price of the evaluation target.

[0022] The map information storage unit 22 stores a map for identifying the area in which the evaluation target is located. In this map, addresses, railway stations, regional divisions, and the range of local governments (prefectures) are recorded in relation to longitude and latitude (World Geodetic System). Here, two, three, seven, etc., divisions can be used as regional divisions.

[0023] Standard land management data on standard land for which the publicly announced land price is published is recorded in the standard land information storage unit 23. This standard land management data records information on the standard land ID, the publicly announced land price, and the location.

[0024] The reference site ID is an identifier for identifying each reference site. The official land price is the land price (land price per square meter) published for this standard land. In this embodiment, the official land price is used as the standard land value evaluation information. The location is the address, longitude and latitude of this standard location.

[0025] The route information storage unit 24 stores information about a route map connecting each station. In addition, attribute information for each station is stored. In this embodiment, the attribute information includes the number of passengers boarding and alighting (station usage), information about representative stations in regional divisions, and the like. By using this attribute information, it is possible to identify major stations in a wide area or region.

[0026] The teacher information storage unit 25 records teacher information used for learning. This teacher information is recorded when a teacher information creation process is performed. The teacher information records a data set that combines the officially announced land price (valuation information) with explanatory variables that explain this officially announced land price. In this embodiment, as described below, multiple pieces of access information up to the first station (nearest station) and the second station (wide area main station, regional main station) are used as explanatory variables. This access information is an index that indicates ease of access.

[0027] A land price prediction model for predicting land prices from attribute information of an evaluation target is recorded in the learning result storage unit 26. This land price prediction model is recorded after the execution of a learning process.

[0028] (Land price forecast processing) Next, the land price prediction process will be described with reference to FIG. Here, the control unit 21 of the support server 20 executes a process of identifying the evaluation target (step S11). Specifically, the acquisition unit 210 of the control unit 21 acquires location information (latitude and longitude) related to the evaluation target from the user terminal 10.

[0029] Next, the control unit 21 of the support server 20 executes a process of identifying the regional mesh of the evaluation target (step S12). Specifically, the acquisition unit 210 of the control unit 21 identifies a regional mesh of a predetermined size with the position information of the evaluation target as the center. Here, the regional mesh is a region divided into mesh areas without gaps based on latitude and longitude, and statistical data on each area is compiled. This regional mesh is used as basic materials for planning and drafting administrative measures such as formulation of urban comprehensive plans and disaster prevention plans, and for formulating store opening plans. The regional mesh sections are classified into 1st to 3rd mesh sections and 1 / 10 fine mesh sections using latitude and longitude, and are numbered with numbers called regional mesh codes. Here, the 1st mesh section is a section divided vertically and horizontally by the meridians of each degree, the even latitudes, and the latitudes that divide the intervals into thirds, based on 100 degrees east longitude and 0 degrees north latitude. A secondary mesh division is an area created by dividing a primary mesh division into eight equal parts in the latitude and meridian directions. A tertiary mesh division is called a regional mesh, and is an area created by dividing a secondary mesh division into ten equal parts in the latitude and meridian directions. A 1 / 10 fine mesh division is an area created by dividing a tertiary mesh division into ten equal parts in the latitude and meridian directions.

[0030] Next, the control unit 21 of the support server 20 executes a process of identifying a target number of standard sites (step S13). Specifically, the acquisition unit 210 of the control unit 21 counts the number of standard sites included in the regional mesh (distribution of standard sites) using the standard site information storage unit 23. If the number of standard sites included in the regional mesh is less than a predetermined target number, the acquisition unit 210 expands the regional mesh outward from the position information of the evaluation target at the center until the number of standard sites included in the regional mesh reaches the target number. Then, the standard sites included in the regional mesh are identified as standard sites to be used for teacher information.

[0031] On the other hand, if the number of standard sites included in the regional mesh is equal to or greater than the target number, the acquisition unit 210 identifies the target number of standard sites in the regional mesh in order of proximity to the evaluation target as standard sites to be used for the teacher information. Note that any target number of standard sites may be identified from the standard sites included in the regional mesh.

[0032] The control unit 21 of the support server 20 sequentially identifies processing targets among the standard sites of the target number, and repeats the following processing for each standard site. Next, the control unit 21 of the support server 20 executes the process of acquiring the publicly announced land price of the standard land (step S14). Specifically, the acquisition unit 210 of the control unit 21 acquires the publicly announced land price of the standard land to be processed from the standard land information storage unit 23.

[0033] Next, the control unit 21 of the support server 20 executes an acquisition process of explanatory variable values ​​of the standard land (step S15). Specifically, the acquisition unit 210 of the control unit 21 acquires explanatory variable values ​​of the standard land to be processed. This process will be described later with reference to FIG.

[0034] Next, the control unit 21 of the support server 20 executes a process of generating teacher information (step S16). Specifically, the acquisition unit 210 of the control unit 21 generates a data set combining the publicly announced land price of the standard land to be processed and the first to third access information, and records the data set in the teacher information storage unit 25. The above process is repeated until it is completed for all the target number of standard locations.

[0035] Next, the control unit 21 of the support server 20 executes a learning process (step S17). Specifically, the learning unit 211 of the control unit 21 performs machine learning using the teacher information recorded in the teacher information storage unit 25 to generate a land price prediction model that predicts land prices (value assessment information) from explanatory variable values. Then, the learning unit 211 records the generated land price prediction model in the learning result storage unit 26.

[0036] Next, the control unit 21 of the support server 20 executes a process of acquiring explanatory variable values ​​of the evaluation target (step S18). Specifically, the acquisition unit 210 of the control unit 21 acquires explanatory variable values ​​of the evaluation target. This process will also be described later with reference to FIG. 4.

[0037] Next, the control unit 21 of the support server 20 executes a prediction process of the land price of the evaluation target (step S19). Specifically, the prediction unit 212 of the control unit 21 predicts the land price of the evaluation target by inputting the explanatory variable values ​​of the evaluation target to the land price prediction model recorded in the learning result storage unit 26. Then, the prediction unit 212 outputs the predicted land price to the user terminal 10.

[0038] (Acquisition of explanatory variable values) Next, the process of acquiring explanatory variable values ​​(steps S15, S18) for the processing object (reference land or evaluation object) will be described with reference to FIG. Here, the control unit 21 of the support server 20 executes a process of identifying the nearest station (step S21). Specifically, the acquisition unit 210 of the control unit 21 identifies the nearest station that is closest to the processing target, using a map recorded in the map information storage unit 22. For example, the acquisition unit 210 sequentially expands concentric circles centered on the processing target, and identifies the station that is first included in the concentric circle as the nearest station (first station).

[0039] Next, the control unit 21 of the support server 20 executes a calculation process of the first access information to the nearest station (step S22). Specifically, the acquisition unit 210 of the control unit 21 uses a map to calculate the straight-line distance from the processing target to the nearest station, and specifies this distance as the first access information (local evaluation information).

[0040] Next, the control unit 21 of the support server 20 executes a process of identifying the wide-area main station (step S23). Specifically, the acquisition unit 210 of the control unit 21 identifies the regional division in which the processing target is located as a wide area (the first area to which the processing target belongs). Next, the acquisition unit 210 identifies a representative station in this wide area as a wide-area main station (the second station).

[0041] Next, the control unit 21 of the support server 20 executes a calculation process of the second access information to the wide-area main station (step S24). Specifically, the acquisition unit 210 of the control unit 21 uses a map to calculate the straight-line distance from the processing target to the wide-area main station, and specifies this distance as the second access information (area evaluation information).

[0042] Next, the control unit 21 of the support server 20 executes a process of identifying regional main stations (step S25). Specifically, the acquisition unit 210 of the control unit 21 identifies the local government (prefecture) in which the processing target is located as the region (the second area to which the processing target belongs). Next, the acquisition unit 210 identifies the station with the largest number of passengers in this region as the regional main station.

[0043] Next, the control unit 21 of the support server 20 executes a calculation process of the third access information to the regional main station (step S26). Specifically, the acquisition unit 210 of the control unit 21 calculates the straight-line distance from the processing target to the regional main station, and specifies this distance as the third access information (area evaluation information).

[0044] According to this embodiment, the following effects can be obtained. (1) In this embodiment, the control unit 21 of the support server 20 executes a process of identifying an evaluation target (step S11), a process of identifying a regional mesh of the evaluation target (step S12), and a process of identifying a target number of standard sites (step S13). This makes it possible to generate teacher information using more than the target number of standard sites.

[0045] (2) In this embodiment, the control unit 21 of the support server 20 executes a process for acquiring the publicly announced land price of the standard land (step S14) and a process for acquiring the explanatory variable value (step S15). This makes it possible to acquire information for explaining the land price of the standard land.

[0046] (3) In this embodiment, the control unit 21 of the support server 20 executes a learning process (step S17). This makes it possible to generate a land price prediction model using machine learning.

[0047] (4) In this embodiment, the control unit 21 of the support server 20 executes a calculation process of the first access information to the nearest station (step S22). This makes it possible to predict the land price by considering the convenience of public transportation from the evaluation target to the nearest station as an explanatory variable.

[0048] (5) In this embodiment, the control unit 21 of the support server 20 executes a process of calculating the second access information to the wide-area main station (step S24) and a process of calculating the third access information to the local main station (step S26). This makes it possible to predict land prices by considering the region or area where the evaluation target is located as an explanatory variable.

[0049] This embodiment can be modified as follows: This embodiment and the following modifications can be combined with each other to the extent that there is no technical contradiction. In the above embodiment, a user terminal 10 and a support server 20 are used. The hardware configuration is not limited to these. For example, they may be configured as a single device or a cloud (server). In the above embodiment, the control unit 21 of the support server 20 executes a process of identifying the regional mesh to be evaluated (step S12) and a process of identifying the target number of standard locations (step S13). Here, the regional mesh may be identified according to regional attributes. For example, the size of the regional mesh may be changed for each region based on the usage of transportation facilities in the region. As an example of the usage of transportation facilities, the size of the regional mesh may be changed according to the number of passengers getting on and off. Here, when the number of passengers getting on and off is low, the regional mesh is expanded. In addition, the size of the regional mesh may be changed according to the statistical value of the publicly announced land price of the standard land included in each region. For example, if the statistical value of the publicly announced land price (variation such as standard deviation) is large, the regional mesh is made larger and the target number is increased. Also, the size of the regional mesh may be changed depending on the number of houses included in the regional mesh.

[0050] In the above embodiment, the control unit 21 of the support server 20 executes a process of acquiring explanatory variable values. Here, the first to third access information are used as explanatory variables. The access information is not limited to three types. It is sufficient that the access information includes at least a second station (either a wide-area main station or a local main station) corresponding to the area (region) in which the processing target is located, in addition to a local first station (e.g., the nearest station) that is the starting point when using public transportation.

[0051] Also, three or more types of access information may be used. In this case, multiple types of access information may be used according to attribute information of relay stations on the route from the nearest station to the main station. For example, relay stations with a number of passengers greater than a reference number are extracted, and access information to each relay station is used.

[0052] In the above embodiment, the control unit 21 of the support server 20 executes a process for identifying the nearest station (step S21). Here, concentric circles centered on the processing target are successively expanded, and the station that is first included in the concentric circle is identified as the nearest station (first station). The method for determining the first station is not limited to this. For example, the station may be determined based on the time required to reach the station. Furthermore, the first station may be determined among the stations included in a predetermined range based on the amount of use of the station or the station's functions (such as the types of trains that stop there).

[0053] In the above embodiment, the control unit 21 of the support server 20 executes a calculation process (steps S22, S24, S26) of the first access information to the nearest station, the second access information to the wide-area main station, and the third access information to the local main station. Here, the straight-line distance to each station is calculated as the access information. The access information is not limited to the straight-line distance. For example, the route distance on a map or the required time to a main station may be used. In this case, the route is identified by route search, and the required time is calculated.

[0054] In the above embodiment, the control unit 21 of the support server 20 executes a process of identifying major stations in a wide area (step S23). Here, a representative station in this wide area is identified as a major station in the wide area. The method of identifying the major station in the wide area is not limited to the representative station. The major station in the wide area may be identified according to the number of passengers boarding and alighting at the station included in the wide area.

[0055] In the above embodiment, the control unit 21 of the support server 20 executes a process of identifying regional main stations (step S25). Here, the station with the highest number of passengers in the region is identified as the wide-area main station. The method of identifying regional main stations is not limited to using the number of passengers. For example, stations that are stops on a specific type of line such as the Shinkansen, or stations in areas with high population density may be used. In addition, a station with the largest number of transferable lines in a regional division, or a station with a certain number or more of transferable lines may be used.

[0056] In the above embodiment, the map information storage unit 22 stores a map for identifying the area in which the evaluation target is included. In this map, addresses, train stations, regional divisions, and municipalities (prefectures) are stored in relation to longitude and latitude (World Geodetic System). The information stored in the map information storage unit 22 is not limited to this. For example, information on bases such as bus stops, national roads, hospitals, schools, entrances to expressways, and nearby commercial facilities may be included. The position information of these bases may be used to determine the first to third stations. For example, the evaluation information is calculated using the distance when passing through these bases. [Explanation of symbols]

[0057] 10...user terminal, 20...support server, 21...control unit, 210...acquisition unit, 211...learning unit, 212...prediction unit, 22...map information storage unit, 23...standard land information storage unit, 24...route information storage unit, 25...teacher information storage unit, 26...learning result storage unit.

Claims

1. An evaluation support system including a control unit and a standard land information storage unit that records evaluation information of a standard land, The control unit: Using the standard land information storage unit, a standard land in a regional mesh to which the evaluation object belongs is identified; Identifying local evaluation information for a first station for the reference site; Identifying area evaluation information regarding a second station included in the area to which the evaluation object belongs; An evaluation support system characterized by generating a predictive model that predicts the value evaluation information of the evaluation object from the local evaluation information and area evaluation information of the evaluation object using the local evaluation information, area evaluation information and value evaluation information of the standard site as teaching information.

2. 2. The evaluation support system according to claim 1, wherein the control unit determines the first station according to a distance from the reference site and the evaluation target.

3. 3. The evaluation support system according to claim 1, wherein the control unit determines the second station according to the amount of use of stations included in an area to which the evaluation target belongs.

4. 3. The evaluation support system according to claim 1, wherein a major station in a region is identified as the second station.

5. 3. The evaluation support system according to claim 1, wherein the second stations are specified to include major stations in a wider area than the area.

6. 3. The evaluation support system according to claim 1, wherein straight-line distances are used as the local evaluation information and the area evaluation information.

7. 3. The evaluation support system according to claim 1, wherein a required time is used as the local evaluation information and the area evaluation information.

8. 3. The evaluation support system according to claim 1, wherein the area evaluation information is weighted according to a utilization state of the second station.

9. 3. The evaluation support system according to claim 1, wherein the size of the regional mesh is specified according to the number of houses included in the regional mesh.

10. 3. The evaluation support system according to claim 1, wherein the size of the regional mesh is specified in accordance with a distribution of standard land included in the regional mesh.

11. 3. The evaluation support system according to claim 1, wherein the size of the regional mesh is specified in accordance with attributes of the region to which the evaluation object belongs.

12. A method for supporting an evaluation of an evaluation object using an evaluation support system including a control unit and a standard location information storage unit that records evaluation information of a standard location, comprising: The control unit: Using the standard land information storage unit, a standard land in a regional mesh to which the evaluation object belongs is identified; Identifying local evaluation information for a first station for the reference site; Identifying area evaluation information regarding a second station included in the area to which the evaluation object belongs; An evaluation support method characterized by using local evaluation information, area evaluation information and value evaluation information of the standard site as teaching information to generate a predictive model that predicts the value evaluation information of the evaluation object from the local evaluation information and area evaluation information of the evaluation object.

13. A program for supporting an evaluation of an evaluation target using an evaluation support system including a control unit and a standard land information storage unit that records evaluation information of a standard land, The control unit, Using the standard land information storage unit, a standard land in a regional mesh to which the evaluation object belongs is identified; Identifying local evaluation information for a first station for the reference site; Identifying area evaluation information regarding a second station included in the area to which the evaluation object belongs; An evaluation support program that functions as a means for generating a predictive model that predicts the value evaluation information of the evaluation object from the local evaluation information and area evaluation information of the evaluation object using the local evaluation information, area evaluation information and value evaluation information of the standard site as teacher information.

Images