Program, information processing method, and information processing apparatus

Abstract

To provide a program, an information processing method, and an information processing apparatus capable of presenting useful information for considering the purchase of a commercial real estate.SOLUTION: A program causes a computer (server) to execute processing for: receiving an input, from each user or an operator, real estate information including public information on each commercial real estate, which is disclosed to all users, and non-public information which is not disclosed to users other than the user who input the real estate information; storing the input real estate information in a database; extracting, from the database, other commercial real estates having real estate information similar to that of one commercial real estate selected by a user who browses real estate information of similar properties, as similar properties, based on the public information on each commercial real estate and non-public information which is not disclosed to users other than the user who browses similar properties; and displaying, on a display unit, real estate information of the similar properties.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to a program, an information processing method, and an information processing device. [Background technology]

[0002] Systems have been proposed that evaluate commercial real estate that a user is considering purchasing and present the evaluation results to the user. For example, Patent Document 1 discloses a real estate information providing system that calculates a real estate evaluation based on real estate information, calculates a simulation result of the costs required to purchase and maintain the real estate based on the real estate information and the real estate evaluation, and outputs the real estate information, the real estate evaluation, and the simulation result to a user terminal device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-13905 A Summary of the Invention [Problem to be solved by the invention]

[0004] In one aspect, the present invention aims to provide a program or the like that can present useful information for considering the purchase of commercial real estate. [Means for solving the problem]

[0005] In one aspect, the program accepts input from each user of real estate information regarding each commercial property, including public information that is public to all users and private information that is not public to users other than the user who entered the real estate information, stores the input real estate information in a database, and, based on the public information for each commercial property and the private information that is not public to users other than users viewing similar properties, extracts other commercial properties from the database as similar properties that have similar real estate information to a commercial property selected by a user viewing real estate information for similar properties, and displays the real estate information for the similar properties on a display unit. [Effects of the Invention]

[0006] On the one hand, it can provide useful information for those considering purchasing commercial real estate. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of the configuration of a real estate management system. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a server. [Figure 3] 1 is an explanatory diagram showing an example of the record layout of an importance table, a real estate DB, a tenant information DB, a recruitment information DB, and a land price DB. FIG. [Figure 4] FIG. 2 is an explanatory diagram showing an example of a display screen of a terminal. [Figure 5] FIG. 2 is an explanatory diagram showing an example of a display screen of a terminal. [Figure 6] FIG. 2 is an explanatory diagram showing an example of a display screen of a terminal. [Figure 7] 10 is a flowchart illustrating an example of a processing procedure executed by a server. [Figure 8] FIG. 10 is an explanatory diagram showing a display example of a property display field according to the second embodiment. [Figure 9] 10 is a flowchart illustrating an example of a processing procedure executed by a server according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] The present invention will be described in detail below with reference to the drawings showing embodiments thereof. (Embodiment 1) FIG. 1 is an explanatory diagram showing an example of the configuration of a real estate management system. In this embodiment, a real estate management system is described that presents (displays) information for considering purchasing (considering whether or not to purchase) a commercial property that is for sale (an income-generating property expected to generate income through rental), based on information on other commercial properties similar to the commercial property. The real estate management system includes an information processing device 1 and a terminal 2. Each device is connected to communicate with each other via a network N such as the Internet.

[0009] For the sake of simplicity, in the following explanation, the commercial property being considered for purchase will be referred to as the "subject property," and other commercial properties similar to the subject property will be referred to as "similar properties." Furthermore, when referring to any commercial property without distinguishing between the subject property and similar properties, the commercial property will simply be referred to as the "property."

[0010] The information processing device 1 is an information processing device capable of various information processing and sending and receiving information, such as a server computer or a personal computer. In this embodiment, the information processing device 1 is assumed to be a server computer, and for simplicity, will be referred to as server 1 below. The server 1 accepts input from a user to register a target property that is for sale, and provides a service that allows the user to view information about the registered target property. In this embodiment, the server 1 presents information about similar properties that are similar to the target property (such as the acquisition price and appraisal value of the similar properties) as part of the information about the target property (see FIG. 5).

[0011] Terminal 2 is a terminal device used by a user of this system, such as a personal computer, smartphone, tablet terminal, etc. As will be described later, Terminal 2 displays a list of target properties registered by the user, and when it receives an input to select one of the target properties from the list, it displays information on similar properties that are similar to the selected target property.

[0012] It should be noted that users of this system are not limited to those who purchase properties, but may also be agents who introduce properties to those who wish to purchase them.

[0013] 2 is a block diagram showing an example of the configuration of the server 1. The server 1 includes a control unit 11, a main memory unit 12, a communication unit 13, and an auxiliary memory unit . The control unit 11 has one or more processors such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), etc., and performs various information processing by reading and executing a program P stored in the auxiliary storage unit 14. The main storage unit 12 is a temporary storage area such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory), and temporarily stores data necessary for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing processing related to communication, and transmits and receives information to and from the outside.

[0014] The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory or a hard disk, and stores a program P (program product) and other data required for the control unit 11 to execute processing. The auxiliary storage unit 14 also stores an importance table 141, a real estate DB 142, a tenant information DB 143, a recruitment information DB 144, and a land value DB 145. The importance table 141 is a table referenced when extracting similar properties, and specifies the importance of each feature (item) of the real estate information of a property. The real estate DB 142 is a database that stores real estate information for each property. The tenant information DB 143 is a database that stores tenant information regarding tenants occupying each property. The recruitment information DB 144 is a database that stores recruitment information for tenants for each property (vacancy information for the property). The land value DB 145 is a database that stores land values ​​for each area on a map.

[0015] The auxiliary storage unit 14 may be an external storage device connected to the server 1. The server 1 may be a multi-computer consisting of multiple computers, or may be a virtual machine virtually constructed by software.

[0016] Furthermore, in this embodiment, the server 1 is not limited to the above configuration, and may include, for example, an input unit that accepts operation input, a display unit that displays images, etc. Furthermore, the server 1 may be provided with a reading unit that reads a portable storage medium 1a such as a CD (Compact Disk)-ROM or a DVD (Digital Versatile Disc)-ROM, and may read and execute the program P from the portable storage medium 1a.

[0017] FIG. 3 is an explanatory diagram showing an example of the record layout of the importance table 141, the real estate DB 142, the tenant information DB 143, the recruitment information DB 144, and the land value DB 145. The importance table 141 includes a feature column and an importance column. The feature column stores the name of each feature included in the real estate information of the property. The importance column stores the importance of each feature in association with the feature.

[0018] The real estate DB 142 includes a property ID column, a property name column, and a real estate information column. The property ID column stores a property ID for identifying each property. The property name column and the real estate information column each store the property name (building name) and other real estate information in association with the property ID. The real estate information column stores, for example, the property's address, asset type (use such as residential or office), nearest station, etc.

[0019] The tenant information DB143 includes a tenant ID column, a tenant name column, a tenant property column, and a tenant information column. The tenant ID column stores a tenant ID for identifying each tenant. The tenant name column, tenant property column, and tenant information column each store the tenant name, the tenant property name, and other tenant information in association with the tenant ID. The tenant information column stores, for example, the type of business and number of employees (number of employees) of the tenant (company, etc.).

[0020] The recruitment information DB 144 includes a recruitment ID column and a recruitment information column. The recruitment ID column stores a recruitment ID for identifying each tenant recruitment case. The recruitment information column stores recruitment information for the tenant in association with the recruitment ID. The recruitment information column stores, for example, the name of the property for which a tenant is being recruited, the rental portion, the rental portion area, etc.

[0021] The roadside land value DB 145 includes an area column, a route number column, a location information column, and a price information column. The area column stores each area on a map. The route number column, location information column, and price information column each store, in association with an area, the number of each route (the road that the property faces) within the area, location information of the route on the map, and information on the roadside land value corresponding to the route.

[0022] 4 to 6 are explanatory diagrams showing examples of the display screen of the terminal 2. An outline of this embodiment will be described based on FIGS.

[0023] FIG. 4 is an example of a display screen when registering a target property. When terminal 2 receives an input from the case registration button 41 displayed in the upper right corner of the screen, it displays the screen shown in FIG. 4. This screen includes a registration field 42. The registration field 42 is an input field for newly registering a target property. Terminal 2 receives input of the target property's property name, asset type, information acquisition date, and other required input items via the registration field 42. Terminal 2 also receives uploading of a property summary of the target property (material introducing the target property) via the registration field 42.

[0024] The server 1 acquires real estate information for the property to be registered. For example, the terminal 2 accepts input from the user via the registration field 42 regarding details of the property, such as the company that brought the property (the real estate agent introducing the property, the business or individual that owns the property, etc.), the name of the person in charge at the company, and the name of the property owner. Alternatively, the server 1 accepts input of real estate information contained in the uploaded property summary from the operator (administrator) of this system.

[0025] In this embodiment, the description will be given assuming that the user or operator manually inputs the real estate information, but the server 1 may automatically extract the real estate information from the property summary.

[0026] The real estate information may be information about a property, and its content is not particularly limited. The real estate information includes, for example, the property name, asset type, address, nearest station, year of completion, site area, total floor area, rentable area, floor area ratio, building coverage ratio, etc. In particular, in this embodiment, the real estate information includes property tenant information, vacancy information (tenant recruitment information), purchase price, rentable area, and yield information.

[0027] Tenant information is information about the tenants occupying the property, including information on the tenant's industry and employee information. By including tenant information in real estate information, when extracting similar properties (described later), it is possible to extract properties with similar revenue and cost structures based on the hypothesis that the tenants' trends in moving in and out and demographic attributes (visitor attributes) are similar depending on their industry, etc.

[0028] Vacancy information is information that indicates the vacancy status of a property, and includes the property's vacancy rate. By including vacancy rate information in real estate information, it is possible to extract properties with similar revenue structures when extracting similar properties, as described below. In addition, by including the vacancy rate of each property compared to the vacancy rate of the area as a feature, it is possible to extract properties with similar relative positions within the area.

[0029] In addition, since the real estate information includes the property's purchase price, rentable area, and yield information (NOI yield, gross yield, etc.), when extracting similar properties as described below, it is possible to capture subtle differences between properties with similar feature values.

[0030] Since the tenant information and vacancy information are unknown to the user, the server 1 acquires this information from various databases (tenant information DB143, recruitment information DB144) prepared in advance. Specifically, when the server 1 accepts registration of real estate information from a user or operator, it acquires tenant information and vacancy information (recruitment information) corresponding to the target property from the tenant information DB143 and recruitment information DB144 based on specific information included in the real estate information (e.g., the property name, address, etc. of the target property). The server 1 combines the acquired tenant information and vacancy information with the registered real estate information (e.g., stores the real estate information in association with the acquired tenant information and vacancy information).

[0031] In addition, the server 1 may also acquire land value corresponding to the property, data on the flow of people around the property, and the like, and combine this with the real estate information.

[0032] The server 1 stores the data (real estate information) of the target property registered as described above in the real estate DB 142 as data of a new property.

[0033] Figure 5 is an example of a management screen for a target property. The management screen includes a list 51. The list 51 is a table showing the target properties registered by the user. As shown in Figure 5, the list 51 displays information such as the property name, asset type, and nearest station of the target property.

[0034] Terminal 2 accepts an input to select one of the target properties from list 51. When the target property is selected, terminal 2 displays property display field 52. Property display field 52 is a display field that displays information related to the selected target property. Terminal 2 displays real estate information (not shown in FIG. 5) of the target property in property display field 52.

[0035] In this embodiment, the terminal 2 further displays information about similar properties having real estate information with similar features to the target property in the property display field 52, as information for considering the purchase of the target property. Specifically, as shown in Fig. 5, the terminal 2 displays the property name and address of each similar property that is similar to the target property, as well as the latest acquisition price (and acquisition date), appraisal value (and appraisal date), rentable price per tsubo, and yield (Cap Rate) of the similar property.

[0036] The process of extracting similar properties will be described below. The server 1 calculates the similarity between the target property selected by the user and each property whose real estate information is stored (registered) in the property DB 142, and extracts similar properties based on the calculated similarity.

[0037] Specifically, the server 1 first calculates the feature quantities necessary for calculating the similarity from the real estate information. For example, the server 1 calculates the vacancy rate of a property by dividing the rentable area for which tenants are being sought by the rentable area. Similarly, the server 1 calculates the ratio of the potential vacancy rate (the vacancy rate taking into account the rentable area from which tenants are expected to move out) to the vacancy rate, the aggregate value for a specified area, the property vacancy rate relative to the area vacancy rate (the rentable area for which tenants are being sought in the entire area divided by the rentable area for the entire area), etc. The server 1 performs processes such as dummying and standardization on each feature quantity calculated in this way for the purpose of calculating the similarity.

[0038] Next, the server 1 refers to an importance table 141 that defines the importance of each feature of the real estate information, and assigns a weight to each feature. As shown in FIG. 3, the importance table 141 defines the importance of each feature in stages, such as "High," "Middle," and "Low." The server 1 assigns a weight to each feature according to the importance, and vectorizes the real estate information of each property. By specifying the importance of each feature and weighting each feature according to the importance, similar properties can be more appropriately extracted.

[0039] Based on the vectorized real estate information, the server 1 calculates the similarity between the target property and each property registered in the real estate DB 142. For example, the server 1 calculates the Euclidean distance as the similarity. The server 1 compares the calculated similarity with a predetermined threshold and extracts properties whose similarity is equal to or greater than the threshold as similar properties.

[0040] The server 1 may extract a certain number of properties with the highest similarity as similar properties.

[0041] Furthermore, in this embodiment, similar properties are extracted on a rule-based basis, but this embodiment is not limited to this, and similar properties may be extracted using a machine learning model.

[0042] The server 1 displays the extracted information on similar properties in the property display field 52. Specifically, as described above, the server 1 displays the latest acquisition price, appraisal value, rentable price per tsubo, and yield of the similar properties. For example, the server 1 displays this information in descending order of similarity.

[0043] Fig. 6 is an example of a display screen for detailed information on similar properties. When an input for selecting one of the similar properties is received in the property display field 52 in Fig. 5, the terminal 2 transitions to the screen shown in Fig. 6 and displays detailed information on the selected similar property.

[0044] Specifically, terminal 2 displays real estate information (address, nearest station, asset type, information acquisition date, etc.) of similar properties, as shown on the left side of Figure 6. Furthermore, terminal 2 displays graphs on the right side of the screen showing past trends in the acquisition price, appraisal value, leasable price per tsubo, and yield, the latest values ​​of which are displayed in property display field 52 (the leasable price per tsubo and yield are not shown in Figure 6). This allows the user to check how the acquisition price, etc. have changed over time.

[0045] In this embodiment, the past trends in the acquisition prices, etc. of similar properties are displayed in graph format, but they may also be displayed in table format, etc. In other words, the terminal 2 only needs to be able to display information on past trends in the acquisition prices, etc. of similar properties.

[0046] As described above, according to this embodiment, similar properties having real estate information with similar features to the target property for sale are extracted, and information for considering purchasing the target property is displayed based on the real estate information of the extracted similar properties. This allows the user to consider whether or not to purchase the target property while comparing it with similar properties.

[0047] 7 is a flowchart showing an example of a processing procedure executed by the server 1. The processing contents executed by the server 1 will be described with reference to FIG. The control unit 11 of the server 1 receives an input from the user to register a target property that is for sale via the terminal 2 (step S11). For example, the control unit 11 receives an input of the property name of the target property, etc., via the registration field 42 illustrated in FIG.

[0048] The control unit 11 acquires real estate information of the target property (step S12). For example, the control unit 11 may accept input of real estate information from the user via the registration field 42, or may accept upload of a property summary from the user and accept input of the real estate information described in the uploaded summary from the operator.

[0049] Based on the property name, address, etc. of the target property included in the acquired real estate information, the control unit 11 acquires tenant information about tenants occupying the target property and vacancy information (tenant recruitment information) of the target property from the tenant information DB 143 and recruitment information DB 144 (step S13). The control unit 11 combines the acquired tenant information and vacancy information with the real estate information of the target property (step S14).

[0050] The control unit 11 outputs a list 51 of target properties registered by the user to the terminal 2 and causes it to be displayed (step S15). The control unit 11 accepts an input to select one of the target properties from the list 51 (step S16).

[0051] The control unit 11 extracts similar properties having real estate information with feature amounts similar to those of the selected target property from the real estate DB 142 (step S17). Specifically, the control unit 11 refers to a table that defines the importance of each feature amount of the real estate information, weights each feature amount of the real estate information of each property, and vectorizes it. The control unit 11 calculates the similarity between the target property and each property registered in the real estate DB 142 based on the vectorized real estate information. The control unit 11 extracts properties whose calculated similarity is equal to or greater than a threshold as similar properties.

[0052] The control unit 11 outputs information related to the target property selected in step S16 to the terminal 2 and causes it to be displayed (step S18). Specifically, the control unit 11 causes the information about the target property to be displayed in the property display field 52, and also causes the information about each similar property extracted in step S17 to be displayed in the property display field 52. For example, the control unit 11 causes the information about the similar properties to be displayed, in addition to the property name and address of the similar property, the latest acquisition price (and acquisition date), appraisal value (and appraisal date), loanable price per tsubo, and yield (Cap Rate).

[0053] The control unit 11 receives an input to select one of the displayed similar properties (step S19). The control unit 11 outputs detailed information about the selected similar property to the terminal 2 and displays it (step S20). Specifically, as shown in FIG. 6, the control unit 11 displays a graph 61 showing past trends in the acquisition price, appraisal value, lentable price per square meter, and yield of the similar property, in addition to the real estate information of the similar property. The control unit 11 then ends the series of processes.

[0054] As described above, according to the first embodiment, it is possible to present useful information for considering the purchase of commercial real estate.

[0055] (Embodiment 2) In this embodiment, a future predicted value of fluctuations related to a target property (such as the purchase price and yield of the target property) is calculated based on real estate information of similar properties, and the calculated value is presented to the user. Note that the same reference numerals are used to designate the same contents as in the first embodiment, and the description thereof will be omitted.

[0056] 8 is an explanatory diagram showing a display example of the property display field 52 according to the second embodiment. An outline of the present embodiment will be described with reference to FIG.

[0057] In this embodiment, the server 1 calculates a future predicted value of a fluctuation value related to a target property based on real estate information of similar properties, and displays the calculated value in the property display field 52. The fluctuation value may be, for example, the purchase price or yield of the property. In this embodiment, the description will be given assuming that the fluctuation value is the purchase price of the property.

[0058] In the above, examples of variable values ​​have been given of numerical values ​​related to the profits obtained by buying, selling, or renting a property, such as the purchase price and yield, but this embodiment is not limited to these. For example, the variable value may be the occupancy rate of the property (rentable area / rentable area), etc. In this way, the variable value may be any numerical value that can change depending on the time and situation.

[0059] For example, the server 1 calculates the predicted value of the purchase price of the target property at each point in time (for example, every year) for the next 10 years. Specifically, the server 1 calculates the predicted value of the purchase price of the target property based on the actual past purchase prices of similar properties as well as the actual past purchase prices of the target property. For example, the server 1 calculates the predicted value for each point in time for the next year using regression analysis based on these values.

[0060] In this embodiment, regression analysis is used as an algorithm for calculating the predicted value, but this embodiment is not limited to this, and the predicted value may be calculated using a machine learning model. That is, the server 1 may generate (learn) a machine learning model from past actual values ​​of similar properties and their sales prices that outputs a predicted value of the sales price of the target property when actual values ​​of the sales prices (fluctuation values) of similar properties (and the target property) are input, and may calculate a predicted value of the sales price of the target property by inputting the actual values ​​of the sales prices of similar properties into the model.

[0061] Furthermore, it is preferable that the server 1 calculates the predicted sales price of the target property by referring to the land price corresponding to the target property in addition to the actual sales prices of similar properties and the target property. For example, the server 1 uses the roadside land price corresponding to the target property as the land price. The server 1 acquires the roadside land price corresponding to the target property from the roadside land price DB 145, and calculates the predicted sales price of the target property based on the acquired roadside land price and the actual sales prices of similar properties and the target property. This allows the predicted sales price to be more appropriately predicted.

[0062] In addition, depending on the real estate information of similar properties, the server 1 may preferably exclude the real estate information of the similar properties from the calculation criteria for the predicted value. For example, if the vacancy rate of the similar properties is equal to or greater than a predetermined value, the server 1 may exclude the actual sales price of the similar properties from the calculation criteria. This allows similar properties that are unsuitable for calculating the sales price to be excluded from the calculation criteria.

[0063] The server 1 outputs the calculated predicted value to the terminal 2 and displays it in the property display field 52. For example, the terminal 2 displays the predicted value of the purchase price 10 years from now, as well as a graph showing the trends in the actual and predicted values ​​of the purchase price, as shown in Fig. 8. In the graph, the solid line represents the actual value, and the dotted line represents the predicted value.

[0064] When displaying a graph, it is preferable that terminal 2 display the sales prices of similar properties alongside the sales price of the target property, as shown in FIG. 8. In FIG. 8, the sales price of the target property is shown in a thick line, and the sales prices of similar properties are shown in a thin line. Terminal 2 displays the actual and predicted sales prices of the target property, as well as the trends in the actual and predicted sales prices of similar properties, on a graph. Note that server 1 may calculate predicted sales prices for similar properties based on real estate information for other properties similar to the target property, just as it does for the target property. This allows the user to easily predict how the sales price of the target property will fluctuate.

[0065] 9 is a flowchart showing an example of a processing procedure executed by the server 1 according to embodiment 2. After extracting similar properties (step S17), the server 1 executes the following processing. The control unit 11 of the server 1 calculates a future predicted value of the fluctuation value related to the target property based on the extracted real estate information of similar properties (step S201). The fluctuation value may be, for example, the purchase price or yield of the property. The control unit 11 calculates a predicted value of the fluctuation value at a future point in time based on the actual values ​​of the fluctuation values ​​of similar properties, the actual value of the fluctuation value of the target property, and the land price (e.g., roadside price) corresponding to the target property.

[0066] The control unit 11 outputs the predicted value calculated in step S201 to the terminal 2, in addition to the information on the subject property and the similar properties, and causes it to be displayed (step S202). Specifically, the control unit 11 causes the terminal 2 to display the predicted value for a future point in time (for example, 10 years from now), as well as a graph showing the trends in the actual and predicted values ​​of the fluctuation value of the subject property. When displaying the graph, the control unit 11 causes the terminal 2 to display the trends in the actual and predicted values ​​of the fluctuation value of similar properties side by side, in addition to the trends in the actual and predicted values ​​of the subject property. The control unit 11 then proceeds to step S19.

[0067] As described above, according to this second embodiment, by using real estate information of similar properties, future predicted values ​​of fluctuation values ​​(such as purchase and sale prices) related to the target property can be appropriately predicted and presented to the user.

[0068] In this embodiment 2, when a predicted value is calculated using a machine learning model, if server 1 acquires information on the actual value of the fluctuation value of the target property (such as the purchase and sale price when the target property is actually purchased and sold) after the calculation of the future predicted value of the calculated fluctuation value related to the target property, the machine learning model may be updated using the actual value as learning data.

[0069] (Variation 1) In this modified example, when extracting similar properties similar to the target property from the real estate DB 142, the extraction of similar properties is limited to properties having the same asset type as the target property.

[0070] As described in the first embodiment, the server 1 accepts input of real estate information about a target property, and extracts similar properties having similar features to the target property from the real estate DB 142. The real estate information includes tenant information, vacant room information, etc., as well as an asset type that indicates the type of use of the property.

[0071] In this modification, when extracting similar properties, the server 1 first extracts properties that have the same asset type as the target property. By narrowing down the search results according to asset type, it is possible to prevent situations such as residential properties being extracted as similar properties when, for example, an office property is being searched for.

[0072] When a user inputs real estate information about a target property, including the asset type, the asset type may not be clearly identified because "Other" is specified as the asset type and no specific asset type information is registered, or the asset type is not entered at all. In such cases, the server 1 may estimate the asset type of the target property based on real estate information other than the asset type. For example, the server 1 may estimate the asset type from the floor area ratio, fire resistance standards, etc. of the target property. Alternatively, the server 1 may estimate the asset type from information such as the addresses of buildings already built on the land related to the target property and applicable ordinances for the addresses. Alternatively, the server 1 may estimate the asset type using a machine learning model rather than a rule-based method.

[0073] Furthermore, if the asset type of other properties (candidates for similar properties) registered in the real estate DB 142 cannot be clearly identified, the asset type of the other commercial real estate may be estimated from real estate information other than the asset type. In other words, when extracting properties with the same asset type as the target property, the asset type of properties registered as "other" or the like may be estimated from real estate information other than the asset type, and properties may be extracted according to the estimated asset type.

[0074] When estimating the asset type, the server 1 may estimate multiple asset types as candidates for the asset type of the target property (for example, estimate that the property can be used as both an "office" and a "residential").

[0075] The server 1 extracts, from among properties that have the same asset type as the target property, properties that have similar real estate information to the target property as similar properties. That is, the server 1 vectorizes the real estate information of the target property and the real estate information of each property extracted as having the same asset type, calculates the similarity, and extracts similar properties.

[0076] In this case, the server 1 may change the extraction method for extracting similar properties depending on the asset type of the target property. Specifically, the server 1 changes the feature amounts (items) of real estate information that are weighted as having high importance depending on the asset type. For example, if the target property is a residential property, the server 1 weights the facility information of the target property as having high importance. Also, if the target property is an office property, the server 1 weights the yield information (Cap Rate) of the target property as having high importance. Alternatively, if a machine learning model is used as the algorithm for extracting similar properties, the server 1 may extract similar properties using different models depending on the asset type. In this way, by changing the extraction method for similar properties depending on the asset type, it is possible to extract appropriate similar properties for each asset type.

[0077] (Variation 2) In this modified example, a form will be described in which similar properties are extracted by referring to the property browsing history of the user.

[0078] As described in the first embodiment, the server 1 displays on the terminal 2 information such as the acquisition price of one or more similar properties to the target property as information for considering the purchase of the target property. When an input to select one of the one or more similar properties is received, the server 1 displays detailed information of the selected similar property on the terminal 2. In this modification, the server 1 stores the display history of the similar properties as the user's property viewing history.

[0079] When the server 1 extracts new similar properties and presents them to the user, it extracts properties whose real estate information is similar to that of the target property and similar to that of properties previously viewed by the user as similar properties.

[0080] For example, the server 1 predicts the asset type of properties that the user will likely want to view based on the asset type of each property the user has previously viewed, narrows down the search to that asset type, and extracts properties similar to the target property. Alternatively, the server 1 may change the feature weights used when extracting similar properties based on the real estate information of each property the user has previously viewed.

[0081] In this way, by referring to the user's property viewing history, the tendency of the properties viewed by the user may be analyzed, and properties that fit that tendency may be extracted.

[0082] (Variation 3) In this modified example, we will explain a form in which similar properties are extracted based on the real estate information of each property, including public information that is made public to all users and private information that is made public to the user who input (uploaded) the real estate information.

[0083] As described in the first embodiment, the server 1 receives input of real estate information of a target property from a user. The input real estate information is stored (registered) in the real estate DB 142 as a candidate for a similar property.

[0084] In this modification, the server 1 classifies the real estate information of each property into public information that is public to all users and private information that is not public to users other than the user who inputs the real estate information.

[0085] Public information is information that is generally publicly available, such as the asset type and address of a property. In contrast, private information is information that is, for example, the rent of a property, and is information that users have collected themselves and registered in real estate DB 142. In real estate DB 142, private information is stored in association with the user who input the private information.

[0086] When calculating the degree of similarity between the real estate information of a target property and the real estate information of each other property, the server 1 calculates the degree of similarity based on the public information of each property and the private information that can be made public to the user who is the viewer of the similar property (associated with the viewer user). In other words, if the viewer user is the input source of the real estate information of the property, the server 1 calculates the degree of similarity with the target property by referring to not only the public information but also the private information. On the other hand, if the viewer user is the input source of the real estate information, the server 1 calculates the degree of similarity with the target property from the public information without referring to the private information. The server 1 extracts properties with a similarity equal to or greater than a threshold as similar properties and displays information about the similar properties on the terminal 2.

[0087] In this way, the real estate information of each property may be divided into public information and private information, and the private information may be used depending on the user viewing similar properties.

[0088] The embodiments disclosed herein are to be considered as illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims.

[0089] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any combination, regardless of the reference format. Furthermore, although the claims use a format in which a claim references two or more other claims (multi-claim format), this is not limited to this format. A format in which multiple claims (multi-multi-claims) that reference at least one other multiple claim may also be used.

[0090] At least a portion of the processing described herein as being executed by a specific device may be executed by any information processing device. For example, at least a portion of the processing described in the above embodiment as being executed by a server may be executed by each terminal. Conversely, at least a portion of the processing described in the above embodiment as being executed by each terminal may be executed by the server, with each terminal functioning only as an interface with the user, such as for input and output.

[0091] The series of processes performed by each device described herein may be implemented using software, hardware, or a combination of software and hardware. The software programs may be stored in advance, for example, on a recording medium (more specifically, a non-transitory computer-readable storage medium) internal or external to each device. Each program is then loaded into RAM and executed by a processing circuit such as a CPU when executed by a computer controlling each device described herein. The recording medium may be, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a flash memory. The computer program may also be distributed, for example, via a network, without using a recording medium. The computer may be, for example, an application-specific integrated circuit (ASIC), a general-purpose processor that executes functions by loading a software program, or a computer on a server used in cloud computing. The series of processes performed by each device described herein may be centrally processed by a single computer, or may be distributed across multiple computers. Furthermore, in each of the above embodiments, two or more communication means present in one device may be physically implemented on a single medium.

[0092] Furthermore, the processes described herein using flowcharts or sequence diagrams do not necessarily have to be performed in the order shown. Some process steps may be performed in parallel. Furthermore, additional process steps may be employed, and some process steps may be omitted.

[0093] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Explanation of symbols]

[0094] 1. Server (information processing device) 11 Control section 12 Main memory 13 Communications Department 14 Auxiliary storage P Program 141 Importance Table 142 Real Estate DB 143 Tenant Information DB 144 Recruitment Information DB 145 Roadside Land Value DB 2. Devices

Claims

1. Accepting input of real estate information from each user, the real estate information including public information that is public to all users and private information that is private to users other than the user who inputted the real estate information, regarding each commercial property; The entered real estate information is stored in the database, Based on the public information of each commercial property and the private information that is not public to users other than the user viewing the similar property, extracting from the database as similar properties other commercial properties that have similar property information to the commercial property selected by the user viewing the real estate information of the similar property; Displaying real estate information about the similar property on the display unit A program that causes a computer to perform a process.

2. storing a user's browsing history of commercial real estate in a storage unit; When extracting the similar properties, other commercial properties that have similar real estate information to the one commercial property and similar real estate information to the commercial property viewed by the user are extracted as the similar properties. The program according to claim 1.

3. Vectorize the real estate information of each commercial property, Calculating the similarity between the one commercial property and the other commercial property based on the vectorized real estate information; Based on the calculated similarity, the other commercial real estate that is similar to the one commercial real estate is extracted as the similar property. The program according to claim 1.

4. The real estate information includes the name or address of a commercial real estate property; When receiving input of real estate information for a commercial real estate property, based on the property name or address of the commercial real estate property, acquire tenant information or vacancy information for the commercial real estate property from a database that stores tenant information or vacancy information for the commercial real estate property in association with the property name or address, Adding the acquired tenant information or vacancy information to the real estate information of the commercial real estate; Based on the real estate information to which the tenant information or vacancy information has been added, the other commercial real estate that is similar to the one commercial real estate is extracted as the similar property. The program according to claim 1.

5. Accepting input of real estate information from each user, the real estate information including public information that is public to all users and private information that is private to users other than the user who inputted the real estate information, regarding each commercial property; The entered real estate information is stored in the database, Based on the public information of each commercial property and the private information that is not public to users other than the user viewing the similar property, extracting from the database as similar properties other commercial properties that have similar property information to the commercial property selected by the user viewing the real estate information of the similar property; Displaying real estate information about the similar property on the display unit An information processing method in which processing is performed by a computer.

6. An information processing device including a control unit, The control unit Accepting input of real estate information from each user, the real estate information including public information that is public to all users and private information that is private to users other than the user who inputted the real estate information, regarding each commercial property; The entered real estate information is stored in the database, Based on the public information of each commercial property and the private information that is not public to users other than the user viewing the similar property, extracting from the database as similar properties other commercial properties that have similar property information to the commercial property selected by the user viewing the real estate information of the similar property; Displaying real estate information about the similar property on the display unit Information processing device.

Images