JP2021068437A - Output program, method for output, and output device - Google Patents

Abstract

To provide an output program, for example, that can output information of real estate properties suitable for borrowers, with contract records taken into consideration.SOLUTION: The output program causes a computer to perform processing of: inputting input data including answer information about answers to questions on real estate properties and personal information into a learned model learned by teacher data including answer information, personal information, and contract property information; acquiring property information; and outputting property information that fits the acquired property information.SELECTED DRAWING: Figure 18

Description

The present invention relates to an output program or the like that outputs real estate property information.

A system that provides property information (housing information) suitable for a borrower who wants to rent real estate has been proposed (for example, Patent Document 1). However, if the borrower does not enter his / her wishes as accurate search conditions, there is a possibility that some properties that hit the search may not be suitable.

On the other hand, a system for introducing suitable real estate by using the contract record has been proposed (for example, Patent Document 2). The system described in Patent Document 2 associates a user with one of a plurality of clusters, and outputs the contracted real estate included in the contracted results classified into the linked clusters. Since the output real estate corresponds to the cluster, the detailed wishes of the user are not taken into consideration.

Japanese Unexamined Patent Publication No. 2003-281175 Japanese Unexamined Patent Publication No. 2016-206783

The present invention has been made in view of such a situation. The purpose is to provide an output program or the like that outputs real estate property information suitable for the lessee while considering the contract record.

The output program according to the present invention inputs answer information, input data including personal information into a learned model learned from teacher data including answer information, personal information, and contracted property information for a question about a real estate property, and property information. The feature is that the computer is made to perform the process of acquiring the property information and outputting the property information that matches the acquired property information.

In the present invention, it is possible to output real estate property information suitable for the lessee while considering the contract record.

It is explanatory drawing which shows the configuration example of the provision system. It is a block diagram which shows the hardware configuration example of the provision server. It is explanatory drawing which shows the example of the property DB. It is explanatory drawing which shows the example of the room basic DB. It is explanatory drawing which shows the example of the basic equipment DB. It is explanatory drawing which shows the example of the additional information DB. It is explanatory drawing which shows the example of the contract condition DB. It is explanatory drawing which shows the example of the peripheral DB. It is explanatory drawing which shows the example of the special mention DB. It is explanatory drawing which shows the example of facility DB. It is explanatory drawing which shows the example of the answer DB. It is explanatory drawing which shows the example of the prospective customer DB. It is explanatory drawing which shows the example of the history DB. It is explanatory drawing which shows the example of the additional information DB. It is explanatory drawing about the generation processing of a room selection model. It is explanatory drawing about a room selection process. It is a flowchart which shows the procedure example of the room selection model generation processing. It is a flowchart which shows the procedure example of a room selection process. It is explanatory drawing which shows the example of the room selection result display screen. It is a flowchart which shows the procedure example of the viewing room selection process. It is explanatory drawing which shows the example of the viewing room selection result display screen. It is explanatory drawing which shows the example of the actual data DB. It is a flowchart which shows the procedure example of the decision tree generation processing. It is a flowchart which shows the procedure example of the actual data creation process. It is a flowchart which shows the procedure of the decision tree analysis process. It is explanatory drawing which shows the example of the decision tree. It is a flowchart which shows the other procedure example of a room selection process. It is a flowchart which shows the other procedure example of a room selection process. It is a flowchart which shows the other procedure example of a room selection process. It is a flowchart which shows the procedure example of a room search process. It is explanatory drawing which shows the example of the search result display screen. It is a flowchart which shows the procedure example of a room search process.

(Embodiment 1)
Hereinafter, embodiments will be described with reference to the drawings. FIG. 1 is an explanatory diagram showing a configuration example of the provided system. The providing system 100 includes a providing server 1, a business terminal 2, and a user terminal 3. The providing server 1, the business terminal 2, and the user terminal 3 are connected to each other so as to be able to communicate with each other by the network N. The providing server 1 mainly provides information on real estate rental properties. The business terminal 2 is a terminal used by a salesperson of a real estate agent. The business terminal 2 acquires the conditions of the property, transmits the acquired property information to the providing server 1, and receives the property information from the providing server 1. The user terminal 3 is a terminal used by a general user who is looking for a real estate property. FIG. 1 shows three business terminals 2 and three user terminals 3, but the present invention is not limited to the three. The number of business terminals 2 may be one or more. The number of user terminals 3 may be one or more. However, if the providing server 1 does not provide information to general users, the user terminal 3 is not included in the providing system 100.

FIG. 2 is a block diagram showing a hardware configuration example of the providing server. The providing server 1 is composed of a workstation, a server computer, a blade server, and the like. The providing server 1 () includes a control unit 11, a main storage unit 12, an auxiliary storage unit 13, a communication unit 15, and a reading unit 16. Each part is connected by bus B. The function of the providing server 1 may be realized by a cloud service. Further, the control device may be composed of a multi-computer composed of a plurality of computers, a virtual machine virtually constructed by software, or a quantum computer.

The control unit 11 has one or a plurality of arithmetic processing units such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), and a GPU (Graphics Processing Unit). The control unit 11 reads and executes the control program 1P (output program) stored in the auxiliary storage unit 13 to perform various information processing, control processing, and the like related to the providing server 1. The control unit 11 operates as a functional unit such as an acquisition unit or an output unit by executing the control program 1P.

The main storage unit 12 is a SRAM (Static Random Access Memory), a DRAM (Dynamic Random Access Memory), a flash memory, or the like. The main storage unit 12 temporarily stores data necessary for the control unit 11 to execute arithmetic processing.

The auxiliary storage unit 13 is a hard disk, SSD (Solid State Drive), or the like, and stores a control program 1P and various DBs (Databases) necessary for the control unit 11 to execute processing. The auxiliary storage unit 13 stores the property DB 131, the room basic DB 132, the basic equipment DB 133, the additional information DB 134, the contract condition DB 135, the peripheral DB 136, the special note DB 137, the facility DB 138, the answer DB 139, the prospective customer DB 13A, the history DB 13B, and the additional information DB 13C. To do. Further, the auxiliary storage unit 13 stores the room selection model 141. The auxiliary storage unit 13 may be an external storage device connected to the providing server 1. Various DBs and the like stored in the auxiliary storage unit 13 may be stored in the cloud storage.

The communication unit 15 communicates with the business terminal 2 and the user terminal 3 via the network N. Further, the control unit 11 may use the communication unit 15 to download the control program 1P from another computer via the network N or the like and store it in the auxiliary storage unit 13.

The reading unit 16 reads a portable storage medium 1a including a CD (Compact Disc) -ROM and a DVD (Digital Versaille Disc) -ROM. The control unit 11 may read the control program 1P from the portable storage medium 1a via the reading unit 16 and store it in the auxiliary storage unit 13. Further, the control unit 11 may read the control program 1P from the semiconductor memory 1b.

FIG. 3 is an explanatory diagram showing an example of the property DB. The property DB 131 stores information about the property building. When the rental property belongs to the apartment house, the property DB 131 stores the information of the apartment house. When the rental property is a single-family house, the property DB 131 stores the information of the single-family house. The property DB 131 includes a property ID column, a property name column, a property address column, an area column, the nearest station column, a school district column, a management type column, a structure column, a building age column, and a common section column. The property ID column stores the property ID that can uniquely identify the building. The property ID will be issued when a new record is registered. The property name column stores the name of the building. The property address column remembers the location of the building. The area column stores the area of the location. The area may be determined and entered by the sales staff, but a correspondence table between the town chome and the area may be created and uniformly determined based on the correspondence table. The nearest station row stores the means of transportation from the nearest station of the building and the nearest station. The school district column stores the school district of the public elementary school corresponding to the location of the building and the school district of the public junior high school. Specifically, the names of elementary schools and junior high schools are memorized. The management type column stores the management type of the building. The management type is, for example, self-owned, self-managed, lump-sum borrowing, or general. Own ownership indicates that you manage the building owned by the real estate company. In-house management is entrusted and indicates that the real estate company manages it. Lump-sum leasing indicates that the entire building is rented and managed from the owner of the building in a lump sum. The structure column stores the structure of the building. The structure of the building is, for example, wooden, steel, lightweight steel, or RC. Wooden construction refers to a structure that uses wood for columns, beams, walls, floors, etc., which are the main structural parts of a building. Steel structure refers to a structure that uses a steel frame for the frame of a building. Steel structure is also called heavy steel structure. The lightweight steel structure refers to a structure using a steel material having a thickness of less than 6 mm among the steel structures. RC construction is also called reinforced concrete construction. RC construction refers to a structure in which reinforcing bars are embedded in concrete. The age sequence stores the age of the building. The age of the building is the number of years that have passed since the building was completed. If the building is an apartment house, the common area row stores the equipment shared by the residents. Information about the property building is also called property building information.

FIG. 4 is an explanatory diagram showing an example of a room basic DB. The room basic DB 132 stores basic room information (room basic information). When the building is an apartment house, the room basic DB 132 stores the basic information of each dwelling unit. When the building is a single-family house, the room basic DB 132 stores the building information that is not included in the property DB 131. The room basic DB 132 includes a room ID column, a house number column, a floor plan column, a property ID column, a guarantee classification column, a rent column, a management fee column, a vacancy period column, and a status column. The room ID column stores a room ID that can uniquely identify a room. The room ID is issued when a new record is registered. The house number string stores the house number. The house number is also called the room number. If the building is a single-family house, the house number will not be remembered. The floor plan stores a character string representing the floor plan. The floor plan is, for example, 2LDK, 3DK, or the like. The property ID column stores the property ID of the corresponding building. The guarantee classification column remembers whether or not it is necessary to join a rent guarantee company and conclude a rent guarantee contract. If subscription is required, the warranty classification column remembers subscription. If subscription is not required, the warranty classification column remembers that it is not required. A rent guarantee company is also called a rental guarantee company. The rent column remembers the monthly rent of the room. The management fee column stores the monthly management fee of the room. The vacancy period column stores the vacancy period when the room is vacant. The status column stores information about room occupancy. For example, the status column stores the following values. If there is a resident in the room, the status column remembers the occupancy. If there is a resident in the room but is scheduled to move out, the status column remembers the move-out schedule.

FIG. 5 is an explanatory diagram showing an example of the basic equipment DB. The basic equipment DB 133 stores information (basic equipment information) regarding the basic equipment of the room. The basic equipment DB 133 includes a room ID row, a floor plan breakdown row, an entrance row, and a water supply row. The room ID column stores the room ID. The floor plan breakdown column stores the details of the floor plan of the room. FIG. 5 shows a detailed example of the floor plan 2DK. DK 6.4 indicates that the dining kitchen is 6.4 tatami mats in size. Western-style room 6 indicates that one of the two rooms is a Western-style room with 6 tatami mats. Japanese-style room 7 indicates that the other room is a Japanese-style room with 7 tatami mats. The entrance line memorizes the equipment at the entrance. Entrance rows include space rows, auto-lock rows, TV rows, and clog box rows. The size row remembers the size of the entrance. The auto-lock line remembers whether or not the common building entrance is auto-locked. If the building entrance is auto-locked, the auto-lock line remembers the presence. If the building entrance is not auto-locked, the auto-lock line remembers none. The TV line remembers whether or not an intercom with a TV monitor is attached to the entrance of the room. If the intercom with a TV monitor is attached, the TV line is stored, and if the intercom with the TV monitor is not attached, the TV line is not stored. The clog box line remembers whether or not a clog box is installed at the entrance. If a geta box is installed, the clog box row is stored, and if the clog box is not installed, the clog box row is absent. The water line remembers the equipment around the water. The water line includes a gas line, a washing pan line, a reheating line, a thermo faucet line, a shower / toilet line, a bathroom dryer line, a kitchen hot water supply line, and a BT line. The gas train remembers the gas being supplied to the room. When city gas is supplied, the gas train stores the city gas. When propane gas is supplied, the gas train stores the propane gas. The washing pan row remembers the size of the washing pan. For example, when the size of the washing pan is 640 mm in width × 640 mm in depth, the washing pan row stores 640. When the size of the washing pan is 740 mm in width × 640 mm in depth, the washing pan row stores 740. When the size of the washing pan is 800 mm in width × 640 mm in depth, the washing pan row stores 800 sizes. The reheating line remembers whether or not the bath kettle has a reheating function. If there is a reheating function, the reheating line remembers the existence. If there is no reheating function, the reheating line remembers none. The thermostatic faucet row remembers whether the bathroom faucet is a thermostatic faucet. If the faucet in the bathroom is a thermostatic faucet, remember that there is a thermostatic faucet row. If the bathroom faucet is not a thermostatic faucet, remember none of the thermofaucet rows. The thermostat type faucet mixes hot water and water, and if the temperature is set with the temperature control handle, the thermostat cartridge automatically adjusts the mixing amount of hot water. As a result, it is possible to produce hot water at a stable temperature without the hot water becoming hot or cold. The shower / toilet line remembers whether or not the toilet has a shower / toilet function. If the shower / toilet function is on, the shower / toilet line remembers the presence. If the shower / toilet function is not installed, the shower / toilet line is memorized. The bathroom dryer row remembers whether or not the bathroom is equipped with a clothes dryer. If a clothes dryer is installed, the bathroom dryer line remembers the presence. If the clothes dryer is not installed, the bathroom dryer line remembers none. The kitchen hot water supply line remembers whether or not hot water comes out in the kitchen. If hot water comes out in the kitchen, remember that there is a kitchen hot water supply line. If there is no hot water in the kitchen, remember that there is no hot water supply line in the kitchen. The BT row remembers whether the bathroom and the toilet are separate rooms. If the bathroom and toilet are separate rooms, the BT row remembers the different. In the case of a three-point unit bath in which the bathroom and toilet are integrated, the BT row stores the unit.

FIG. 6 is an explanatory diagram showing an example of the additional information DB. Additional information DB 134 stores additional information about the room. In the case of an apartment house, the additional information includes information about the building. The additional information DB 134 includes a room ID row, an EL row, a pet row, a musical instrument row, a net row, a storage row, an outdoor warehouse row, a parking lot row, and a bicycle parking lot row. The room ID column stores the room ID. The EL column stores whether or not there is an elevator in the case of an apartment house. If there is an elevator, the EL column remembers the presence. If there is no elevator, the EL column stores none. The pet line remembers whether or not you can keep pets such as dogs and cats. If you are willing to keep a pet, the pet line remembers yes. If pets are prohibited, the pet line remembers no. The instrument sequence remembers whether or not the instrument is allowed to play in the room. If playing instruments is allowed in the room, the instrument sequence remembers yes. If the room is not allowed to play an instrument, the instrument sequence remembers no. The net line remembers whether or not the internet line is connected. If the internet line is connected, the net line remembers the existence. If the internet line is connected and the usage amount is not generated separately, the net line stores free of charge. If the internet line is not connected, the net column remembers none. The storage row stores the number of storage spaces such as closets and closets. If there is no storage, the storage row stores 0 or none. The outdoor warehouse line stores whether or not there is an outdoor warehouse available to residents. If there is an outdoor warehouse, the outdoor warehouse line remembers the presence. If there is no outdoor warehouse, the outdoor warehouse line remembers none. The parking lot line stores the conditions for renting a parking lot at the same time. For example, if the monthly charge is 3000 yen, the parking lot row stores 3000 yen (1 car). If the rent includes the parking fee for two cars, the parking lot row remembers the parking fee for two cars. The bicycle parking lot line stores the presence or absence of a bicycle parking lot. If the rent includes the usage fee, the bicycle parking lot line will remember the inclusion. If the monthly charge for the bicycle parking lot is 250 yen, the bicycle parking lot line stores 250 yen. If there is no bicycle parking lot, the bicycle parking lot line remembers none.

FIG. 7 is an explanatory diagram showing an example of the contract condition DB. The contract condition DB 135 stores the main conditions (contract conditions) of the occupancy contract. The contract condition DB135 includes a room ID row, a free rent row, an immediate move-in row, a security deposit row, a key money row, and a guarantor row. The room ID column stores the room ID. The free rent column remembers whether or not a free rent is included in which the rent is free for a certain period of time. If free rent is included, the free rent column remembers the period of free rent. The immediate move-in line remembers whether or not to move in immediately. If immediate occupancy is possible, the immediate occupancy line remembers yes. If you cannot move in immediately, remember that you cannot move in immediately. The security deposit line stores the security deposit to be paid when moving in. For example, if the security deposit is for one month's rent, the security deposit line stores one month. If the security deposit is not in rent units, the security deposit column remembers the specific amount. The key money line remembers the key money paid when moving in. The contents memorized by the key money line are the same as those of the security deposit line. The guarantor line remembers whether or not it is necessary to have a joint guarantor at the time of contract. If a guarantor needs to be set up, the guarantor line remembers the need. If there is no need to have a guarantor, the guarantor line remembers no need.

FIG. 8 is an explanatory diagram showing an example of a peripheral DB. Peripheral DB 136 stores information (environmental information) such as facilities around the property. The peripheral DB 136 includes a property ID row, a convenience store row, a highway row, a station row, a hospital row, and a supermarket row. The property ID column stores the property ID. The convenience store line stores information on the convenience store (hereinafter abbreviated as convenience store) closest to the property. The convenience store line includes a distance line and a store line. The distance column stores the distance from the property to the nearest convenience store. The store line stores the name of the convenience store chain and the store ID. The highway row stores information on the highway closest to the property. The main road row includes a distance row and a road name row. The distance column stores the distance from the property to the nearest highway. The road name column stores the name of the main road. The station line stores information on the station closest to the property. The station line includes a distance line and a station name line. The distance column stores the distance from the property to the nearest station. The station name column stores the line name and the station name. The hospital line stores information on the hospital closest to the property. The hospital column includes a distance column and a name column. The distance column stores the distance from the property to the nearest hospital. The name column stores the hospital name. The supermarket line stores information about the supermarket closest to the property. The super row includes a distance row and a store row. The distance column stores the distance from the property to the nearest supermarket. The store line stores the name of the supermarket and the store ID. It is desirable that the distance stored in the above distance sequence is not a straight line distance but a route. Both the distance and the straight line distance may be stored in the distance sequence. Whether or not a convenience store or the like is closest is determined by determining a threshold value. When determining by the required time on foot, for example, assuming that the walking speed is 80 m / min, the required time is calculated from the distance and determined. In addition, it may be determined whether or not there is a facility such as a convenience store nearby based on the time required by car. In the case of a car, the speed is, for example, 400 m / min. A default value is set for the judgment threshold. For example, the time required for walking is within 10 minutes.

FIG. 9 is an explanatory diagram showing an example of a specially described DB. The special note DB137 stores the matters (special notes) that the real estate agent thinks should be especially remembered regarding the property. The special note DB137 includes a room ID column, an in-house management column, a remodeling column, a long-term vacancy column, an initial cost reduction column, and a customer segment column. The room ID column stores the room ID. The in-house management column remembers whether or not the property is owned by a real estate agent. In the case of a room owned by a real estate agent (property owned by the company), the company management column stores ○. In the case of a room that is not owned by a real estate agent but is entrusted with management (property managed by the company), the column managed by the company stores △. In the case of a room where the real estate agent only acts as an intermediary (a property that the real estate agent does not receive management consignment and does not own), the company management column stores x. The remodeling column remembers whether or not the room has been remodeled. When the room is remodeled, the remodeling column remembers ○ or the corresponding. If the room has not been remodeled, the remodeling column remembers x or not applicable. The long-term vacancy row remembers whether or not it is vacant for a long time. If the room is vacant for a long period of time, the long-term vacancy row stores ○ or the corresponding. If the room is not vacant for a long period of time, the long-term vacancy row stores x or not applicable. The real estate agent will determine the criteria for determining whether or not the room will be vacant for a long period of time. The initial cost reduction column stores whether or not the room is subject to initial cost reduction. If the room is subject to initial cost reduction, the initial cost reduction column stores ○ or the corresponding. If the room is not subject to initial cost reduction, the initial cost reduction column remembers x or not applicable. The initial cost reduction means that, for example, by adding a small amount of monthly rent, for example, about 1500 yen, there is no need for a security deposit, key money, key exchange fee, brokerage fee, and house cleaning fee to be paid when moving out. It is a thing. The customer base row stores the customer base suitable for the room or the customer base desired by the owner of the room. In addition, the information of the psychologically defective property may be stored in the special note DB 137.

FIG. 10 is an explanatory diagram showing an example of a facility DB. The facility DB 138 stores detailed information (facility information) of the facility stored in the peripheral DB 136 described above. The facility DB 138 includes a number column, a type column, a chain name column, a store number column, a store name column, a business hours column, a regular holiday column, and a point column. The number string stores the sequential number that is the primary key. The number is issued when adding a record. The type column stores the type of facility. For example, the types are convenience stores, supermarkets, drug stores, family restaurants (meaning family restaurants), fast food, and the like. In the chain name column, if the facility is a chain store store or a store of a company that has multiple stores, the chain name or a common store name is stored. The store number column stores a number that can identify each store in the same chain. The store name column stores the unique name of each store. The business hours column stores the business hours of the store. The regular holiday line stores the regular holidays of the store. In the case of a convenience store, the business hours line stores 24 hours, and the regular holiday line stores no holidays. The point column stores the names of points that can be used at the store. Information on electronic money that can be used at the store may be stored in the facility DB 138.

FIG. 11 is an explanatory diagram showing an example of the answer DB. The answer DB 139 stores the contents (answer information) that the prospective customer answered to the questionnaire prepared by the real estate agent. The answer to the questionnaire may be entered by the salesperson using the sales terminal 2 or by the prospective customer using the user terminal 3. Answer DB139 has a case ID column, a rent lower limit column, a rent upper limit column, an area row, a floor layout row, a nearest station row, a school district row, an auto lock row, a TV row, a BT separate row, a pet allowed row, an instrument allowed row, Includes free online queues and queues with warehouses. The case ID column stores a case ID column that can uniquely identify the case. The case ID is issued when a new record is added. The rent lower limit column stores the lower limit of rent desired by the prospective customer. The minimum amount is divided into money bands of 5,000 yen, and a numerical value is attached to each money band. For example, 0: no lower limit, 1: 20,000 yen or more, 2: 25,000 yen or more, 3: 30,000 yen or more, ..., 13:80,000 yen or more. Since it is 3 in FIG. 11, the customer wants more than 30,000 yen as shown in parentheses. The rent cap column stores the rent cap desired by the prospective customer. As with the lower limit, a numerical value is added for each amount range. For example, 1: 20,000 yen or less, 2: 25,000 yen or less, ..., 13: 80,000 yen or less, 14: No upper limit. Since it is 7 in FIG. 11, the customer wants less than 50,000 yen as shown in parentheses. The area column stores the customer's wishes for the area. The area will be determined by the real estate agent as appropriate. FIG. 11 shows an example divided into six areas. ○ indicates the desired area. X indicates an undesired area. Δ indicates an area that is allowed depending on other conditions. The floor plan memorizes the desired floor plan. Divide the floor plan into groups and add numerical values to each group. For example, 1: 1R / 1K / 1DK, 2: 1LDK, 3: 2K / 2DK, 4: 2LDK, 5: 3DK / 3LDK, 6: 4DK or more, 7: Other. In the example shown in FIG. 11, since it is 4, it indicates that the prospective customer desires 2LDK. The nearest station line remembers the desired nearest station. Although the station name is stored in FIG. 11, a number, a symbol, or the like that identifies the station may be used instead of the station name. The school district column memorizes elementary school districts and junior high school districts. Each elementary school district and junior high school district stores, for example, the corresponding elementary school name and junior high school name. The auto-lock line indicates whether or not the common entrance is desired to have an auto-lock when the desired property is a room of an apartment house. If you want to have an auto lock, the auto lock row will store a circle. If it is desirable to have an auto lock, the auto lock column stores Δ. If you do not specifically want to have auto-lock, the auto-lock column stores x. The TV queue remembers whether or not it wants to be equipped with an intercom with a TV monitor. The contents stored in the TV sequence are the same as those in the auto-lock sequence. The BT separate line remembers whether or not the bathroom and toilet are desired to be separate rooms. The contents stored in the BT separate column are the same as those in the auto-lock column. The pet-friendly store remembers whether or not you want a property that allows you to keep pets such as dogs and cats. If you want a property that is allowed to keep pets, the pet-friendly line will remember ○. If you do not specifically wish to have a pet, the pet-friendly will remember a triangle. If you want a property that is not allowed to keep pets, pet-friendly will remember x. Musical instrument row remembers whether or not you want a property where you are allowed to play musical instruments in the room. The contents stored in the musical instrument sequence are the same as those in the pet column. The free internet line stores whether or not you want a property that has an internet connection and does not generate a separate usage amount. The contents stored in the online free line are the same as those in the auto-lock line. The warehouse row stores whether or not you want a property that has an outdoor warehouse available to residents. The contents stored in the column with warehouse are the same as those in the auto-lock column. The above case starts when a prospective customer looking for a real estate property visits a real estate agent and answers a questionnaire. Alternatively, it starts when a prospective customer accesses the real estate agent's Web page, answers the questionnaire on the questionnaire screen, and sends the answer. The case ends when the prospective customer makes an application, or when the prospective customer contracts with another real estate agent and there are no more inquiries.

FIG. 12 is an explanatory diagram showing an example of a prospective customer DB. The prospect DB13A stores information (personal information) about the prospect. The prospect DB13A has a prospect ID column, a name column, a furigana column, an age column, a gender column, an occupation classification column, a mail column, a telephone column, a FAX column, a postal code column, an address column, a contact method column, a faculty column, and a contract. Includes prospective person column, customer classification column, number of residents column, family type column, foreign nationality column and Japanese column. The prospect ID column stores a prospect ID that can uniquely identify the prospect. The prospect ID is issued when a new record is added. The name column stores the names of prospective customers. The furigana column remembers the furigana of the name. The age column remembers the age of the prospective customer. The gender column stores the gender of the prospective customer. The occupation classification column stores the occupation classification of the prospective customer. Occupational categories are, for example, full-time employees, part-time workers, students, and others. The email sequence stores the contact email address of the prospect. The telephone line stores the contact telephone number of the prospective customer. The FAX column stores the contact facsimile number of the prospective customer. The zip code column stores the zip code of the prospect's current address. The address column stores the current address of the prospective customer. The contact method column stores the contact method desired by the prospective customer. The contact method column stores, for example, telephone, e-mail, and fax. The contact method column may store a plurality of prioritized contact methods. The faculty line remembers the faculty to which it belongs if the prospective customer is a college student. The prospective contractor line stores the information of the prospective contractor when the prospect of concluding a contract is other than the customer. For example, the prospective customer is a college student and the contractor is their guardian. The prospective contractor column includes the occupation column and the annual income column. The occupation column stores the occupation of the prospective contractor. The annual income column stores the latest annual income of the prospective contractor. The customer classification stores the customer classification. When a corporation is a contractor, the customer category remembers "corporation". If the resident is a student, the customer category remembers "student". When a member of society contracts and moves in, "general" is memorized. The number of tenants column stores the number of people scheduled to move in. The family form column remembers the family form in which you plan to move in. Family type rows include household rows, children rows, and infant rows. The household row stores the household type. Household types include single-person households, couple-only households, couples + children's households, and the like. The children's line remembers the number of children. The infant line remembers whether or not the infant is included in the child. When including infants, the infant column stores ○, applicable or 1, and so on. If the infant is not included, the infant column stores x, non-applicable, 0, and the like. The foreign nationality column remembers whether or not the prospective customer is foreign national. If the prospective customer is a foreign national, the foreign nationality column remembers 1 or ○. If the prospect is Japanese, the foreign nationality column either remembers 0 or x or does not remember the value. You may remember the country of nationality in the foreign nationality column. For example, if the prospective customer has Chinese nationality, the foreign nationality column stores the CN indicating China. The Japanese column memorizes the communication ability of the prospective customer in Japanese. For example, it is classified into three stages (○, △, ×) according to the degree of communication ability. Further, the religion, the belief, the ethnic group, and the race of the prospective customer may be stored in the prospective customer DB13A. However, since this information is sensitive information, care must be taken when handling it. Information about prospective customers is also referred to as customer information below.

FIG. 13 is an explanatory diagram showing an example of the history DB. The history DB 13B stores activities for prospective customers. The history DB 13B includes a case ID column, a prospective customer ID column, a reference property column, a preview property column, a status column, and a result column. The case ID column stores the case ID. The prospect ID column stores the prospect ID. The reference property column stores the room ID of the room referred to by the prospective customer. The room ID of the room posted on the property sheet presented by the salesperson to the prospective customer at the store is stored. Further, the room ID of the room referred to from the history referred to by the prospective customer on the property introduction Web page provided by the real estate agent may be acquired and stored. The preview property line stores the room ID of the room viewed by the prospective customer. The preview property row includes a preview 1 row, a preview 2 rows, a preview 3 rows, and other rows. In many cases, the salesperson presents three properties to be viewed, so the three room IDs are stored in the first row, the second row, and the third row. If more than 3 cases are viewed, the remaining room IDs are stored in the other columns. A preview is a field trip or survey of a real estate property, and is also called a preview. The status column stores the status of the case. For example, the situation is in-process, previewed, chasing, finished, lost order. During the work in process, the stage before the preview is shown. Previewed indicates a situation in which the application has not been completed although it has been previewed. Pursuit is the stage after contacting a prospective customer who has been previewed but has not yet applied by telephone or email. Termination indicates that the application has been completed. Loss of order indicates that it has been confirmed that the application will not be completed. The result column stores the status or result for the finished case. The result column includes a contract column, a room ID column, and a contract rent column. The contract column shows the status of the contract. For example, the situation is under review, waiting for payment, and closing a contract. Indicates that a move-in examination is being conducted during the examination. Waiting for deposit indicates a situation in which the customer is waiting for deposit, key money, initial rent, etc. The contract indicates that the contract has been concluded. The room ID column stores the room ID of the room for which the application or contract has been concluded. The contracted rent column stores the contracted rent.

FIG. 14 is an explanatory diagram showing an example of the additional information DB. The additional information DB 13C stores additional information about the prospective customer obtained by the sales staff. The additional information DB 13C indicates a case ID column, a current housing structure column, a working hour column, a self-catering column, a property column, a holiday column, and a bathing time column. The case ID column stores the case ID. The current dwelling structure column stores the structure of the dwelling in which the prospective customer currently lives. The working hours column stores the hours that the prospective customer is working. The working hours column includes a start column and an end column. The start column stores the work start time. The end column stores the work end time. If the prospective customer is a student, etc., remember the time zone at school, etc. The self-catering line remembers whether or not to cook, and if so, the day of the week and the time zone for self-catering. The property column remembers the property if the prospect owns something that needs to be considered when selecting a room. For example, the inventory row stores a drum-type washing machine. The holiday column stores the holidays of prospective customers. If the prospect is not working, the holiday column stores an empty string, blanks, etc. The bathing time column stores the time when the prospective customer takes a bath. As described above, the information stored in the additional information DB 13C includes information that has little relation to the room selection conditions, but stores the additional information obtained for the sales staff to grasp the lifestyle of the prospective customer.

FIG. 15 is an explanatory diagram relating to the generation process of the room selection model. FIG. 15 conceptually illustrates the process of performing machine learning to generate the room selection model 141. The generation process of the room selection model 141 will be described with reference to FIG.

As a room selection model 141, the providing server 1 deeply uses information about the contracted room (contracted property information), information about the contracted customer (personal information), and response information as teacher data based on the past contract information. Learn. The contracted property information includes the property building information stored in the property DB 131, the room basic information stored in the room basic DB 132, and the basic equipment information stored in the basic equipment DB 133. Additional information stored in the additional information DB 134, contract conditions stored in the contract condition DB 135, peripheral information stored in the peripheral DB 136, special notes stored in the special note DB 137, and facilities stored in the facility DB. Information (however, limited to those related to facilities included in the surrounding information) may be included in the contracted property information. The personal information includes customer information stored in the prospective customer DB 13A. The personal information may include additional information stored in the additional information DB 13C. By learning, a neural network is generated in which information about a customer is input and information about a room suitable for the customer is output.

A neural network is, for example, a CNN (Convolution Neural Network), which includes an input layer that accepts input of room information and customer information, an output layer that outputs information about a room suitable for the customer, and room information and customer information. Has an intermediate layer to relate to.

The input layer has a plurality of neurons that accept the values of a plurality of data items included in the information about the customer as inputs, and passes the input item values to the intermediate layer. For example, when the room selection model 141 is CNN, in the intermediate layer, the convolution layer that convolves the value of each data item input from the input layer and the pooling layer that maps the value convolved by the convolution layer alternate. It has a concatenated structure, and finally extracts the feature amount while compressing the input information. The output layer has a plurality of neurons that output the value of each item for the room suitable for the customer, and outputs the item value for the room suitable for the customer based on the feature amount output from the intermediate layer.

In the present embodiment, the room selection model 141 will be described as being a CNN, but the room selection model 141 is not limited to the CNN, and other learning algorithms such as a neural network other than the CNN, a Bayesian network, and a decision tree can be used. It can be a built trained model.

The providing server 1 performs learning using the teacher data. The teacher data is data (contract history) in which contract property information, customer information, and response information are associated with each other. The teacher data is created based on the history data that has reached the contract stored in the history DB 13B.

The providing server 1 inputs the customer information and the answer information included in the teacher data to the input layer, and acquires the information about the room suitable for the customer from the output layer through the arithmetic processing in the intermediate layer. Since the information about the room includes a plurality of data items, a set of values in which the values for each data item are combined is obtained from each output node. A probability value is attached to each set. The probability value indicates the certainty of the room information output with respect to the input data. The total probability value is 1. Each element of the set of values output from the output layer may be discrete values (eg, room layout is 1K, 1DK, 2DK, 2LDK, ...), and continuous values (eg, rent). It may be a value in the range of 0 yen to 200,000 yen). The output information about the room corresponds to the property building information, the room basic information, and the basic equipment information.

The providing server 1 compares the information about the room output from the output layer with the contracted property information included in the teacher data, that is, the correct answer value, and performs an operation in the intermediate layer so that the output value from the output layer approaches the correct answer value. Optimize the parameters used for processing. The parameters include, for example, the weight between neurons (coupling coefficient), the coefficient of the activation function used in each neuron, and the like. The method of optimizing the parameters is not particularly limited, but for example, the providing server 1 optimizes various parameters by using the backpropagation method.

The providing server 1 performs the above learning process using all the teacher data, and generates the trained room selection model 141. The room selection model 141 at the time of constructing the providing system 100 becomes the learned room selection model 141 through the learning process. The output layer of the room selection model 141 is not limited to that shown in FIG. For example, information on different items may be output for each node in the output layer. Some output nodes output the floor plan and some output nodes output the rent. Each output node may output a plurality of data in which a value and a probability are a set. If the floor plan is used, the output will be (2LDK, 0.85), (2DK, 0.09), (3K, 0.06), or the like. If the floor plan of the correct answer included in the teacher data is 2LDK, learning is performed so that the probability of 2LDK increases.

A business for determining a room to be proposed to a prospective customer by a salesperson using the provision system 100 will be described. The salesperson acquires customer information such as name, address, and occupation from prospective customers who visit the store. The salesperson registers the customer information in the prospective customer DB 13A by using the sales terminal 2. In addition, the prospective customer is requested to answer the questionnaire and the answer information is acquired. The salesperson registers the answer information in the answer DB 139 using the sales terminal 2. A tablet terminal or the like may be prepared so that the customer can input the customer information and the response information by himself / herself. The salesperson specifies customer information and response information via the sales terminal 2 and requests the providing server 1 to select a room to be proposed. Upon receiving the request from the business terminal 2, the providing server 1 performs the room selection process.

FIG. 16 is an explanatory diagram relating to the room selection process. FIG. 16 schematically describes the content of the process. The providing server 1 acquires the designated customer information from the prospective customer DB 13A and the designated response information from the response DB 139. The providing server 1 inputs the acquired customer information and the answer information as input data to the room selection model 141. The room selection model 141 outputs information (proposal room information, property information) regarding the room to be proposed as an output. The proposed room information includes property building information, room basic information, and basic equipment information. The providing server 1 stores the proposed room information output from the room selection model 141, the property building information stored in the property DB 131, the room basic information stored in the room basic DB 132, and the basic equipment DB 133. Refer to the basic equipment information and identify the room that most closely resembles the proposed room information. If the specified room cannot be moved in, it will be the runner-up room. The providing server 1 acquires the room basic information (property information) from the room basic DB 132 by using the room ID of the specified room. The providing server 1 transmits the room ID, the room basic information, and the similarity to the business terminal 2. The similarity here can be obtained by the same method as the similarity of vectors. For example, cosine similarity, Pearson's correlation coefficient, or deviation pattern similarity is used as the similarity. Since the calculation of the degree of similarity is known, the description thereof will be omitted.

Proposals are made to prospective customers based on the room selection result displayed on the sales terminal 2. When a contract is concluded as a result of the proposal, the information on the new contract (contract history) becomes teacher data for re-learning the room selection model 141. The re-learning of the room selection model 141 may be performed every time a new contract is made, batch processing may be performed at predetermined intervals, or a certain number of contract histories may be accumulated.

Next, the generation process of the room selection model 141 will be described again using a flowchart. FIG. 17 is a flowchart showing a procedure example of the room selection model generation process. The control unit 11 of the providing server 1 acquires the contract history from the history DB 13B (step S1). The control unit 11 acquires contracted property information (property building information, room basic information, basic equipment information) using the room ID included in the contract history (step S2). The control unit 11 acquires customer information using the prospective customer ID included in the contract history (step S3). The control unit 11 acquires the response information using the case ID included in the contract history (step S4). The control unit 11 generates teacher data including contracted property information, customer information, and response information (step S5). The control unit 11 uses the teacher data to generate a room selection model 141 (learned model) that outputs the proposed room information when the customer information and the answer information are input (step S6). Specifically, the control unit 11 inputs the customer information and the response information included in the teacher data to the input layer of the neural network, and acquires the proposal room information from the output layer. The control unit 11 compares the acquired proposed room information with the correct answer value (contracted property information) of the teacher data, and parameters (weights) used for arithmetic processing in the intermediate layer so that the information output from the output layer approaches the correct answer value. Etc.) to optimize. The control unit 11 stores the generated room selection model 141 in the auxiliary storage unit 13. In the initial construction stage of the room selection model 141, steps S2 to S6 are repeated for each contract history acquired in step S1 to end a series of processes.

Subsequently, the room selection process will be described again using a flowchart. FIG. 18 is a flowchart showing an example of the procedure of the room selection process. The sales terminal 2 acquires customer information (step S11). The business terminal 2 acquires the answer information (step S12). The sales terminal 2 transmits the customer information and the response information to the providing server 1 (step S13). The sales terminal 2 may individually transmit the customer information and the response information to the providing server 1 as soon as they are acquired. The control unit 11 of the providing server 1 receives the customer information and the answer information, stores the customer information in the prospective customer DB 13A, and stores the answer information in the answer DB 139 (step S14). The control unit 11 inputs the customer information and the response information into the room selection model 141, and acquires the proposed room information output by the room selection model 141 (step S15). The control unit 11 refers to the proposed room information, the property building information stored in the property DB 131, the room basic information stored in the room basic DB 132, and the basic equipment information stored in the basic equipment DB 133, and makes a proposal. The degree of similarity between the room information and each room information is calculated (step S16). The control unit 11 identifies the room most similar to the proposed room information (step S17). The control unit 11 transmits basic room information about the specified room to the business terminal 2 (step S18). The business terminal 2 receives and displays the basic room information (step S19).

If the room specified in step S17 cannot be moved in, it will be the next room. In addition, if the specified room is a room managed by another real estate agent, and if the room is managed by the company after the runner-up and the difference in similarity with the specified room is within the specified range. , It may be a property managed by the company.

FIG. 19 is an explanatory diagram showing an example of a room selection result display screen. The room selection result display screen d01 includes a prospective customer name display d011, a property name display d012, a room information display field d013, a next button d014, a front button d015, and a preview recommendation button d016. The prospective customer name display d011 displays the name of the prospective customer. The property name display d012 displays the name of the building and the like. The room information display field d013 displays room information. The next button d014 is a button for switching the display to the next room of the displayed room. The front button d015 is a button for switching the display to the room of the previous rank when the displayed room is the second or lower rank. The preview recommended button d016 is a button for displaying a room suitable for viewing together with the recommended room.

This embodiment has the following effects. Since the room selection model 141 learned from the contract history is used to determine the room to be proposed to the customer, even a salesperson with little work experience can propose a room suitable for the customer as well as a skilled salesperson. It becomes.

When calculating the similarity, each data item may be weighted. For example, ask the customer to answer the items that they want to emphasize in the questionnaire. For items specified by the customer, the weight is increased to calculate the similarity. Further, the proposed room information may be plural, and may be ranked according to the degree of similarity and displayed on the business terminal 2.

The personal information input to the room selection model 141 in the room selection process is customer information and response information, but is not limited thereto. The additional information stored in the additional information DB 13C may be included in the personal information to be input. In this case, when the room selection model 141 is generated, additional information is included in the teacher data and used as one of the input data to the room selection model 141.

Further, the proposed room information output to the room selection model 141 includes, but is not limited to, property building information, room basic information, and basic equipment information. The proposed room information may include additional information, contract conditions, surrounding information, special notes, and facility information. In this case, when calculating the similarity for selecting a room, the additional information, contract conditions, peripheral information, special notes, and facility information included in the proposed room information are stored in the additional information DB 134. , Contract conditions stored in the contract condition DB135, peripheral information stored in the peripheral DB136, special notes stored in the special note DB137, facility information stored in the facility DB138 (however, facilities included in the peripheral information). (Limited to those related to). Furthermore, additional information, contract conditions, peripheral information, special notes, and facility information are included in the contracted property information used when generating the room selection model 141.

By increasing the types of input data and output data to the room selection model 141, the rooms selected by the room selection process will be closer to those that meet the wishes of prospective customers, and an improvement in the contract rate can be expected.

It is assumed that the business terminal 2 acquires customer information and response information, but the present invention is not limited to this. The user terminal 3 may transmit the customer information and the answer information to the providing server 1 via the network N. Further, the user terminal 3 may be allowed to execute the room selection process. The providing server 1 inputs the customer information and the response information transmitted from the user terminal 3 into the room selection model 141, and transmits the basic room information based on the proposed room information output by the room selection model 141 to the user terminal 3.

Further, a plurality of room selection models 141 may be provided according to the attributes of prospective customers. A room selection model for medical students that selects a room for medical students and a selection model for foreign nationalities that selects a room for foreign nationalities may be provided.

(Embodiment 2)
The present embodiment further includes a function of proposing a room suitable for preview (also referred to as preview) together with the selected room in the first embodiment. Customers looking for a room are usually wondering if they should sign a contract, even if they are introduced to only one room that best suits their needs. Therefore, a real estate agent's salesperson usually recommends two more rooms in addition to the room most recommended to the customer. Then, the salesperson asks the customer to view the three rooms and guides the customer to select the room that he / she wants to recommend most. If the two rooms added here are too similar to the room you want to recommend the most, the customer will get lost, so it is better to have a room where the customer feels the goodness of the room you want to recommend the most. However, the best room has traditionally depended on the experience of the sales staff. This embodiment has a function of proposing a room to be viewed together with a room that is most recommended. In the following explanation, the room most recommended to the customer is referred to as a recommended room, and the room suitable for viewing together with the recommended room is referred to as a viewing room.

FIG. 20 is a flowchart showing a procedure example of the viewing room selection process. The salesperson inputs the room ID of the recommended room into the sales terminal 2. When the salesperson determines the recommended room by the room selection process in the first embodiment, if the recommended room displayed on the sales terminal 2 is selected, it is not necessary to input the room ID. The business terminal 2 transmits the room ID to the providing server 1 (step S31). The control unit 11 of the providing server 1 receives the room ID (step S32). The control unit 11 acquires the contract history for which the recommended room is contracted from the history DB 13B using the room ID (step S33). The control unit 11 analyzes the acquired contract history (step S34). For example, association analysis or market basket analysis. The analysis is an analysis method for finding a rule that when a product A sells, a product B often sells together. Applying this, in the past contract history, the room that has been viewed many times together with the recommended room is obtained. The control unit 11 selects the top two rooms that have been viewed frequently together with the recommended rooms as viewing rooms (step S35). The control unit 11 transmits the basic room information regarding the selected viewing room to the business terminal 2 (step S36). The business terminal 2 receives and displays the basic room information (step S37). The business terminal 2 ends the process.

FIG. 21 is an explanatory diagram showing an example of a viewing room selection result display screen. The viewing room selection result display screen d02 includes a prospective customer name display d021, a recommended property name display d022, a viewing room information display field d023, a decision button d024, an additional button d025, and an edit link d026. The prospective customer name display d021 displays the name of the prospective customer. The recommended property name display d022 displays the name of the building including the room recommended to the prospective customer. The viewing room information display column d023 displays information on the room recommended for viewing together with the recommended room. The decision button d024 is a button for inputting that the preview of the displayed room has been decided. By operating the enter button d024, the combination of rooms to be viewed is stored in the history DB 13B. The add button d025 is selected when adding a property to be viewed. The edit link d026 is a hyperlink that displays an operation menu in the displayed room. A pull-down menu for displaying the edit link d026 is displayed. The pull-down menu includes, for example, detailed reference, deletion, replacement, and the like. The detailed reference is a menu for displaying detailed information (plan, map, etc.) about the room. Delete is a menu for deleting the displayed room from the viewing room. Replacement is a menu for deleting the displayed room from the viewing room and adding another room.

In the present embodiment, the business terminal proposes a room to be viewed together with the room most recommended to the customer. The salesperson can increase the contract rate of the room that he / she wants to recommend most by having the customer preview the room according to the proposal. In addition, regardless of the amount of experience of the sales staff, it is possible to select the room to be viewed.

Although the market basket analysis was used to select the contracted room, a trained model similar to the rules obtained from the analysis may be used. When the trained model inputs the recommended room information, it outputs the viewing room information. The teacher data of the trained model is a combination of the information of the contracted room acquired from the contract history and the information of the rooms viewed together. The information of the contracted room included in the teacher data is input to the input layer of the neural network, and the information of the room to be viewed together is acquired from the output layer. The acquired room information to be viewed together is compared with the correct answer value of the teacher data (viewing room information), and the parameters (weights, etc.) used for arithmetic processing in the intermediate layer so that the result output from the output layer approaches the correct answer value. ) Is optimized. By performing such learning, a trained model is generated from the neural network.

(Embodiment 3)
The present embodiment relates to a form of determining a room to be proposed to a customer by using a decision tree. Decision trees are one of the supervised learning algorithms that solve classification and regression problems. This is a method of classifying data in stages by setting conditions one after another for given data. In the present embodiment, a decision tree is generated in which the attributes of the customer, the desired conditions for the real estate property of the customer, and the information of the real estate property are used as explanatory variables, and the probability of reaching a contract is used as the objective variable. The attributes of the customer are, for example, age, gender, occupation, contracting entity (individual / corporate), number of residents, presence or absence of a guarantor, and the like. The desired conditions are the range of rent, floor plan, area, etc. Information on real estate properties is, for example, rent, floor plan, area, and the like.

In the present embodiment, a decision tree is created based on past activity information for prospective customers (hereinafter, also referred to as “activity information”) as a learning stage, and a decision tree created is used for the customer in the operation stage. Determine the real estate property to propose. CART (Classification And Regression Trees) is used to create the following decision trees. First, a group of actual data that combines customer attributes, real estate property information, and sales results (concluded or not concluded) based on past activity information stored in the history DB 13B. It is divided into two performance data groups according to the customer's attributes, the customer's desired conditions for the real estate property, or one value (feature amount) included in the real estate property information. At this time, the feature amount is selected so that the data that has reached a contract is biased to one of the actual data groups after the division and the data that has not reached a contract is biased to the other actual data group. The greater the bias after the split compared to before the split, the greater the effect of the features on the business results. First, the actual data group is divided into two actual data groups according to the feature amount that has the maximum influence on the sales result, and then each divided actual data group is divided in the same manner, and the actual data group is divided in the same manner. Repeat the division of. In this way, a decision tree, which is a model for classifying actual data into a tree shape, is generated.

The influence of the feature amount on the business result is determined by calculating the information gain when the actual data group is divided according to the feature amount value. The actual data group will be divided into a first taxon and a second taxon. _{Let N 0} be the total number of data included in the actual data group before division _{, N 1} be the number of data included in the first taxon, _{and N 2} be the number of data included in the second taxon. N ₀ = N ₁ + N ₂ . Let the information gain be IG. The information gain IG is represented by the following equation (1).
IG = (impurity of actual data group before division)-{(N ₁ / N ₀ ) × (impurity of first taxon) + (N ₂ / N ₀ ) × (impurity of second taxon) Purity)} ... (1)

Impure is a numerical value of the bias of the data included in the actual data group. Specifically, Gini impureness is used as the impureness. _{Let n 0} be the total number of data included in the actual data group, _{n 1} be the number of data _{that have been concluded, and n 2} be the number of data that have not been concluded. n ₀ = n ₁ + n ₂ . Let Gi be impure. Gini impure Gi is represented by the following formula (2).
Gi = 1-{(n ₁ / n ₀ ) ² + (n ₂ / n ₀ ) ² } ... (2)

The value of gini impureness increases as the bias toward either the data included in the actual data group is the data that has been contracted or the data that has not been contracted is smaller. The information gain indicates the difference between the impureness before division and the weighted average of the impureness after division. The value of the information gain becomes larger as the bias before the division is smaller and the bias after the division is larger. Therefore, the larger the information gain, the greater the influence of the feature amount on the business result. By selecting a feature amount that increases the information gain, it is possible to select a feature amount that has a large influence on the business result.

Instead of the information gain, the improve value, which is the value obtained by multiplying the _{information gain value by N 0, may be calculated.} Similar to the information gain, the larger the improve value, the greater the influence of the feature amount on the business result. Assuming that the improve value is Imp, the improve value Imp is expressed by the following equation (3).
Imp = N ₁ × {(impurity of actual data group before division)-(impurity of first taxon)} + N ₂ × {(impurity of actual data group before division)-(second taxon) Impureness of the group)} ... (3)

CART was used as the algorithm used for decision tree analysis, but it is not limited to this, and CHAID (Chi-) using ID3 (Iterative Dichotomiser 3), C4.5, or C5.0, which uses entropy as the purity, or chi-square value. squared Automatic Interaction Detection) or the like may be used.

The actual data used when generating the decision tree will be described. FIG. 22 is an explanatory diagram showing an example of the actual data DB. The actual data DB 13D stores the actual data to be analyzed by the decision tree. The actual data DB 13D is stored in, for example, the auxiliary storage unit 13. A decision tree is generated by analyzing the actual data. The actual data DB 13D includes an ID column, a branch number column, a business result column, a gender column, an age column, a desired floor plan, a desired rent column, a desired area column, a room ID column, a contract rent column, a floor plan column, and an area column. The ID column stores an ID that identifies the actual data. The branch number sequence stores the branch number. Actual data can be uniquely identified by the ID and the branch number. The business result column remembers whether or not the contract for the proposed room has been concluded. When the contract is concluded, the business result column stores "contract". If the contract is not concluded, the business result column stores "lost order". When proposing a room to a prospective customer, it is usual to propose a plurality of rooms, so even if a contract is reached, a plurality of actual data are created. Actual data with the same ID indicate that they are actual data created from the same case. Of the actual data with the same ID, one actual data has a contracted business result, and the other actual data has a lost order. The gender column stores the gender of the prospective customer. The chronological column remembers the age group of prospective customers. If the potential customer's age is between 20 and 29, the chronology remembers "20's". The desired floor plan stores the floor plan desired by the prospective customer. The desired rent column stores the rent desired by the prospective customer. The rent range in which the lower and upper limits of the desired rent are specified may be stored in the desired rent column. The desired area column stores the area desired by the prospective customer. The room ID column stores the room ID of the room proposed to the prospective customer. The contracted rent column stores the contracted rent of the room. The floor plan memorizes the floor plan of the room. The area column stores the area where the room is located.

In the actual data, gender and age are examples of the attributes of prospective customers (borrowers). The attributes may include the occupation, annual income, number of residents, etc. stored in the prospective customer DB13A. The desired floor plan and desired rent are examples of desired conditions. The desired conditions may include the nearest station, school district, and the desire for auto-locking, which are stored in the answer DB 139. Contract rent and floor plans are examples of property information. As property information, information such as the structure and age of the building stored in the property DB 131, information on the entrance and water facilities stored in the basic equipment DB 133, and surrounding environment information such as the nearest convenience store and the nearest main road stored in the surrounding DB 136. , Special notes stored in the special note DB 137, and facility information stored in the facility DB 138 may be included.

Next, the process of generating the decision tree will be described. FIG. 23 is a flowchart showing a procedure example of the decision tree generation process. The control unit 11 of the providing server 1 creates the actual data (step S51). The control unit 11 performs a decision tree analysis using the created actual data (step S52), and generates a decision tree.

FIG. 24 is a flowchart showing a procedure example of the actual data creation process. The process shown in FIG. 24 corresponds to step S51 in FIG. The control unit 11 of the providing server 1 acquires activity information from the history DB 13B (step S61). The activity information to be acquired excludes the in-process ones, and the ones whose results are confirmed and the ones whose status column values are terminated or lost orders are acquired. The control unit 11 selects one to be processed from the acquired activity information (step S62).

The control unit 11 acquires customer information (step S63). The control unit 11 searches the prospective customer DB 13A using the prospective customer ID included in the activity information as a key, and acquires the customer information. The control unit 11 acquires the answer information (step S64). The control unit 11 searches the answer DB 139 using the case ID included in the activity information as a key, and acquires the answer information. The control unit 11 acquires the property information (step S65). The control unit 11 searches the room basic DB 132 and acquires the room basic information by using the room ID stored in each row of the preview property row and the room ID row of the result row included in the activity information as a key. The control unit 11 searches the property DB 131 using the property ID included in the basic room information as a key, and acquires information on the property building.

The control unit 11 acquires other information (step S66). Using the room ID as a key, the control unit 11 searches the basic equipment DB 133 for basic equipment information, searches the additional information DB 134 for additional information about the room, searches the contract condition DB 135 for the contract condition, and specially describes DB 137. Search for special notes. In addition, the control unit 11 searches the peripheral DB 136 using the property ID as a key to acquire environmental information. Further, the control unit 11 uses the case ID as a key to search the additional information DB 13C and acquire the additional information. As other information, which information is to be acquired is determined by the data items included in the actual data.

The control unit 11 generates actual data based on the activity information to be processed, the acquired customer information, the response information, the property / room information, and the basic equipment information, additional information, contract conditions, special notes, environmental information and additional information. It is generated and stored in the actual data DB 13D (step S67).

The attributes of prospective customers included in the actual data can be obtained from the customer information. The desired conditions included in the actual data can be obtained from the response information and additional information. Property information included in the actual data can be obtained from room basic information, property building information, basic equipment information, contract conditions, special notes, and environmental information.

The control unit 11 determines whether or not there is unprocessed activity information (step S68). When the control unit 11 determines that there is unprocessed activity information (YES in step S68), the control unit 11 returns the process to step S62 and processes the unprocessed activity information. When it is determined that there is no unprocessed activity information (NO in step S68), the actual data creation process is terminated.

FIG. 25 is a flowchart showing the procedure of the decision tree analysis process. The process shown in FIG. 25 corresponds to step S52 in FIG. The control unit 11 of the providing server 1 calculates the information gain of the actual data group stored in the actual data DB 13D by brute force (step S81). The control unit 11 calculates the information gain for all the items included in the actual data. The control unit 11 individually calculates the information gain when the actual data group is divided according to the contents of each item included in the actual data.

Further, when the actual data can be classified in a plurality of ways according to the contents of the items included in the actual data, the control unit 11 calculates the information gain for each of the plurality of classification methods. The plurality of classification methods for which the information gain should be calculated may be predetermined for each item. The control unit 11 may calculate the improve value instead of the information gain.

Next, the control unit 11 selects the value (feature amount) of one item to be used for classifying the actual data from the items included in the actual data (step S82). The control unit 11 selects the item from which the maximum information gain is obtained among the calculated information gains. The control unit 11 may make a selection by using the improve value instead of the information gain. Next, the control unit 11 classifies a plurality of actual data by dividing the actual data group into two actual data groups according to the selected feature amount (step S83). The control unit 11 classifies the actual data according to the classification method selected in step S82. By classifying the actual data according to the value of the item that maximizes the information gain, the actual data is classified according to the value of the item in the order of the items that have the greatest influence on the business results.

Next, the control unit 11 determines whether or not there is an actual data group that does not satisfy the classification end condition among the plurality of actual data groups (step S84). The classification end condition is predetermined and is stored in advance in the auxiliary storage unit 13 or included in the control program 1P. An example of the classification end condition is that the number of classifications has reached a predetermined number. Another example of the end condition of classification is that the ratio of data whose business result is a contract or whose business result is a loss of order exceeds a predetermined ratio in the actual data group. Another example of the classification end condition is that the number of actual data included in the actual data group is less than a predetermined number. Another example of a classification termination condition is that the number of performance data groups exceeds a predetermined upper limit.

When the control unit 11 determines that there is an actual data group that does not satisfy the classification end condition (YES in step S84), the control unit 11 selects one good / bad data group that does not satisfy the classification end condition (S85). The control unit 11 returns the process to step S81 and executes the processes of steps S81 to S83 for the selected actual data group. In this way, the control unit 11 recursively repeats the processes of steps S81 to S85 to classify the actual data step by step according to the value of the item in the order of the items having a large influence on the business result.

When there is no actual data group that does not satisfy the classification end condition (NO in step S84), the control unit 11 creates a decision tree that classifies a plurality of actual data in stages, and the created decision tree is stored in the auxiliary storage unit 13. (Step S86). The control unit 11 ends the decision tree analysis process and returns the process to the caller.

FIG. 26 is an explanatory diagram showing an example of a decision tree. The decision tree shown in FIG. 26 is an example of classifying the actual data into two items, the desired rent and the property rent. If the customer's desired rent exceeds 50,000 yen and the introduced property rent exceeds 50,000 yen, the probability of loss of orders is 80% and the probability of closing a contract is 20%. If the customer's desired rent exceeds 50,000 yen and the introduced property rent is 50,000 yen or less, the probability of loss of orders is 20% and the probability of closing a contract is 80%. If the customer's desired rent is 50,000 yen or less and the introduced property rent exceeds 50,000 yen, the probability of loss of orders is 80% and the probability of closing a contract is 20%. If the customer's desired rent is 50,000 yen or less and the introduced property rent is 50,000 yen or less, the probability of loss of orders is 20% and the probability of closing a contract is 80%. Although FIG. 26 shows an example of classifying by two items, the classification result by other items included in the actual data may be reflected in the decision tree. For example, it is a classification based on the desired floor plan and the floor plan of the introduced property.

The process of selecting a room to be proposed to a new prospective customer using the generated decision tree will be described. In the following description, it is assumed that customer information, response information, and additional information about the new prospective customer are acquired and already stored in the prospective customer DB13A, the response DB139, and the additional information DB13C, respectively. FIG. 27 is a flowchart showing another procedure example of the room selection process. The control unit 11 of the providing server 1 acquires customer information from the prospective customer DB 13A (step S91). The control unit 11 acquires the desired information from the response DB 139 and the additional information DB 13C (step S92). The control unit 11 refers to the room basic DB 132 and selects a room to be processed (step S93). The room selected by the control unit 11 is a room whose status column value is vacant, expected to move out, etc., and excludes rooms whose status column value is occupying, applied, etc. The control unit 11 acquires property information from the property DB 131 and the room basic DB 132 (step S94). The control unit 11 acquires other information from the basic equipment DB 133, the additional information DB 134, the contract condition DB 135, the peripheral DB 136, the special note DB 137, the additional information DB 13C, and the like (step S95). Based on the information acquired in steps S91 to S95, the control unit 11 searches the decision tree and acquires the contract probability (step S96). The acquired contract probability is stored in the temporary storage area provided in the main storage unit 12, the auxiliary storage unit 13, etc. in association with the property ID and the room ID. The control unit 11 determines whether or not there is an unprocessed room (step S97). When the control unit 11 determines that there is an unprocessed room (YES in step S97), the control unit 11 returns the process to step S93 and performs the process for the unprocessed room. When the control unit 11 determines that there is no unprocessed room (NO in step S97), the control unit 11 narrows down the rooms based on the contract probability (step S98). For example, the control unit 11 narrows down to the top three rooms with a high probability of closing. The control unit 11 outputs information about the narrowed down room (step S99), and ends the process. Since the room information output by the control unit 11 is displayed on the sales terminal 2, the salesperson proposes a room to the prospective customer accordingly.

In the present embodiment, the following effects are obtained. Since the decision tree generated based on past sales activities is used to determine the room to be proposed to the customer, even a salesperson with little work experience is expected to have a high probability of closing a contract with a prospective customer. It is possible to propose a room.

In the present embodiment, the description has been made on the premise that one decision tree is generated, but the present invention is not limited to this. The actual data may be divided according to some items included in the actual data, and a decision tree may be generated for each divided actual data group. For example, the customer's occupation may be divided into four cases of student, office worker, business owner, and others, and a decision tree may be generated for each divided actual data. In the room selection process, a decision tree to be used is selected according to the attributes of the prospective customer, and the process is performed using the selected decision tree.

(Embodiment 4)
The present embodiment relates to a mode for narrowing down the rooms for which the contract probability is calculated. FIG. 28 is a flowchart showing another procedure example of the room selection process. The room selection process in the present embodiment is a modification of the room selection process in the third embodiment shown in FIG. 27. FIG. 28 shows the changed part. After executing step S92 in FIG. 27, the control unit 11 of the providing server 1 extracts the narrowing-down information (step S100). The information for narrowing down is, for example, the desired floor plan, desired rent, and desired area included in the desired information. The control unit 11 narrows down the room to be processed by using the narrowing down information (step S101). The control unit 11 executes steps S93 and subsequent steps of FIG. 27 with the narrowed room as the processing target.

In the present embodiment, since the room to be processed is narrowed down, it is possible to reduce the processing amount of the room selection process.

(Embodiment 5)
The present embodiment relates to a mode in which a plurality of decision trees are used properly while narrowing down the rooms to be processed as in the fourth embodiment. FIG. 29 is a flowchart showing another procedure example of the room selection process. The room selection process in the present embodiment is a modification of the room selection process in the third embodiment shown in FIG. 27. FIG. 29 shows the changed part. In FIG. 29, the processes in steps S100 and S101 are the same as those in the fourth embodiment, and thus the description thereof will be omitted. After executing step S101, the control unit 11 extracts selection information for selecting a decision tree (step S102). The selection information is, for example, the occupation or family type of the prospective customer. The control unit 11 selects the decision tree to be used by using the selection information (step S103). Using the selected decision tree, the control unit 11 executes steps S93 and subsequent steps of FIG. 27 with the narrowed room as the processing target.

In this embodiment, since the properties / rooms to be processed are narrowed down, it is possible to reduce the processing amount of the room selection process, and it is predicted that the contract probability is high by properly using a plurality of decision trees. It is possible to select a room.

(Embodiment 6)
The present embodiment relates to a form in which a prospective customer accesses the providing server 1 via a network to search and refer to property / room information. Similar to the conventional non-operation information site, the providing server 1 provides property / room information matching the search conditions to prospective customers. At that time, the recommended room information judged using the decision tree is presented. In the following description, it is assumed that the customer terminal used by the prospective customer and the providing server 1 communicate with each other, but the present invention is not limited to this. A Web server that mediates between the customer terminal and the providing server 1 may be provided.

FIG. 30 is a flowchart showing a procedure example of the room search process. The control unit 11 of the providing server 1 acquires desired information from the customer terminal (step S111). The control unit 11 searches for a room that matches the desired information (step S112). The control unit 11 searches the property DB 131 and the room basic DB 132, as well as the basic equipment DB 133, the additional information DB 134, the contract condition DB 135, the peripheral DB 136, the special note DB 137, or the facility DB 138, according to the conditions included in the desired information. If the desired information does not include the condition, the control unit 11 searches for a room that can be moved in immediately. The control unit 11 determines whether or not the search is hit (step S113). When the control unit 11 determines that the search has not been hit (NO in step S113), the control unit 11 shifts the process to step S121. When the control unit 11 determines that the search is successful (YES in step S113), the control unit 11 determines whether or not the information (customer information) about the prospective customer is obtained (step S114). As the customer information, what the prospective customer himself has input to the customer terminal is received from the customer terminal together with the desired information and acquired. Further, on the customer terminal, the behavior history of the prospective customer on the Internet may be stored in a cookie or the like, and the customer information (age, gender, etc.) may be inferred from the behavior history. When the control unit 11 determines that the customer information has not been obtained (NO in step S114), the control unit 11 shifts the process to step S116. When the control unit 11 determines that the customer information has been obtained (YES in step S114), the control unit 11 extracts the information used for the determination by the decision tree from the customer information (step S115). The control unit 11 selects a room to be processed from the rooms that hit the search (step S116). The control unit 11 acquires the information used for the determination by the decision tree from the information regarding the selected room (step S117). The control unit 11 uses the decision tree to acquire the contract probability of the selected room (step S118). The control unit 11 determines whether or not there is an unprocessed room (step S119). When the control unit 11 determines that there is an unprocessed room (YES in step S119), the control unit 11 returns the process to step S116 and performs the process for the unprocessed room. When the control unit 11 determines that there is no unprocessed room (NO in step S119), the control unit 11 sorts the information of the room hit in step S111 (step S120). The control unit 11 generates a screen to be transmitted to the customer terminal (step S121). When transitioning from step S113, the screen to be transmitted generates a screen notifying that the number of hits in the search is 0 (step S121). When the transition is made from step S120, a screen is generated so as to be conspicuously displayed separately from the list for several cases having the highest contract probability. The control unit 11 outputs the generated screen to the customer terminal (step S122), and ends the process.

FIG. 31 is an explanatory diagram showing an example of a search result display screen. The search result display screen d03 includes a display area d031, a recommended area d032, a condition setting area d033, and a search button d034. The display area d031 displays the information of the room that hit the search. The recommended area d032 displays the information of the room determined by the decision tree to have a high probability of closing. The condition setting area d033 is an area for setting search conditions. The search button d034 is a button for instructing a re-search with the search conditions set in the condition setting area d033. The recommended area d032 has, for example, a frame different from the display area d031. In FIG. 31, it is a shaded frame. Further, the recommended area d032 includes a recommended message d0321. As described above, the recommended area d032 is expected to catch the eyes of prospective customers by including a display mode visually different from the display area d031.

The number of recommended areas d032 provided on the search result display screen d03 is arbitrary. It is determined by the contract probability determined by the decision tree. For example, if it is set to display a maximum of three rooms with a contract probability of 75% or more, the recommended area d032 is not displayed unless there is any property with a contract probability of 75% or more. Even if there are 4 or more properties with a contract probability of 75% or more, only 3 recommended areas d032 are displayed. Further, there is no particular limitation on how the display area d031 and the recommended area d032 are displayed, but it is desirable that the recommended area d032 be displayed as high as possible.

This embodiment has the following effects. Since the information of the room determined to have a high contract probability by the decision tree is displayed on the search result display screen d03, the contract rate is expected to be improved.

If there is no property whose contract probability is equal to or higher than the predetermined value, the recommended area d032 is not displayed, but the present invention is not limited to this. If there is no property with a contract probability higher than the specified value, increase the number of applicable rooms by deleting some of the multiple conditions included in the desired information or expanding the range of values. .. Then, with respect to the increased number of rooms, the contract probability is determined by the decision tree, and the one determined to have a high contract probability may be displayed in the recommended area d032. In this case, even if the prospective customer misunderstands the conditions of the room he / she is looking for, the contract rate is expected to improve. In addition, since information on rooms that have not been hit in the search will be displayed in the recommended area d032, in order to inform prospective customers of that fact, the content of the recommended message d0321 is "How about a similar room?" Etc. is desirable.

In the above-described embodiment, it is assumed that one decision tree is used in the room selection process, but a plurality of decision trees may be used. For example, a random forest that creates multiple decision trees from a plurality of arbitrarily selected items from all the items included in the actual data is adopted. In the room selection process, the probability of closing each room is calculated using a random forest.

(Modification example)
This modification includes another example of the room search process shown in the sixth embodiment. FIG. 32 is a flowchart showing a procedure example of the room search process. The customer terminal is transmitted to the providing server 1 by the operation of the prospective customer (step S131). The control unit 11 of the providing server 1 receives the request (step S132). The control unit 11 acquires a cookie from the transmitted request (step S133). If the cookie is not transmitted from the customer terminal, the cookie acquired by the control unit 11 is empty. The control unit 11 determines whether or not there is a room condition (step S134). Here, the control unit 11 determines that there is a condition in the following cases. This is a case where the search button d034 is selected after the conditions are set in the condition setting area d033 on the search result display screen d03, and the desired information of the room is transmitted from the customer terminal. If the same conditions as the condition setting area d033 can be set, it may be sent from a Web form other than the search result display screen d03. In addition, the desired information of the room is not sent to the customer terminal by the form, but is set in the cookie. The control unit 11 determines that there is a condition when the form containing the desired information of the room has not been sent, the cookie is empty, or the cookie is not empty but the desired information of the room is not included. When the control unit 11 determines that there is a room condition (YES in step S134), the control unit 11 acquires the condition from the form and the cookie (step S135). If it has already been acquired when the determination in step S134 is performed, reacquisition is not necessary. The control unit 11 searches for a room that meets the conditions (step S136). The control unit 11 acquires the contract probability for each room that hits the search by using the decision tree (step S137). If the cookie contains analogical attributes of prospective customers, such as gender, age group, occupation, and residential area, a plurality of decision trees may be used properly based on this. For example, use a student decision tree for potential customers who appear to be students. The control unit 11 sorts the room information in descending order according to the contract probability (step S138). The control unit 11 generates a screen to be transmitted to the customer terminal (step S139). The control unit 11 transmits the generated screen to the customer terminal (step S140). The customer terminal receives and displays the screen (step S141). The screen displayed by the customer terminal is the search result display screen d03. The control unit 11 ends the process. As described above, when the prospective customer selects the search button d034 on the search result display screen d03, the room search process is activated and executed from step S131.

When the control unit 11 determines that there is no room condition (NO in step S134), the control unit 11 determines whether or not the number of rooms viewed by the prospective customer is k or more (step S143). A natural number is set in advance for k. The judgment is made from the browsing history of the prospective customer. The browsing history is included in the cookie sent by the customer terminal. Alternatively, the browsing history associated with the ID of the prospective customer may be stored in the auxiliary storage unit 13, and the ID given by the providing server 1 may be acquired from the cookie transmitted by the customer terminal to acquire the browsing history. The browsing history referred to here is different from the history stored in the history DB 13B. When it is determined that the number of rooms viewed by the prospective customer is k or more (YES in step S143), the room information based on the browsing history is acquired (step S144). The control unit 11 executes step S139 and subsequent steps. When it is determined that the number of rooms viewed by the prospective customer is not k or more (NO in step S143), it is determined whether or not there are k or more popular rooms (step S145). Although the same k as in step S143 is used for the determination, another natural number may be used instead of k. A popular room is, for example, the room with the most page views. The room with the largest number of favorites registered by prospective customers may be used. When the control unit 11 determines that there are k or more popular rooms (YES in step S145), the control unit 11 acquires information about the popular rooms (step S146). The control unit 11 executes step S139 and subsequent steps. When the control unit 11 determines that there are no or more popular rooms (NO in step S145), the control unit 11 acquires information about a predetermined room (step S147). The predetermined room is, for example, a preset recommended room. The control unit 11 executes step S139 and subsequent steps.

In this modification, it is possible to obtain a list of rooms even when the prospective customer does not set the room conditions (desired room information). Since prospective customers can obtain room information with few operations, it is less likely that the search will be abandoned due to the complexity of setting conditions. By having the prospective customer set the conditions again after displaying the list, it is possible to prevent the prospective customer from feeling that he / she does not have the information of the room he / she desires.

The process when the room condition is not acquired (NO in step S134) is merely an example, and other processes may be performed. For example, a list may be created and displayed in which all rooms are sorted according to predetermined conditions, in order of cheapest rent, in order of age, newest information (newest order), and the like. Also, if you have not acquired the room conditions but have the analogical attributes of prospective customers, a list of rooms according to the attributes, for example, a list of rooms recommended for students, recommended for office workers in their 20s You may display the room list of. The room list may be created in advance, or may be created each time using the value of the customer layer column of the special note DB 137.

The technical features (constituent requirements) described in each embodiment can be combined with each other, and by combining them, a new technical feature can be formed.
The embodiments disclosed this time should be considered to be exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of claims, not the above-mentioned meaning, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

100 Providing system 1 Providing server 11 Control unit 12 Main storage unit 13 Auxiliary storage unit 131 Property DB
132 Room basic DB
133 Basic equipment DB
134 Additional information DB
135 Contract conditions DB
136 Peripheral DB
137 Special Note DB
138 Facility DB
139 Answer DB
13A Prospect customer DB
13B history DB
13C additional information DB
141 Room selection model 15 Communication unit 1P control program 2 Sales terminal 3 User terminal

Claims (13)

Enter answer information, input data including personal information into the trained model learned with teacher data including answer information, personal information, and contracted property information for questions about real estate properties, and acquire property information.
An output program characterized by having a computer perform processing to output property information that matches the acquired property information. The output program according to claim 1, wherein the teacher data and the input data include additional information including environmental information around the property. The output program according to claim 1 or 2, wherein the property information includes a plurality of property information suitable for the borrower. The property information includes a management type indicating whether or not the property is managed by the company, and any one of claims 1 to 3 is characterized in that the property information whose management type is managed by the company is output. Described output program. Select the property to be viewed based on the property information of the real estate that was viewed together with the property contracted by the lessee but did not reach the contract.
The output program according to any one of claims 1 to 4, wherein the property information and the information of the property to be viewed are output. The computer inputs the answer information, the input data including the personal information into the trained model learned by the teacher data including the answer information, the personal information, and the contracted property information to the question about the real estate, and acquires the property information.
An output method characterized by outputting property information that matches the acquired property information. An acquisition department that acquires property information by inputting answer information and input data including personal information into a trained model learned with teacher data including answer information, personal information, and contracted property information for questions about real estate.
An output device characterized by having an output unit that outputs property information that matches the acquired property information. The attributes of the lessee, the desired conditions for the lessee's property, and the property information as explanatory variables, and the decision tree with the probability of closing the property as the objective variable, the attributes of the lessee, the desired conditions for the lessee's property, and the property information To get the contract probability of the property,
An output program characterized by having a computer perform a process of outputting the acquired contract probability. Obtain the desired conditions for the lessee's property and
Acquire property information that matches at least a part of the acquired desired conditions,
The output program according to claim 8, wherein the acquired property information is input to the decision tree and the contract probability is acquired. The output program according to claim 8 or 9, wherein the borrower's attributes include age, gender or classification. The output program according to any one of claims 8 to 10, wherein the property information corresponding to the higher-order predetermined number of contract probabilities is output. The computer uses the attributes of the borrower, the desired conditions for the borrower's property, and the property information as explanatory variables, and the decision tree with the contract probability of the property as the objective variable, and the attributes of the borrower and the desired conditions for the borrower's property. In addition, enter the property information to obtain the contract probability of the property,
An output method characterized by outputting the acquired contract probability. The attributes of the lessee, the desired conditions for the lessee's property, and the property information as explanatory variables, and the decision tree with the probability of closing the property as the objective variable, the attributes of the lessee, the desired conditions for the lessee's property, and the property information To acquire the contract probability of the property by inputting
An output device including an output unit that outputs the acquired contract probability.

Images