KR20210073819A - Method and server for recommending personalized real estate information using the consumer choice model - Google Patents

Abstract

According to one aspect of the present application, a method for recommending customized real estate information by using a consumer choice model includes the steps of: generating real estate information data by applying a pre-processing process to real estate information collected through a network; selecting real estate decision-making parameters through a consumer choice model on the basis of the real estate information data; calculating a user weight score for each selected real estate decision parameter by inputting new user information into a real estate information recommendation model when the new user information is input, and generating customized real estate information data including recommended real estate information according to the calculated user weight score; and providing the customized real estate information data to a user terminal. Accordingly, transactions are activated by providing customized real estate information to sellers, buyers, and brokers in the real estate market.

Description

Recommendation method and server for customized real estate information using consumer selection model {METHOD AND SERVER FOR RECOMMENDING PERSONALIZED REAL ESTATE INFORMATION USING THE CONSUMER CHOICE MODEL}

The present invention relates to a method for recommending customized real estate information, and more particularly, to a method and a server for recommending personalized real estate information by analyzing major factors affecting decision-making using a consumer selection model.

Real estate information has traditionally been provided through the human network of real estate agents, but with the development of the Internet, services providing real estate information through the Internet have spread. In particular, it has been widely used for the purpose of helping real estate transaction brokerage by posting real estate sales information through the Internet.

After the Act on Promotion of Provision and Use of Public Data came into effect, a favorable environment was created to obtain, process and utilize real transaction price information and registered information provided by the state as well as real estate sales information provided by individuals. Aside from the service of simply posting and distributing existing real estate information, services that process real estate information and provide users with the necessary information are being developed.

However, real estate information provided by large portals, online sites of small and medium-sized real estate franchise companies, and real estate information provided by advertising agencies, etc., are only providing basic specifications such as the area, amount, and area of real estate for sale. It looks like you can find it, but in order to actually get a contract, you have no choice but to find a real estate sale by calling a number of real estate agents or visiting a real estate agent directly and investing a lot of time and effort.

In general, people generally prefer convenient transportation and a comfortable environment, but due to the high price, they have no choice but to choose the one that has the highest utility within their budget, not the one that has all the requirements they want. However, as the number of factors to consider increases, the more complex and difficult calculation process is required, and the factors to consider in decision-making exponentially increase as the number of properties to be compared increases. will become more This process involves a lot of trouble and mental labor, and people try to refer to the opinions of experts rather than directly dealing with complex problems, and as many people agree with the opinions of specific people, problems such as concentration and price polarization may occur.

It is common to find real estate for sale online, but as the amount of information increases amid the flood of information, it is becoming more difficult to search for and find the information you need. In the past, people have looked at and checked online real estate listings and searched for the best alternative that shows the best utility within a given budget, whether it contains the elements that are right for you, whether the property is included in their budget. This process not only takes a lot of time, but also requires high mental labor, and in particular, in order to additionally monitor, analyze, and make decisions on the daily updated listing information, it is necessary to watch the listing information frequently and for a long time. In other words, in the process of selecting the information that applies to them among the registered properties or the many options so far, people must go through a repeated decision-making process to constantly collect and process the necessary information, and put enough time and effort into it. For ordinary people who cannot do it, it is not easy to process vast amounts of information and find the best choice for them.

In the prior art, there is a lack of methods to quantify and quantify an abstract value system in the process of making decisions. You can automate the evaluation of specific properties that you depended on. This means that the existing analog decision-making model (although information is disclosed online, but the analysis and decision-making of the information is ultimately made in the head) is converted to digital, through which machines can replace vast online resources with humans. It can help information collection, processing, and decision-making, and this digitization increases data utilization so that various applications can be created through linkage with large-capacity databases, automation, and increase in processing capacity.

Republic of Korea Patent Publication No. 10-2009-0126474 (Title of the invention: customized real estate information provision system)

The present invention provides a method for recommending real estate customized information using a consumer selection model to solve the problems of the prior art.

By extracting key parameters that influence consumers' decision-making, a consumer selection model is constructed, and individual weights are calculated using element-specific value analysis techniques to provide personalized information.

However, the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.

As a technical means for solving the above-described technical problem, the method for recommending customized real estate information using a consumer selection model according to the first aspect of the present disclosure is to generate real estate information data by applying a pre-processing process to real estate information collected through a network. step; selecting a real estate decision parameter through a consumer selection model based on the real estate information data; When new user information is input, the new user information is input into the real estate information recommendation model to calculate the user weight score for each selected real estate decision parameter, and according to the calculated user weight score, customized real estate information data including recommended real estate information is generated. to do; and providing customized real estate information data to the user terminal. At this time, in addition to real estate information collected through the network, real estate information data can be generated by applying a pre-processing process, including information directly or indirectly generated by users and information collected offline.

As a technical means for solving the above technical problem, the real estate customized information recommendation server using the consumer selection model according to the second aspect of the present disclosure includes a memory in which a real estate customized information recommendation program using the consumer selection model is stored; It includes a processor for executing a program stored in the memory. The processor generates real estate information data by applying a pre-processing process to real estate information collected through the network by executing the program, selects real estate decision parameters through a consumer selection model based on the real estate information data, and new user information When is input, new user information is entered into the real estate information recommendation model to calculate the user weight score for each selected real estate decision parameter, and according to the calculated user weight score, customized real estate information data including recommended real estate information is generated, and customized Real estate information data is provided to the user terminal.

According to any one of the above-described problem solving means of the present application, by providing customized real estate information to sellers, buyers, and brokers in the real estate market, it is possible to activate transactions and rationally change the structure of the real estate market.

By using the consumer selection model and using the real estate-customized information recommendation method, it is possible to reduce the time and effort required to collect, manage, and make decisions on a vast amount of online real estate information. By structuring the preference system for each unclear element, measuring the sensitivity of each element, and standardizing and digitizing the atypical value system that stayed in the head, you can directly utilize the vast amount of real estate data to search and analyze the optimal choice for the user from the vast amount of information. . In addition, it prevents the tyranny of existing real estate agents who post false listings online to induce contact with customers and then introduces other listings, and recommends listings to customers based on actual listings. By fundamentally changing consumer-oriented, market efficiency and trust can be improved at the same time.

1 is a block diagram illustrating a configuration of a real estate customized information recommendation server using a consumer selection model according to an embodiment of the present invention.
2 is a block diagram illustrating a configuration of a real estate customized information recommendation system using a consumer selection model according to an embodiment of the present invention.
3 is a flowchart illustrating a process step of a method for recommending customized real estate information using a consumer selection model according to an embodiment of the present invention.
4 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
5 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
6 is a view for explaining the step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
7 is a view for explaining the step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.

Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present application pertains can easily implement them. However, the present application may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present application in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout this specification, when a part is said to be "connected" with another part, it includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. do.

Throughout this specification, when a member is said to be located “on” another member, this includes not only a case in which a member is in contact with another member but also a case in which another member is present between the two members.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating a configuration of a real estate customized information recommendation server using a consumer selection model according to an embodiment of the present invention.

As shown, the real estate customized information recommendation server 100 using the consumer selection model may include a communication module 110 , a memory 120 , a processor 130 , a database 140 , and an input module 150 .

The communication module 110 communicates data with the connected user terminal 100 and the interworking server 200, respectively. The communication module 110 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals through wired/wireless connection with other network devices.

The memory 120 stores a real estate customized information recommendation program using a consumer selection model. The real estate customized information recommendation program using the consumer selection model generates real estate information data by applying a pre-processing process to the real estate information collected through the network, selects real estate decision-making parameters through the consumer selection model based on the real estate information data, and , when new user information is input, the new user information is input into the real estate information recommendation model to calculate a user weight score for each selected real estate decision parameter, and customized real estate including recommended real estate information according to the calculated user weight score Generate information data, and provide the customized real estate information data to the user terminal.

In the memory 120 , various types of data generated during the execution of an operating system for driving the real estate customized information recommendation server 100 using the consumer selection model or the real estate customized information recommendation program using the consumer selection model are stored in the memory 120 .

In this case, the memory 120 collectively refers to a non-volatile storage device that continuously maintains stored information even when power is not supplied, and a volatile storage device that requires power to maintain the stored information.

In addition, the memory 120 may perform a function of temporarily or permanently storing data processed by the processor 130 . Here, the memory 120 may include magnetic storage media or flash storage media in addition to the volatile storage device requiring power to maintain stored information, but the scope of the present invention is limited thereto. it's not going to be

The processor 130 executes the program stored in the memory 140 , but controls the entire process according to the execution of the real estate customized information recommendation program using the consumer selection model. Each operation performed by the processor 130 will be described in more detail later.

The processor 130 may include any type of device capable of processing data. For example, it may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed as a code or instruction included in a program. As an example of the data processing device embedded in the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific (ASIC) An integrated circuit) and a processing device such as a field programmable gate array (FPGA) may be included, but the scope of the present invention is not limited thereto.

The database 140 stores or provides data required for a real estate customized information recommendation system using a consumer selection model under the control of the processor 130 . The database 140 may be included as a component separate from the memory 140 , or may be built in a part of the memory 140 .

2 is a block diagram illustrating a configuration of a real estate customized information recommendation system using a consumer selection model according to an embodiment of the present invention.

The real estate customized information recommendation method using the consumer selection model may be implemented in the server 100 or the user terminal 200 . Data analysis based on the collected real estate information may be performed in the server 100 , and customized real estate information data may be provided to the user terminal 200 .

3 is a flowchart illustrating a process step of a method for recommending customized real estate information using a consumer selection model according to an embodiment of the present invention.

The processor 130 generates real estate information data by applying a pre-processing process to real estate information collected through a network.

The processor 130 may recognize and group a plurality of real estate information for the same real estate as one integrated group by applying a pre-processing process. For example, information on the same sale registered on a plurality of real estate information platforms can be organized into one piece of information, or information about the same sale item uploaded by each real estate agent on the same real estate information platform can be integrated into one piece of information. In addition, the processor 130 may filter the currently invalid real estate information in consideration of the upload timing of real estate information, whether the transaction is completed, and the like.

The real estate information data includes individual real estate feature data and real estate environment information, and the individual real estate feature data includes one or more of price information, structure information, size information, number of floors, facility aging information, public facility information, or parking information, , the real estate environment information may include one or more of traffic information, school district information, or surrounding environment information.

The processor 130 selects a real estate decision parameter through a consumer selection model based on the real estate information data.

The processor 130 may quantitatively analyze major factors affecting decision-making during a real estate transaction through a consumer selection model to select parameters affecting decision-making. For example, when a user selects a real estate, it is possible to extract parameters for size, structure, age, traffic information, school district information, complex size, etc., and determine the payment intention according to the parameter change while adjusting the value of each parameter. have. At this time, the real estate decision parameters may be sorted in the order of the parameters with the highest payment intention, and the real estate decision parameters to be used for the real estate recommendation may be selected according to the set criteria.

The processor 130 may receive new user information from the user terminal.

The new user information may include one or more of age, gender, job information, work location information, preferred area information, acquaintance information, budget information, and purchase purpose information.

The processor 130 may then provide a user value evaluation test to the user terminal, receive the user value evaluation test result, and include it in the new user information.

The user value evaluation test consists of step-by-step question information, "fitness to go to work (subway/bus/car)", "suitability to study (school/hakwon)", "suitability for shopping (mart facilities, department stores)", "fitness to eat out" (Fast food, Korean restaurant, cafe, etc.) Fit", "Delivery order (number of companies listed on the mobile app for the user's residential area) Suitability", "Late night walking (safety) suitability", "Parking It may consist of questions such as “fitness”, “fitness to go to the hospital”, “fitness to exercise”, and “fitness to walk”.

Separately, the processor 130 may collect the user's information while repeating the steps of presenting two pieces of real estate information to the user through a user value evaluation test and allowing the user to select preferred real estate information.

For example, the processor 130 may provide different prices for each real estate information, and may determine the intention to pay for each parameter of the real estate information according to the user's repeated selection.

The processor 130 calculates a user weight score for each selected real estate decision parameter by inputting new user information into the real estate information recommendation model.

The real estate information recommendation model may be to calculate a user weight score using a value analysis technique for each element, and generate recommended real estate information according to the weight score. Elemental value analysis is a technique for predicting which product a customer will choose by estimating the value that a customer attaches to each attribute of a product or service. It is one of the methods for measuring specific factors of consumer behavior. . When consumer behavior is triggered with a specific goal, various psychological factors of the consumer are involved, and the purchase decision mechanism becomes more complex, so it is necessary to conduct research in advance and analyze customer preferences and results to provide product can be optimized.

The real estate information recommendation model may be learned using an artificial neural network by inputting the real estate information data and new user information, calculate a user weight score, and generate recommended real estate information according to the weight score. Also, after providing the customized real estate information data to the user terminal, the method may further include evaluating the accuracy of the recommended real estate information, and updating the evaluated accuracy in the real estate information recommendation model.

The real estate information recommendation model can use any one of collaborative filtering, content-based filtering, and hybrid, which predicts users' preferred information by analyzing information such as users' usage patterns and consumption records. , it is also possible to use a recommendation model using an artificial neural network.

When extracting text from real estate information data, the processor 130 may extract text by performing logistic regression on each word in the collected information using a text extraction module based on a recurrent neural network. In this case, the recurrent neural network may use bidirectional LSTM (Long Short Term Memory models).

The processor 130 generates customized real estate information data including recommended real estate information according to the calculated user weight score.

The processor 130 provides the customized real estate information data to the user terminal.

4 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.

In the method of recommending real estate customized information, new user information can be collected through membership registration, etc. The main personal information is as follows.

As the composition of the family that will be living in the future, it is possible to collect information about adults, children's age, school age, number of people, whether there are additional family plans, and pet information. You can collect information on your current residence, major bases, most frequently visited points, frequency of visits, means of transportation, and movement routes. A plurality of preferred local information may be collected. Additionally, age, car ownership, type of car, and hobby information related to real estate selection can be collected.

Factor-by-factor value analysis can be leveraged to leverage the new user information collected to construct questions for screening real estate decision parameters through a consumer choice model.

A question for prioritizing real estate decision-making parameters is shown in FIG. 4 . For example, the steps of providing the user with two pieces of real estate information and selecting the preferred real estate information may be repeated several times.

5 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.

The question of FIG. 5 is for prioritizing locations. When a preferred location is selected on the map, user value evaluation is possible according to the selection. For example, if a preferred location is selected based on a component including a school, a subway, a company, and a department store, the weight of each component may be increased according to the selection. You can evaluate location preference by repeating the question.

6 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.

For example, the steps of providing the user with two pieces of real estate information and selecting the preferred real estate information may be repeated several times. At this time, by changing the price in the same question and repeating the question, it is possible to determine how much willingness to pay for each component is.

7 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.

For example, the value system of Mr. A can be evaluated through new user information collection and user value evaluation test, and the score for each parameter of K apartment can be evaluated from the collected real estate information data, and by combining the results, Mr. A's K An expected evaluation score for the apartment can be calculated. In addition, it is possible to calculate the K apartment evaluation score for a specific group such as the middle class in their 30s in Seoul.

In another embodiment, a method for recommending customized real estate information using a consumer selection model may transmit step-by-step question information to a user terminal for step-by-step collection of lifestyle data, and store the answer result in a database.

The server 100 accumulates, for each parameter, a relative rating for a region and a community of a user who operates each user terminal 200 as a 'first staged question information category'. The question could be: The server 100 asks the user who operates the user terminal 200 "information about the area where they live, apartment", receives the address information as answer information, and transmits the address information to the address information providing server, A dwelling corresponding to the information may receive information on the size of a building or apartment.

Next, the server 100 collects answer information for each parameter as to whether it is a good place to live through the lifestyle of the user who operates each user terminal 200 as a 'second stage question information category' do.

More specifically, the server 100 additionally includes a machine learning module for a lifestyle question (Action oriented question), and statisticizes the evaluation value for each parameter answer by the machine learning module.

Here, as lifestyle questions, "fitness to go to work (subway/bus/car)", "suitability to study (school/credentials, etc.)", "shopping (mart facilities, department stores, etc.)", "eating out (fast food, Korean food)" "House, cafe, etc.) fit", "Delivery order (the number of companies listed on the mobile app for the user's residential area) suitability", "Late-night walking (safety) suitability", "Parking junction", " After transmitting the “fitness to go to hospital”, “fitness to exercise”, “fitness to walk”, etc. to the user terminal 200 through the network, the first to nth steps for each parameter (n is a natural number greater than or equal to 2) The divided parameter scores are collected and stored in the database.

Thereafter, when the server 100 accumulates big data for a preset area including the user's residence for a preset period, the common denominator of users for an apartment or region comes out, and a rating for each parameter is obtained. perform the extraction process. More specifically, the server 100 receives the size information of the building or apartment as answer information for the 'first-stage question information category', and then the 'second-stage question information category in the area for the building or apartment. As the answer information for ', a rating for each parameter for lifestyle is recommended and stored in the database.

Thereafter, the server 100 performs an individual house characteristic data accumulation process from each seller's terminal or real estate broker's terminal through the network. That is, since the server 100 needs to collect data on the detailed characteristics of individual houses, 'individual house characteristic data' directly from a real estate broker terminal operated by a real estate broker who intends to sell real estate or a seller terminal operated by the landlord It can be received, and it can be collected by extracting a source from big data stored in an external server. The individual house characteristic data may include the number and structure of rooms, the size of each room, the number of floors, the degree of deterioration of the facility (toilet, sink, floor, etc.), and state information of public facilities (security room, elevator, hallway, etc.).

Here, with respect to 'number and structure of rooms' among 'individual house feature data', the most similar big data stored in the real estate brokerage server via intranet by each real estate agent terminal is followed by the selection signal received from the real estate agent terminal or the seller terminal. It may be collected in a way the real estate agent or seller selectively chooses.

In addition, when collecting 'individual room size' among 'individual house characteristic data', if the real estate agent terminal and the seller terminal are a smart phone or smart pad equipped with a computing function, a floor plan that automatically draws a floor plan through camera shooting The method of collecting the floor plan drawn through the drawing app, or the method of collecting the calculated room size information through the room area calculation app that automatically calculates the size of the room automatically through camera shooting based on the wall of the individual room can be done with

After access to the server 100 through the network for a real estate search request including weight information for each parameter of the lifestyle data to live in of the user terminal 200 and each parameter information of individual house characteristic data, the server ( 100) can perform matching with scores for each parameter generated by statisticizing evaluation values in the step-by-step collection of lifestyle data, and analysis of individual houses having the closest information to each parameter information of individual house characteristic data. .

The server 100 extracts high-ranked real estate listing information up to a preset rank matching the score for each parameter and individual house characteristic data, and provides it to the user terminal 200 requesting a real estate search through the network. That is, in the stage corresponding to the new user, score analysis for each parameter for the user who requested real estate search is performed, and whether the score for each parameter is matched or not, as well as each parameter information of individual house characteristic data By analyzing whether or not it matches, it is possible to provide real estate sales information for the top five, for example, a preset ranking that matches the most. For this real estate sale information, the server 100 said, "As a result of analyzing the data of 2800 people in the area, which apartment house, which lake, and what price is the house that you would like among them. You can provide online services through the message "We have the following items on the list..."

After the user terminal 200 accesses the server 100 for a real estate search request, it is possible to analyze the score for each parameter in the step-by-step collection of lifestyle data. That is, after access to the server 100 through the network for a real estate search request including weight information for each parameter of the lifestyle data of the user terminal 200 and each parameter information of individual real estate characteristic data, The server 100 performs analysis of individual real estate having the closest information to each parameter information of individual real estate feature data and matching with scores for each parameter generated by statisticizing evaluation values in the step-by-step collection of lifestyle data. Then, create a list of individual real estate.

The server 100 collects profile information from the user terminal 200 . Information about each user's profile collects information about the area, locality, facilities, acquaintances, budget, and authenticity to find.

For the local information to be found here, you can ask for the area with a regional area/metro area, etc. or select a target area on the map (a method in which a person looking for the boundary of a specific district selects two specific districts), and for locality information, "Which of the following keywords or hashtags do you think is important? Quiet/Residential/Hangang/Park/Promenade/Educational conditions/Subway/City/Clean air/Hospital/..." Select through questions, and for information on facilities, choose from options such as "Old-New Building/Apartment-Outside of Apartment/Low-Rise-High-Rise/Parking Lot/View/Sunshine (South-facing)/..." For information on size, please refer to "People living together (O people in direct line, O other people), gender and age living together, number of rooms, size (30 pyeong, 40 pyeong, 50 pyeong), number of bathrooms, balcony extension, ..." Select from the same options, and for acquaintance information, select from options such as "address of people who want to live close, address of people who want to live far away, ..,", and for budget information, the net investment possible (server (100 ), it has a calculation module for purchasing while maintaining loan and charter status), and for information about authenticity, it is a web site to analyze whether a house is really recognized as a joke or a curiosity. It can also be identified through site response speed or behavioral patterns, and collected through payment of the returned deposit of 30,000 won.

The server 100 hides the provided information and personal identification information of each user and transmits the individual house list and profile information to the designated real estate agent terminal, so that the real estate matched by the real estate agent through the matching of the profile information and the profile information A recommendation to the user terminal 200 that has performed the steps for the item for sale is performed.

In this case, the server operator can acquire a commission for the real estate broker who operates the designated real estate agent terminal, while the real estate brokers are sincere and target customers who will like the real estate sale they have. opportunity may be provided.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Although the methods and systems of the present invention have been described with reference to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The above description of the present application is for illustration, and those of ordinary skill in the art to which the present application pertains will understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present application.

100: server
110: communication module
120: memory
130: processor
140: database
150: input module
200: user terminal

Claims (10)

In the real estate customized information recommendation method using the consumer selection model performed by the server,
(a) generating real estate information data by applying a pre-processing process to real estate information collected through a network;
(b) selecting a real estate decision-making parameter through a consumer selection model based on the real estate information data;
(c) when new user information is input, inputting the new user information into a real estate information recommendation model, calculating a user weight score for each selected real estate decision parameter, and including recommended real estate information according to the calculated user weight score generating customized real estate information data; and
(d) providing the customized real estate information data to a user terminal; including,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
The pre-processing process comprises the steps of recognizing and grouping a plurality of real estate information for the same real estate as one integrated group, and filtering real estate information corresponding to a preset condition,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
The real estate information data includes individual real estate characteristic data and real estate environment information,
The individual real estate characteristic data includes at least one of price information, structure information, size information, the number of floors, age information of facilities, public facility information, or parking information,
The real estate environment information will include one or more of traffic information, school district information, or surrounding environment information,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
The new user information will include one or more of age, gender, job information, work location information, preferred area information, acquaintance information, budget information, or purchase purpose information,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
After the step (b), a user value evaluation test is provided to the user terminal, and the new user information input in the step (c) includes the user value evaluation test result,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
The real estate information recommendation model calculates a user weight score using a value analysis technique for each element, and generates recommended real estate information according to the weight score,
A method of recommending information tailored to real estate using a consumer choice model. The method of claim 1,
The real estate information recommendation model is learned using an artificial neural network by inputting the real estate information data and new user information, calculates a user weight score, and generates recommended real estate information according to the weight score,
A method of recommending information tailored to real estate using a consumer choice model. 8. The method of claim 7,
Evaluating the accuracy of the recommended real estate information after step (d), further comprising the step of updating the evaluated accuracy to the real estate information recommendation model,
A method of recommending information tailored to real estate using a consumer choice model. In the real estate customized information recommendation server using the consumer selection model,
a memory in which a real estate-customized information recommendation program using a consumer selection model is stored;
A processor for executing the program stored in the memory, wherein the processor by the execution of the program,
Apply a pre-processing process to real estate information collected through the network to generate real estate information data
Select a real estate decision parameter through a consumer selection model based on the real estate information data,
When new user information is input, the new user information is input into the real estate information recommendation model to calculate a user weight score for each selected real estate decision parameter, and customized real estate information including recommended real estate information according to the calculated user weight score create data,
providing the customized real estate information data to a user terminal,
Real estate customized information recommendation server using consumer selection model. A non-transitory computer-readable recording medium on which a computer program for performing the method according to claim 1 is recorded.

Images