KR102432552B1 - Method of operating real estate trading platform that automatically recommends properties to buyers based on artificial intelligence - Google Patents

Abstract

Provided is a method of operating a real estate trading platform which automatically recommends properties to buyers based on artificial intelligence. The method of operating a real estate trading platform comprises: a step of transmitting seller's personal information and buyer's personal information to a main server by a seller's terminal and a buyer's terminal; a step of uploading the properties to the main server by the seller's terminal; a step of uploading preferred property information to the main server by the buyer's terminal; a step of providing a list for the properties to the buyer's terminal by the main server; and a step of selecting a specific property from the list of properties provided from the main server by the buyer terminal, wherein the main server processes the buyer's personal information and the preferred property information using first artificial intelligence to generate the list of properties.

Description

How to operate a real estate trading platform that automatically recommends properties to buyers based on artificial intelligence

The present invention relates to a method of operating a real estate trading platform that automatically recommends a property to an artificial intelligence-based buyer.

Real estate transaction refers to the legal act of buying, selling, or leasing real estate such as land or buildings by a seller (lessor) and a buyer (lessee) through a contract of sale, lease, or lease.

Recently, as the platform business has been actively conducted, attempts are increasing on real estate trading platforms that support direct transactions between sellers and buyers by providing various legal services to transaction parties without the intervention of a real estate agent.

On the other hand, in the existing real estate trading platform, when the seller uploads a property and the buyer enters the conditions for sale preferred by the buyer, a list of properties is provided according to a preset program.

However, the list of recommended listings programmed by a simple algorithm does not accurately reflect the buyer's preference, so there is a problem in that the buyer often spends a lot of time and effort in finding his/her preferred listing.

On the other hand, artificial intelligence (AI) is a field of computer engineering and information technology that realizes human learning ability, reasoning ability, perceptual ability, and natural language understanding ability through computer programs.

In particular, supervised learning, which is used in the most fields of artificial intelligence, is a method of predicting future values using training data including correct answers (labels). The purity of training data and test data in the data collection stage (for example, accuracy and truthfulness) determines the performance of an AI algorithm.

If a list of recommended properties is provided to the buyer using artificial intelligence in the existing real estate trading platform, the buyer's satisfaction will increase by accurately recommending the properties that match the buyer's preference.

The problem to be solved by the present invention is to provide a method of operating a real estate transaction platform that automatically recommends a property to an artificial intelligence-based buyer.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

The operating method of the real estate platform of the present invention for solving the above-described problems comprises the steps of: transmitting, by a seller terminal and a buyer terminal, personal information of a seller and personal information of a buyer to a main server; uploading, by the seller terminal, to the main server; uploading, by the purchaser's terminal, preferred listing information to the main server; providing, by the main server, a list for sale to the terminal of the buyer; and selecting, by the buyer terminal, a specific article from the list of articles provided by the main server, wherein the main server uses a first artificial intelligence to process personal information of the buyer and information on preferred articles to generate a list for sale. can be characterized.

Buyer personal information includes information about the buyer's gender, age, and occupation, and preferred listing information includes information about the location, number of floors, lake, contract terms, and convenience goods and facilities of the property, and the main server is a virtual Using the first artificial intelligence that learned the dataset set by the manager with the buyer personal information and the virtual preferred sale information as the label value as the feature value, to generate the sale list from the buyer personal information and the preferred sale information can be characterized as

transmitting, by the buyer terminal, satisfaction index information for the listing list to the main server; and generating a second artificial intelligence by the main server processing personal information of the buyer, preference information, listing list, and satisfaction index information, and updating the first artificial intelligence using the second artificial intelligence. can do.

Satisfaction index information is a natural number value for absolute evaluation of the listing provided from the main server, and the main server uses personal information of the buyer, preferred listing information, and listing as a label value, and the satisfaction index information as a feature value as a feature value. It may be characterized by

transmitting contract information to the main server by the seller's terminal and the buyer's terminal and requesting a contract process; providing, by the main server, an electronic contract to the seller terminal and the buyer terminal; The method may further include the step of signing the electronic contract by the seller terminal and the buyer terminal to complete the contract.

In the operating method of the real estate transaction platform of the present invention, at the initial stage of platform operation, a list of properties is generated using an artificial intelligence algorithm that has learned the dataset generated by the manager's work, and when the platform enters the stabilization stage, the number of purchasers accumulated in the operation process By incorporating the data evaluated on this recommended listing list into the dataset and updating the existing AI classification algorithm using the AI algorithm learned based on this, the advantage of providing a continuously upgraded, customized recommendation listing for buyers is have.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a flowchart illustrating a process of an operating method of a real estate transaction platform of the present invention.
Figure 2 is a block diagram showing a system used in the operating method of the real estate transaction platform of the present invention.
3 is a conceptual diagram illustrating that a list for sale recommended to a buyer is generated by artificial intelligence in the operating method of the real estate transaction platform of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully inform those skilled in the art of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural, unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, an operating method 1000 of the real estate transaction platform of the present invention will be described with reference to the drawings. 1 is a flowchart showing a process of a method of operating a real estate transaction platform of the present invention, FIG. 2 is a block diagram illustrating a system used for an operating method of a real estate transaction platform of the present invention, and FIG. 3 is a real estate transaction platform of the present invention It is a conceptual diagram showing that a list of listings recommended to the buyer is generated by artificial intelligence in the operation method of .

Hereinafter, a seller is a legal term that refers to a natural person and a corporation who sells real estate as a party to a real estate sales contract, but is not limited thereto, and may be interpreted in a broad sense including a lessor and a setter of cheonsei right.

In addition, as a legal term, the buyer means a natural person and a corporation that purchases real estate as a party to a real estate sales contract, but is not limited thereto, and may be interpreted in a broad sense including a lessee and a cheonsei right holder.

The operating method 1000 of the real estate transaction platform of the present invention may be performed in a system including the seller terminal 10 , the buyer terminal 20 , the network 30 , and the main server 40 .

The seller terminal 10 and the buyer terminal 20 may be terminals in which a web page, an app page (app list), a program or an application related to the method 1000 of operating a real estate transaction platform of the present invention are provided.

In this case, the seller terminal 10 and the buyer terminal 20 may be implemented as a computer that can be accessed and connected to the remote main server 40 through the network 30 .

In detail, the seller's terminal 10 and the buyer's terminal 20 are wireless communication devices, such as navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), and Personal Handyphone System (PHS). ), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone All kinds of handheld-based wireless communication devices such as (smartphone), smartpad, tablet PC, etc. and wired communication devices such as general desktop PC (Desk-top PC) may be included. The present invention is not limited thereto.

The network 30 refers to a connection structure capable of exchanging information between each node, such as the seller terminal 10, the buyer terminal 20, and the main server 40, and an example of such a network includes RF, 3GPP ( 3rd Generation Partnership Project network, LTE (Long Term Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless) Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, Digital Multimedia Broadcasting (DMB) network, etc. are included, but are not limited thereto. does not

The main server 40 may be a server that provides a web page, an app page, a program, or an application related to the operating method 1000 of the real estate transaction platform of the present invention.

The operating method 1000 of the real estate transaction platform of the present invention includes the steps 100 of the seller terminal 10 and the buyer terminal 20 transmitting personal information of the seller and the personal information of the buyer to the main server 40; Step 200 of the seller terminal 10 uploading the item to the main server 40; Step 300 of the purchaser terminal 20 uploading preferred listing information to the main server 40; providing, by the main server 40, a list for sale to the buyer terminal 20 using a first artificial intelligence (400); Transmitting, by the buyer terminal 20, the satisfaction index information for the listing list to the main server 40 (500); The main server 40 generates a second artificial intelligence by processing the buyer's personal information, the preferred sale information, the sale list, and the satisfaction index information, and updates the first artificial intelligence using the second artificial intelligence (600); Step 700 of the buyer terminal 20 selecting a specific item from the list of items provided from the main server 40; A step 800 of the seller terminal 10 and the buyer terminal 20 transmitting contract information to the main server 40 and requesting the contract process to proceed; providing, by the main server 40, an electronic contract to the seller terminal 10 and the buyer terminal 20 (900); Step 910 of the seller terminal 10 and the buyer terminal 20 to sign the electronic contract to complete the contract; may include a.

In the step 100 in which the seller terminal 10 and the buyer terminal 20 transmit "seller personal information" and "buyer personal information" to the main server 40, the seller and the buyer download a real estate transaction platform program and sign up for membership. The seller and the buyer may each input personal information (name, contact information, gender, age, occupation, ID image, etc.) and transmit it to the main server 40 . In the operating method 1000 of the real estate transaction platform of the present invention, personal authentication may be implemented by performing mobile real-name authentication through personal information of the seller and the buyer.

The step 200 of the seller terminal 10 uploading the property to the main server 40 may be a step in which the seller inputs information on the property that the seller owns. Specifically, the seller provides the address and the number of floors of the property. Administrative information on various items for sale, such as purchase contract, lease contract, jeonse contract, sale price, monthly rent price, deposit value, etc. Whether an air conditioner, a washing machine, furniture, etc. are provided and whether a parking lot is provided) may be uploaded to the main server 40 , but is not limited thereto.

The step 300 in which the buyer terminal 20 uploads the preferred sale information to the main server 40 may be a step in which the buyer inputs information on the item for which he/she wants to contract to the main server 40 .

For example, preferred property information includes the location, number of floors, number of properties for sale, contract conditions (purchase contract, lease contract, jeonse contract, sale price, monthly rental price, deposit value, etc.) and information on various convenience items and facilities (air conditioner, washing machine) , whether furniture, etc. is provided and whether or not a parking lot is provided), but is not limited thereto.

The step 400 of the main server 40 providing the list for sale to the buyer terminal 20 by using the first artificial intelligence is recommended among the seller's items by processing the buyer personal information and the preferred item information in the main server 40. It may be a step of generating a list of items to be recommended to the buyer by selecting the items for sale.

On the other hand, since the data available from the platform is limited in the initial stage of operation of the platform, there may be a problem in that it is not possible to sufficiently secure a dataset for learning the first artificial intelligence. Accordingly, in the operating method 1000 of the real estate transaction platform of the present invention, an artificial intelligence prediction algorithm may be generated with virtual data to generate a listing for sale. A detailed description of generating the above-described first artificial intelligence algorithm will be described later.

The step 500 in which the buyer terminal 20 transmits the satisfaction index information for the listing list to the main server 40 may be a step in which the buyer evaluates the satisfaction with the listing list recommended by the main server 40 . In this case, the satisfaction index information may be a natural number value for absolute evaluation of the listing provided from the main server 40, but is not limited thereto.

The main server 40 generates the second artificial intelligence by processing the buyer's personal information, the preferred sale information, the sale list, and the satisfaction index information, and the step 600 of updating the first artificial intelligence using the second artificial intelligence It may be a step of updating the first artificial intelligence with the second artificial intelligence learned by the buyer's satisfaction index information for the real sale list actually matched with the actual buyer personal information and the actual preferred sale information in the main server 40 .

That is, in the stage of stabilizing the operation of the platform, a new artificial intelligence prediction algorithm that updates the above-mentioned first artificial intelligence algorithm in real time by setting personal information, preferred property information, and satisfaction index information obtained from the platform as a dataset is created. By doing so, you can continuously create an updated listing list. A detailed description of generating the above-described second artificial intelligence algorithm will be described later.

The step 700 in which the buyer terminal 20 selects a specific article from the list of articles provided from the main server 40 may be a step in which the buyer selects a specific article from the list of articles provided from the main server 40 .

In the step 800 of the seller terminal 10 and the buyer terminal 20 transmitting contract information to the main server 40 and requesting the contract process to proceed, the seller and the buyer engage in a chat room and visit to obtain various information and contracts for the property. It may be the stage of acquiring the conditions and mutually agreeing, and then proceeding with the drafting of the contract.

The step 900 of the main server 40 providing the electronic contract to the seller terminal 10 and the buyer terminal 20 is the seller/buyer personal information and contract information (address) and specified sale information in the main server 50 . It may be a step of providing the electronic contract by automatically writing the information in the slot (blank) on the standard contract based on the Accordingly, in the operating method 1000 of the real estate transaction platform of the present invention, there is an advantage that a standard contract written by an expert can be provided to the contracting party without the intervention of a certified real estate agent.

The step 910 of the seller terminal 10 and the buyer terminal 20 signing the electronic contract to complete the contract may be a step in which the seller and the buyer sign the legally reviewed electronic contract to conclude the contract. On the other hand, for the legal stability of the contract, the main server 40 can evaluate whether the signature is genuine (handwriting inspection, etc.), and when the seller and the buyer seal the seals, the seller terminal 10 and the buyer terminal 20 After requesting and receiving the necessary documents for issuance of a seal seal certificate from a public institution as an agent and obtaining a seal seal certificate from a public institution, it is also possible to assess whether the seal is genuine or not.

Hereinafter, the artificial intelligence used in the operating method 1000 of the real estate transaction platform of the present invention will be described in detail. Artificial intelligence (AI) is a field of computer engineering and information technology that realizes human learning ability, reasoning ability, perceptual ability, and natural language understanding ability through computer programs. In particular, supervised learning, which is used in the most fields of artificial intelligence, is a method of predicting a future value using training data including a correct answer (Label).

For reference, machine learning can be defined as a methodology that gives a computer the ability to learn on its own even if it is not explicitly programmed, and this is a method that allows a program to learn patterns of data by itself based on data. Machine learning is divided into supervised learning and unsupervised learning depending on whether the correct answer is specified in the data required for learning, and classification by dividing data into finite categories according to the purpose of use, continuous It is divided into regression, which maps to values, clustering, which groups similar data, and dimensional reduction, which maps multidimensional data to a representative lower dimension.

Deep learning is one of the machine learning techniques and has dramatically improved the performance of machine learning, which has been stagnant for a while. , as a deep learning structure, a deep neural network (DNN) in which a plurality of hidden layers exist between an input layer and an output layer, and a filter required for factor extraction in front of the hidden layer Convolutional Neural Network (CNN) that learns filters together with Here, the high performance of the deep learning model is explained in two ways. First, the neural network is a Universal Approximator that can approximate all kinds of functions by superimposing the weighted sum of functions in each layer. Data can be simulated with high accuracy. Second, in order to classify data well, it is important to properly extract the factors representing the data, and it is possible to extract the optimal factors through filter learning using a spiral neural network. In addition, deep learning is a developed form of a model in the field of artificial intelligence called a neural network, and has a structure in which a hidden layer of an artificial neural network consisting of a hierarchical structure consists of several stages. Recent deep learning models have many inner layers, so the number of weights (meaning the strength of connection) connecting nodes can be up to billions.

In the operating method 1000 of the real estate transaction platform of the present invention, since there is insufficient data to learn artificial intelligence at the initial stage of operation of the platform, the main server 40 manages the personal information of the virtual buyer and the virtual preferred property information as a label value. By using the first artificial intelligence that learned the dataset set as the feature value of the virtual listing list classified by can do.

In this case, the virtual buyer's personal information may include, but is not limited to, information on the virtual buyer's gender, age, and occupation, and the virtual preferred sale information includes the location and number of floors of the virtual buyer's preferred sale. This may include, but is not limited to, information about the lake and the terms of the contract and amenities and facilities. The virtual listing list may include, but is not limited to, information on locations, floors, lakes, contract terms, and convenience goods and facilities of a plurality of listings recommended to a virtual buyer.

Accordingly, the main server 40 learns artificial intelligence from the virtual purchaser personal information (label value), virtual preferred listing information (label value), and virtual listing (feature value), personal information where the actual purchaser is the purchaser When inputting and preferred listing information, a first AI prediction algorithm that outputs a listing of a matching seller can be generated.

Furthermore, in the operating method 1000 of the real estate transaction platform of the present invention, when the operation of the platform is stabilized, artificial intelligence is learned from the data generated within the platform itself, and the second artificial intelligence prediction that provides feedback to the above-described first artificial intelligence algorithm By generating an algorithm, the first artificial intelligence algorithm may be updated in real time.

In detail, the main server 40 uses a second artificial intelligence that learns the personal information of the buyer, the preferred sale information, and the sale list as a label value, and the satisfaction index as a feature value, accumulated by a plurality of users (buyers). It is possible to predict the satisfaction index felt by the buyer when a specific list is recommended to the buyer who prefers the property. Next, the main server 40 uses the virtual purchaser personal information set by the existing administrator to learn the first artificial intelligence, the virtual purchaser's preferred listing information, and the virtual listing list as a label value to the second AI. If you input it, you can predict the buyer's satisfaction index information for it. Next, the main server 40 sets the first artificial intelligence among a plurality of data sets for the virtual buyer personal information and the virtual buyer's preferred listing information and the virtual listing list set by the administrator to learn the first artificial intelligence. The first artificial intelligence by excluding the dataset in which the value of the satisfaction index information derived by input into the intelligence is less than or equal to the average value of the preset satisfaction index (the average value of the satisfaction index evaluated by a plurality of real buyers) from the dataset for learning the first artificial intelligence Intelligence can be updated in real time. In this case, since the first artificial intelligence continuously receives and learns the virtual buyer personal information newly set by the manager, the virtual buyer's preferred property information, and the virtual property list, the absence of learning data does not occur and the user (buyer) ) can evolve according to

The operating method 1000 of the real estate transaction platform of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The above-described program is C, C++, JAVA, machine language, etc. that a processor (CPU) of the computer can read through a device interface of the computer in order for the computer to read the program and execute the methods implemented as a program It may include code (Code) coded in the computer language of Such code may include functional code related to a function defining functions necessary to execute the methods, and control code related to the execution procedure necessary for the processor of the computer to execute the functions according to a predetermined procedure. may include In addition, this code may further include additional information or memory reference related code for which location (address address) in the internal or external memory of the computer should be referenced or additional information necessary for the processor of the computer to execute the functions. can In addition, when the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the functions, the code uses the communication module of the computer to determine how to communicate with any other computer or server remotely. It may further include a communication-related code for whether to communicate and what information or media to transmit and receive during communication.

The storage medium is not a medium that stores data for a short moment, such as a register, a cache, a memory, etc., but a medium that stores data semi-permanently and can be read by a device. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program may be stored in various recording media on various servers accessible by the computer or in various recording media on the computer of the user. In addition, the medium may be distributed in a computer system connected by a network, and computer-readable codes may be stored in a distributed manner.

The steps of a method or algorithm described in relation to an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can realize that the present invention may be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (5)

transmitting, by the seller terminal and the buyer terminal, personal information of the seller and personal information of the buyer to the main server;
uploading, by the seller terminal, to the main server;
uploading, by the purchaser's terminal, preferred listing information to the main server;
providing, by the main server, a list for sale to the buyer terminal using a first artificial intelligence;
selecting, by the buyer terminal, a specific item from a list of items provided from the main server;
transmitting, by the buyer terminal, satisfaction index information for the listing list to the main server; and
generating, by the main server, a second artificial intelligence, and updating the first artificial intelligence using the second artificial intelligence;
Buyer personal information includes information about the gender, age and occupation of the buyer;
Preferred property information includes information about the location, number of floors and lakes, contract terms, and convenience goods and facilities of the property,
The main server uses the first artificial intelligence that learned the dataset in which the virtual buyer personal information and virtual preferred sale information are set as label values and the virtual sale list is set as feature values, create a list,
The main server is a method of operating a real estate transaction platform, characterized in that it learns the second artificial intelligence using the personal information of the buyer, the preference information and the listing list as the label value, and the satisfaction index information as the feature value.
According to claim 1,
Satisfaction index information is a method of operating a real estate transaction platform, characterized in that it is a natural number value for absolute evaluation of the listing provided from the main server.
3. The method of claim 2,
The main server is the personal information of the virtual buyer set for learning the first artificial intelligence, the preference information of the virtual buyer, and the satisfaction index information derived by inputting into the second artificial intelligence among a plurality of datasets for the virtual sale list The dataset in which the value of is less than or equal to the value of the preset satisfaction index is excluded from the dataset for learning the first artificial intelligence, and the newly set personal information of the virtual buyer, the preferred sale information of the virtual buyer, and the virtual sale list are added to the first artificial intelligence. A method of operating a real estate transaction platform, characterized in that the first artificial intelligence is updated in real time by supplying it as the learning data of the
According to claim 1,
transmitting contract information to the main server by the seller's terminal and the buyer's terminal and requesting a contract process;
providing, by the main server, an electronic contract to the seller terminal and the buyer terminal; and
The method of operating a real estate transaction platform, characterized in that it further comprises the step of signing the electronic contract by the seller terminal and the buyer terminal to complete the contract. delete

Images