KR102008992B1 - Secretary service apparatus and the same methods using chatbot for real estates transaction - Google Patents

Abstract

Disclosed is a real estate transaction secretary service method which comprises the operations of: receiving natural language input from a user terminal; analyzing the natural language input to extract a first search condition related to real estate; searching for real estate offering information based on the first search condition; setting a priority for the plurality of searched real estate offering information; and transmitting the searched real estate offering information to the user terminal based on the priority.

Description

Real estate transaction secretary service apparatus and method using chatbot {SECRETARY SERVICE APPARATUS AND THE SAME METHODS USING CHATBOT FOR REAL ESTATES TRANSACTION}

The present invention relates to a real estate secretary service apparatus and method using a chatbot, and more particularly, to provide a user with priorities of real estate information searched from a search word extracted from a user's natural language input.

In recent years, many consumers are using the Internet to trade real estate, and information on a number of real estate listings is posted on various real estate trading sites or applications.

The user has a disadvantage of finding various real estate transaction sites or downloading and searching real estate transaction applications in order to obtain his or her favorite real estate information.

However, real estate transaction sites such as Internet portal sites provide a very complex interface to satisfy various real estate transaction users such as apartments, officetels, malls or buildings at once, so that users who do not frequently do real estate transactions prefer their property information. It is difficult to find.

In addition, it is difficult for a user to grasp his or her favorite real estate for sale from the real estate for sale information searched through several search terms, and only after comparing each real estate for sale information, there is a problem that the user can grasp the desired real estate for sale.

Republic of Korea Patent Publication No. 10-2016-0031111 (2016.3.22)

When a conventional information provider provides real estate for sale information through an internet site or an application, it is easy to use and easily obtains the user's preferred real estate for sale, which is difficult for the user to grasp his or her preferred real estate. There is a need for a real estate transaction assistant service apparatus and method.

In addition, there is a need for a real estate transaction assistant service apparatus and method capable of reflecting preferences for various conditions of individual users, as well as a method for retrieving real estate information using only simple conditions such as conventional prices and locations.

This specification proposes a real estate transaction secretary service method. The real estate transaction assistant service method may include receiving a natural language input from a user terminal, extracting a first search condition related to real estate by analyzing the natural language input, and searching for real estate property information based on the first search condition. And setting priority of the retrieved real estate for sale information and transmitting the retrieved real estate for sale information to the user terminal based on the priority.

The service method and other embodiments may include the following features.

The real estate transaction assistant service method may include receiving lifestyle information from the user terminal or any lifestyle information including any one of a family composition form, a work location, a car possession status, a gender information, an age information, and a pet possession or the information data of the user. The method may further include an extracting operation, wherein the searching of the real estate for sale information or the setting of the priority may be based on the first search condition and the lifestyle information.

The real estate transaction secretary service method may receive real estate preference information from the user terminal including any one of a preferred building year, expected time of moving in, preferred floor, room layout type, or layout direction of a house, or from information data of the user. The method may further include an extracting operation, wherein the searching of the real estate for sale information or the setting of the priority may be based on the first search condition and the housing preference information.

The setting of the priority in the real estate transaction assistant service method is based on a machine learning engine trained with data including usage method information of users for the retrieved real estate for sale information, and the usage method information is retrieved by the users. A plurality of real estate for sale information may include any one of the information clicked on the real estate for sale information, the information contacted with the property information provider, visited the searched real estate information or the contract closing information using the searched real estate information; Of these, the same information may be prioritized based on the information of the information provider, including any one of customer satisfaction, sales period of the information provider, commission of the information provider or the number of false listings of the information provider. And check the real estate for sale information. Action that may be from a second server operable to receive at least some of the search results sent, and from the second server of the first search condition.

Another embodiment of the real estate transaction assistant service method includes receiving a natural language input from a user terminal, extracting a first search condition related to the real estate by analyzing the natural language input, and searching for real estate information based on the first search condition And clustering the plurality of searched real estate information based on a preset condition with respect to the plurality of searched real estate information, generating average information of real estate information belonging to the same cluster, and the plurality of clusters. And providing the average information to the user terminal based on a map form.

The real estate transaction assistant service method includes receiving a request related to the change of the map form from the user terminal, re-clustering the plurality of retrieved real estate information based on a request related to the change of the map form and a preset condition. And providing the average information on the plurality of clusters re-clustered to the user terminal based on a map form.

On the other hand, the present specification proposes a real estate transaction secretary service apparatus. The real estate transaction assistant service apparatus receives a natural language input from a user terminal, and transmits the searched real estate information to the user terminal based on the priority, and analyzes the natural language input to extract a first search condition related to real estate An extractor, a controller configured to search for real estate for sale information based on the first search condition, and to set the priority of the found plurality of real estate for sale information, among intermediate data, final data, or user data of the controller and the search unit; It may include a storage unit for storing at least one.

Another embodiment of the real estate transaction secretary service apparatus receives a natural language input from a user terminal, and provides a communication unit for providing the average information for a plurality of clusters to the user terminal based on a map form, analyzing the natural language input to analyze the natural language input 1, an extraction unit for extracting a search condition, searches for real estate for sale information based on the first search condition, clusters the plurality of searched real estate informations based on a preset condition, and compares the real estate information belonging to the same cluster. The control unit may generate the average information, and the storage unit may store at least one of intermediate data, final data, and user data of the control unit and the search unit.

According to the embodiments disclosed herein, real estate information can be easily obtained through natural language input through a ChatBot.

According to the embodiments disclosed in the present specification, real estate property information such as various real estate sites and applications may be acquired at a time through the chatbot.

According to the embodiments disclosed herein, the real estate for sale information may be obtained in the order of priority reflecting the user's preference.

According to the embodiments disclosed in the present specification, a lot of real estate for sale information can be grasped in a macro form and a micro form to obtain desired property information more easily.

1 and 2 schematically show a real estate transaction secretary service apparatus.
3 is a flowchart illustrating an operation of a real estate transaction assistant service method.
4 is a diagram illustrating an interface of a real estate transaction assistant service method.
5 is an embodiment of data for machine learning.
6 is an embodiment of lifestyle information.
7 is an embodiment of real estate preference information.
8 is a flowchart illustrating another operation of the real estate transaction assistant service method.
9, 10 and 11 illustrate another interface of the real estate transaction assistant service method.
12 is an exemplary block diagram of a real estate transaction secretary service apparatus.

The technology disclosed herein may be applied to a real estate transaction assistant service apparatus and method using a chatbot. However, the technology disclosed herein is not limited thereto, and may be applied to all electronic devices and methods to which the technical spirit of the technology may be applied.

It is to be noted that the technical terms used herein are merely used to describe particular embodiments and are not intended to limit the spirit of the technology disclosed herein. In addition, the technical terms used herein should be construed as meanings generally understood by those skilled in the art to which the technology disclosed herein belongs, unless defined otherwise in this specification. It should not be interpreted in a comprehensive sense, or in an overly reduced sense. In addition, when the technical terms used herein are incorrect technical terms that do not accurately express the spirit of the technology disclosed herein, technical terms that can be properly understood by those skilled in the art to which the technology disclosed herein belongs. It should be replaced by. In addition, the general terms used herein should be interpreted as defined in the dictionary, or according to the context before and after, and should not be interpreted in an excessively reduced sense.

As used herein, terms including ordinal numbers such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments disclosed herein will be described in detail with reference to the accompanying drawings, and the same or similar components will be given the same reference numerals regardless of the reference numerals, and redundant description thereof will be omitted.

In addition, in describing the technology disclosed herein, if it is determined that the detailed description of the related known technology may obscure the gist of the technology disclosed herein, the detailed description thereof will be omitted. In addition, it is to be noted that the accompanying drawings are only for easily understanding the spirit of the technology disclosed in this specification, and the spirit of the technology should not be construed as being limited by the accompanying drawings.

1 schematically illustrates an embodiment including a real estate transaction assistant service apparatus 110 using a chatbot. The real estate transaction assistant service device 110 using the chatbot may communicate with one or more user terminals 120 through the network 130.

The user terminal 120 may be connected to the network by wire / wireless to communicate with the real estate transaction assistant service device 130. The user terminal 120 of the embodiments disclosed herein includes not only a personal computer (PC) but also a tablet computer, a smart phone, and the like.

The networks disclosed herein include, for example, wireless networks, wired networks, public networks such as the Internet, private networks, global systems for mobile communication networks (GSM) networks, general packet wireless networks (general) packet radio network (GPRS), local area network (LAN), wide area network (WAN), metropolitan area network (MAN), cellular network, public switched telephone network PSTN, personal area network, Bluetooth, Wi-Fi Direct, Near Field communication, UltraWide band, combinations thereof, or any other It may be a network, but is not limited to these.

The user terminal may request real estate for sale information from the real estate transaction assistant service device 110 in a natural language through a chatbot interface which will be described below, and the real estate transaction assistant service device 110 receives the natural language input received from the user terminal 120. After searching and extracting a search condition, the search result from the real estate for sale information database held may be transmitted to the user terminal 12 based on the priority.

2 schematically shows another embodiment including a real estate transaction assistant service apparatus 211 using a chatbot. The real estate transaction assistant service device 211 using a chatbot may communicate with one or more user terminals 220 and other search or real estate information devices 212 through the network 230.

The real estate transaction assistant service device 211 analyzes the natural language input received from the user terminal 220 and extracts a search condition, and then corresponds to a search result or other search device or real estate information device 212 obtained from the real estate for sale information database. After transmitting the search condition, the returned search result may be transmitted to the user terminal 220 based on the priority.

The other retrieval device or real estate information device 212 may be an Internet portal server, a real estate information server, a retrieval server, or a device providing an application program interface (API) for requesting a search to the servers, and the type thereof is not particularly limited. Do not.

3 is a flowchart illustrating an operation of a service method of the real estate transaction assistant service apparatuses 110 and 211 using a chatbot. The real estate transaction assistant service method described below may be performed after the user terminals 120 and 220 request real estate sale information from the real estate transaction assistant service apparatus 110 or 211.

The user terminals 120 and 220 may request real estate for sale information through the natural language input 410 through the interface as shown in FIG. 4 (S310). The interface as shown in FIG. 4 may be performed through an application such as a smartphone, or may be performed through a page implemented in a web language such as Java Script of an Internet site.

The real estate transaction assistant service apparatus 110 or 211 may extract the first search condition through morphological analysis and natural language analysis on the natural language input received from the user terminals 120 and 220 (S320).

As a basic search condition for real estate property information retrieval, the search condition for real estate type, price, or location such as apartment, officetel, villa, and detached house is extracted through analysis from natural language input received from user terminals 120 and 220 can do.

In the case of FIG. 4, the search condition for the location of the automatic location, the real estate type of the apartment, and the price of one billion won could be extracted from the user's first natural language input 410. If only extractable, the real estate transaction assistant service device 110, 211 may transmit a question asking the desired price through the natural language questions to the user terminal (120, 220).

In addition, when the transaction type 420, a more detailed location, etc. are set as essential search conditions in addition to the basic search conditions of location, real estate type, and price according to the settings of the real estate transaction secretary service apparatus 110, 211, the real estate transaction secretary service The devices 110 and 211 may transmit a question about the corresponding search condition not extracted to the user terminals 120 and 220, and receive the natural language response 430 from the user terminals 120 and 220.

The real estate transaction assistant service device 110 or 211 may extract the first search condition and then perform a search using the first search condition through the real estate for sale information database or other search device or the real estate information device 212 owned by the real estate transaction assistant. (S330).

The real estate transaction assistant service apparatus 110 or 211 may set priorities in consideration of a user for each of the search results when there are a plurality of real estate for sale information search results through the first search condition.

The real estate transaction assistant service apparatus 110 or 211 may set priorities to the search results according to priorities of preset search conditions. For example, a user has requested information on apartments for sale under 1 billion won, and the property information found is "A apartment, Jeongauto, 30 pyeong, 900 million won" and "B apartment, Jeong automatic, 25 pyeong, 700 million won" If the priority is set to the size of the apartment in the setting of the real estate transaction assistant service device (110, 211), the user terminal (120, 220) information "A apartment, automatic, 30 pyeong, 900 million" preferentially (440).

Alternatively, the real estate transaction assistant service apparatus 110 or 211 may set a higher priority on the price condition, or may set a higher priority on other conditions not received from the user terminals 120 or 220 or used for a search. .

For example, when the priority is set high in the year of completion of the apartment, the real estate transaction assistant service apparatus 110 or 211 may set a high priority on the information of the shortest year in the searched real estate for sale.

As another embodiment, when the same real estate information exists among the retrieved real estate for sale information, that is, there may be a plurality of real estate for sale information provided by different property information providers for the same real estate and for sale with the same price condition.

In this case, the real estate transaction assistant service apparatus 110 or 211 may set priorities with respect to the same plurality of pieces of information on the basis of the information of the information for sale provider.

For example, if the listing information A and B provide the same plurality of listing information and the listing information is retrieved, the previous customer satisfaction with the listing information provider, the business period of the listing information provider, the commission or listing of the listing information provider Priority may be given to at least one of the number of false listings presented by the information provider, or the priority may be set by training the machine learning engine.

In this case, the conventional real estate for sale information technology to reduce the damage of the user due to the false sale or bait for sale, the user has an effect that can be determined more securely the sale information desired by the user.

Although the real estate transaction assistant service apparatus 110 or 211 may set priorities to specific real estate conditions in advance as described above, other users may previously search for real estate information and the method using the search results as data. By storing the information, it is possible to prioritize the searched real estate information based on the trained machine learning engine.

For example, the real estate transaction assistant service apparatus 110 or 211 may set priorities of the retrieved real estate information on the basis of a machine learning engine trained with data on a method of using the retrieved real estate information of previous users as shown in FIG. 5. have.

Referring to FIG. 5, if user A confirms the sale information by clicking on the sale information with a specific condition, the user satisfaction score is given to 1, and user C has made a contract with the sale information with the specific condition. You may assign 10 to your type of satisfaction score.

Therefore, the machine learning engine can be trained through data that has been given a user satisfaction score for real estate property information with various types of conditions, and user satisfaction can be predicted for the real estate property information retrieved for new users. Based on this, the priority of the real estate for sale information can be set.

Existing users are classified into various types such as not using the information according to the method of using real estate for sale information, confirming the sale information, attempting to contact the authorized broker who provided the sale information, and contracting through the sale information. To train machine learning engines.

In addition, the machine learning engine can also be trained through comparative company learning that clusters real estate property information with various conditions. In this case, weights are given to each item information of real estate property information included in the information of existing users. Learning may be performed, and the weight may change. In addition, the model trained by machine learning does not limit the method of generating the model such as supervised learning, unsupervised learning, semi-supervised learning, and deep learning is also used. Of course it can.

As an example, the real estate transaction assistant service device 110 or 211 may train a machine learning engine using personal information, real estate preference information, lifestyle information, etc. of existing users.

For example, referring to FIG. 5, since user A has lifestyle information of a single woman and a woman using the subway, the user uses data confirmed and interested in real estate for sale with two rooms on the third floor. Each item of lifestyle information can be used to train a machine learning engine, and each item can be trained with a different weight.

As described above, when the machine learning engine is trained using the items of the lifestyle information, the real estate transaction assistant service apparatus 110 or 211 additionally corresponds to the user terminals 120 and 220 in order to identify a specific item of the lifestyle information. You can send a question asking for an item and receive an answer. This embodiment will be described with reference to FIG. 8.

8 is a flowchart illustrating an operation of another service method of the real estate transaction assistant service apparatuses 110 and 211 using a chatbot. The real estate transaction assistant service method described below may be performed after the user terminals 120 and 220 request real estate sale information from the real estate transaction assistant service apparatus 110 or 211.

The user terminals 120 and 220 may request real estate for sale information through natural language inputs 910 and 1010 through an interface as shown in FIG. 9 or 10 (S810). 9 or 10 may be performed through an application such as a smartphone, but may also be performed through a page implemented in a web language such as Javascript of an Internet site.

The real estate transaction assistant service apparatus 110 or 211 extracts a first search condition such as price, location, type of real estate, etc. through morphological analysis and natural language analysis on the natural language input received from the user terminals 120 and 220 ( In operation S830, a second search condition such as lifestyle information or real estate preference information may be acquired.

In one embodiment, the real estate transaction assistant service device (110, 211) transmits a question asking the corresponding item to the user terminal (120, 220) for a specific item of lifestyle information or real estate preference information, and receives an answer thereto Information about a specific item of lifestyle information or real estate preference information may be extracted.

In another embodiment, the real estate transaction assistant service apparatus 110 or 211 may retrieve information about a specific item of lifestyle information or real estate preference information by searching for information data of a user requesting real estate sale information search.

Referring to FIG. 6, the real estate transaction secretary service apparatus 110 or 211 may include user's family composition form, user's work location, user's transportation use form, user's gender, user's age, and user's lifestyle information. Pets can be used, interests in the safety of the user or possessions and real estate of the user, etc. can be used, but in addition to the above-mentioned information about everyday life type is not particularly limited.

Referring to FIG. 7, as another embodiment, the real estate transaction assistant service apparatus 110 or 211 may include, in addition to information on a user's lifestyle, a preferred building year, a scheduled occupancy time, a structure or layout of a preferred real estate, etc., as real estate preference information. Like the lifestyle information, the user may transmit a question for the item to the user terminal 120 and 220 for the property preference information and receive an answer or receive the information data of the user requesting to retrieve the property information. Searching may also extract information about a specific item of lifestyle information.

As an embodiment, the real estate transaction assistant service apparatus 110 or 211 may additionally use the lifestyle information or the real estate preference information of the user as a search condition in addition to the search condition of the price, location, and real estate type (S840).

In an embodiment, the real estate transaction assistant service apparatus 110 or 211 may set a priority based on the lifestyle information or the property preference information of the user (S850).

The real estate transaction assistant service apparatus 110 or 211 may set priorities in a manner of giving priority to a specific item based on the lifestyle information of the user or the property preference information, and the lifestyle information or the property preference information of the user. Priority can also be set by the machine learning engine learned based on.

Referring to FIG. 9, when the real estate transaction secretary service apparatus 110 or 211 receives a natural language input 910 from the user terminal 120 or 220, the real estate transaction secretary service apparatus 110 or 211 may have a lifestyle in advance. If the information or real estate preference information is set to be reflected in the search condition or priority setting, the user terminal 120 or 220 transmits questions (920, 940) regarding the family composition form, and responds to the response (930, 950). After receiving and analyzing the data, it may be reflected in a search condition or priority setting.

In one embodiment, if it is determined that the user has a child who is a student as lifestyle information, the district information or distance from the school may act as an important selection factor in the selection of real estate, and this may be reflected in the search condition or set priority. This may be reflected in 960.

As another embodiment, even when lifestyle information is not reflected in the search condition or priority setting, information of the corresponding item may be provided together when the search results based on the priority are transmitted to the user terminals 120 and 220 (960).

As another embodiment, the real estate transaction assistant service apparatus 110 or 211 may reflect real estate preference information in a search condition or priority setting.

Referring to FIG. 10, after receiving a request (1010) from a user terminal (120, 220) for real estate for sale information including a price and a location in a natural language input, separately transmitting a question for real estate preference information to the user terminal (120, 220). Instead, the information data of the user requesting the search for real estate information may be searched to extract information about a specific item of the lifestyle information, and may be reflected in the search condition or priority setting (1040 and 1050).

As another embodiment, even if the real estate preference information is not reflected in the search condition or priority setting, the information of the corresponding item may be provided together when the search results based on the priority are transmitted to the user terminals 120 and 220 (1040 and 1050). ).

In another embodiment, the real estate transaction assistant service device 110 or 211 may search not only when the user's lifestyle information or real estate preference information is used as a search condition, but also based on the basic price, location, and real estate type search conditions. Prioritization may be set only based on lifestyle information or real estate preference information.

When the real estate transaction assistant service apparatus 110 or 211 provides the real estate for sale information searched using the search conditions such as the location, price, real estate type, or the search conditions such as lifestyle information and real estate preference information, the real estate for sale information Link information, which can be viewed in detail, may be transmitted together with the user terminals 120 and 220 (441, 960, 1040, and 1050).

11 is a flowchart illustrating another operation of a service method of the real estate transaction assistant service apparatus 110 or 211 using a chatbot. The real estate transaction assistant service method described below may be performed after the user terminals 120 and 220 request real estate sale information from the real estate transaction assistant service apparatus 110 or 211.

The user terminals 120 and 220 may request real estate for sale information by inputting natural language, and the real estate transaction assistant service apparatus 110 or 211 may analyze the morphemes and natural language with respect to the input of the natural language received from the user terminals 120 and 220. The first search condition may be extracted through the analysis, and the search may be performed through the real estate for sale information database or another search device or the real estate information device 212 owned by the extracted first search condition.

The real estate transaction assistant service apparatus 110 or 211 may cluster the retrieved real estate for sale information based on a preset condition when a plurality of retrieved real estate for sale information exists.

As an exemplary embodiment, referring to FIG. 11A, the real estate transaction assistant service apparatus 110 or 211 extracts a natural language input received from the user terminals 120 and 220 and determines that the apartment for sale information is requested in Seoul. When the administrative area is set in advance as a clustering condition, the plurality of searched real estate information may be clustered for each administrative district.

That is, the real estate transaction assistant service apparatus 110 or 211 may cluster the plurality of real estate for sale information in units of administrative districts smaller than the real estate information desired by the user.

The real estate transaction assistant service apparatus 110 or 211 clusters a plurality of real estate for sale information, and then generates representative information about a specific item of real estate information belonging to the same cluster, and based on the map form, the user terminal 120 , 220). Representative information is representative of the information on a particular item of a plurality of real estate items belonging to the cluster, for example, the average value of the actual transaction price, the median of the actual transaction price, the average value of the recent one-year transaction price, the recent one-year transaction Median of price, mean volume area of real estate listings, mean median volume rate of real estate listings, and the like.

As an exemplary embodiment, referring to FIG. 11 (a), when the plurality of searched real estate information is clustered for each administrative region, the actual transaction of the real estate for each administrative region generates average information or median value information, It may be provided to the user terminals 120 and 220 by overlapping the positions of the respective administrative regions. In this case, the number of real estate for sale information used for generating the average information or the median value information of each cluster may be provided to the user terminals 120 and 220 together (1120).

As another embodiment of a specific item of real estate information, the real estate transaction secretary service apparatus 110, 211 may provide average information of the price per square foot of real estate, the price per unit area of real estate, the construction year of the real estate, the charter price, the charter value rate, the floor area rate or the closing rate. The user interface 120 may be generated and provided to the user terminals 120 and 220 based on a map form, or an interface 1110 through which the user may select a corresponding item.

Referring to FIG. 11 (b), the real estate transaction assistant service apparatus 110 or 211 may be configured in a map form from user terminals 120 and 220 with respect to average information of real estate for sale information provided based on a map form. When receiving a request related to the change, the plurality of real estate for sale information retrieved based on the changed map form and a predetermined condition may be re-clustered and provided to the user terminals 120 and 220 based on the map form.

For example, after providing the real estate for sale information based on the map form as shown in FIG. 11 (a) to the user terminals 120 and 220, if the user zooms in a specific administrative district 1120, the corresponding administrative district cluster The real estate for sale information belonging to the cluster may be again clustered by the sub-administrative districts and the average information may be regenerated according to the cluster (1130).

Thus, a user may primarily compare the average information of real estate for sale information based on a wide administrative district and adjust the range more precisely, in order to find a real estate with a possible transaction price or preferred condition, and to dynamically adjust the desired real estate. There is an effect that can easily retrieve information.

12 is an exemplary block diagram showing the configuration of the real estate transaction secretary service apparatus 110, 211. The real estate transaction assistant service apparatuses 110 and 211 disclosed herein may include a communication unit 1210, an extraction unit 1220, a control unit 1230, and a storage unit 1240.

The communication unit 1210 may receive a natural language input from the user terminals 120 and 220, transmit the searched real estate information to the user terminal based on the priority, and may be configured as a wired and / or wireless communication module. For example, the communication unit 1210 may include Wi-Fi, Wi-Fi, Bluetooth, Zigbee, near field communication (NFC), and Wi-Fi (Wireless Broadband Internet: Wibro). It may include a wireless communication module and a wired communication module such as a wired LAN such as Ethernet. The communication unit 1210 may perform wired or wireless communication with the user terminals 120 and 220 through a network.

The extractor 1220 may extract the first search condition related to the real estate by analyzing the natural language input received from the user terminals 120 and 220.

The controller 1230 may search for real estate for sale information based on a first search condition and set the priority for the plurality of retrieved real estate for sale information, or cluster the plurality of retrieved real estate information based on a preset condition, Average information of real estate information belonging to the cluster may be generated.

  The controller 1230 may include any kind of device capable of processing data, such as a processor. Here, the 'processor' may refer to a data processing apparatus embedded in hardware having, for example, a circuit physically structured to perform a function represented by code or instructions included in a program. As an example of a data processing device embedded in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated device may be used. It may include a processing device such as a circuit, a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

The storage unit 1240 may store at least one of intermediate data, final data, or user data of the control unit and the search unit, and may include a magnetic storage media or a flash storage media. However, the scope of the present invention is not limited thereto.

The real estate transaction assistant service method according to the embodiments disclosed herein may be embodied as computer readable codes on a computer readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, optical data storage devices, and the like. The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the art to which the techniques of this specification pertain.

Preferred embodiments of the technology of the present disclosure have been described with reference to the accompanying drawings. Here, the terms or words used in the present specification and claims should not be construed as being limited to ordinary or dictionary meanings, but should be construed as meanings and concepts corresponding to the technical spirit of the present invention.

The scope of the present invention is not limited to the embodiments disclosed herein, and the present invention may be modified, changed, or improved in various forms within the scope of the spirit and claims of the present invention.

110, 211: real estate transaction secretary service apparatus
120, 220: user terminal
130, 230: network
212: retrieval device or real estate information device

Claims (10)

As performed by the real estate chatbot assistant server,
Receiving a natural language input from a user terminal through a communication module of the real estate chatbot assistant server;
Extracting a first search condition related to real estate by analyzing the natural language input by a processor of the real estate chatbot assistant server;
If it is determined that at least one of the preset required search conditions does not exist among the extracted first search conditions, the user terminal transmits a question about an essential search condition that does not exist, and receives a natural language response thereto, thereby receiving the first language. Augmenting the search condition;
The processor of the real estate chatbot assistant server receives lifestyle information from the user terminal or extracts lifestyle information including family composition type, work location, car possession status, gender information, age information, and pet possession status from the user terminal data. To act;
Receive or extract from the user's information data home preference information including the preferred building year, expected time of occupancy, preferred floor, room arrangement type and placement direction of the house by the processor of the real estate chatbot assistant server. To act;
Lifestyle information including the first search condition, the family composition form, the work location, the car possession status, the gender information, the age information, and whether the pet possession is performed by a processor of the real estate chatbot assistant server; Retrieving real estate for sale information based on all of the housing preference information including a building year, the expected time of occupancy, the preferred floor, the room arrangement type, and the arrangement direction of the house;
Setting a priority of real estate for sale information retrieved by a processor of the real estate chatbot assistant server; And
Transmitting, by the processor of the real estate chatbot assistant server, the retrieved real estate for sale information to the user terminal based on the priority;
The setting of the priority includes all of the information on which the user clicked on the searched real estate for sale information, the information on which the users contacted the property information provider, the information on which the user visited the searched real estate, and information on whether or not to make a contract using the retrieved real estate. Based on machine learning engines trained with data that includes information about how users use them,
The same property information among the searched real estate property information is based on the information of the property information provider, which includes all of the customer satisfaction, the sales period of the property information provider, the commission of the property information provider, and the number of times of false listings of the property information provider. Set priorities,
The processor of the real estate chatbot assistant server, the searched real estate for sale information based on the priority and a predetermined condition for the retrieved real estate for sale information is smaller than the real estate location information desired by the user in the first search condition. Clustering the retrieved real estate for sale information by zone unit, and the average value of the actual transaction price, the median of the actual transaction price, the average value of the recent one-year transaction price, the recent one-year transaction price of the real estate for sale information belonging to the same cluster Generating at least one of a median value, a volume fraction mean, or a volume fraction median value as representative information;
The transmitting of the retrieved real estate for sale information to the user terminal may include providing, by the processor of the real estate chatbot assistant server, the representative information about a plurality of clusters to the user terminal based on a map form. The service method of the server. delete delete delete delete According to claim 1,
The searching of the real estate for sale information may include transmitting the first search condition to a second server and receiving a search result from the second server. delete According to claim 1,
Receiving, by the communication module of the real estate chatbot assistant server, a request relating to the change of the map form from the user terminal;
The processor of the real estate chatbot assistant server reclustering the retrieved plurality of real estate information based on a request related to the change of the map form and a preset condition; And
And generating, by the processor of the real estate chatbot assistant server, representative information about the plurality of clustered clusters, and providing the representative information to the user terminal based on a map form. A communication unit for receiving a natural language input from a user terminal and transmitting the retrieved real estate information to the user terminal based on priority;
An extracting unit extracting a first search condition related to real estate by analyzing the natural language input;
Lifestyle information including the first search condition, family composition form, work location, car possession status, gender information, age information, and pet possession status, estimated time of moving in, preferred floor, room layout and housing A control unit for retrieving real estate for sale information based on all of the housing preference information including an arrangement direction of and setting the priority of the plurality of retrieved real estate for sale information; And
A storage unit for storing at least one of the searched real estate information or user data;
If the extracting unit determines that at least one of the preset essential search conditions does not exist among the extracted first search conditions, the extractor transmits a question about a required search condition that does not exist to the user terminal and receives a natural language response thereto. ,
The extraction unit receives lifestyle information including the family composition form, the work location, the vehicle possession status, the gender information, the age information, and whether the pet possession status is received from the user terminal or extracted from the information data of the user. and,
The extractor may receive home preference information including the preferred building year, the expected time of occupancy, the preferred floor, the room arrangement form, and the arrangement direction of the house from the user terminal or extract information from the user data. ,
The control unit may include information on how the user clicks on the searched real estate for sale information, information on how the users contacted the property information provider, information on whether the user visited the searched real estate, and information on whether to make a contract using the searched real estate information. Set priorities based on machine learning engines trained with data,
The control unit may be configured to include the same property information among the searched real estate property information, including information about a customer satisfaction, a sales period of a property information provider, a fee of the property information provider, and a number of false listings of the property information provider. To set priorities based on
The controller controls the searched real estate for sale information based on the priority and a predetermined condition with respect to the searched real estate for sale information in units of administrative districts smaller than the desired real estate location information among the first search conditions. Clustering the information, the average value of the actual transaction price, the median of the actual transaction price, the average value of the recent one year transaction price, the median of the recent one year transaction price, the volume ratio average or the volume ratio Generate at least one of the intermediate values as representative information,
The control unit provides the real estate chatbot assistant server for providing the representative information for a plurality of clusters to the user terminal based on the retrieved real estate for sale information on the map form. delete

Images