KR102153790B1 - Computing apparatus, method and computer readable storage medium for inspecting false offerings - Google Patents

Abstract

The present disclosure provides a computing device for inspecting a false property. The system receives a property database configured to store information of a plurality of properties and information of a plurality of brokerage establishments and a condition of a property desired by a user from a user terminal, and among a plurality of properties stored in the property database, the condition of the received property is A property extraction module configured to extract a property list including one or more matching properties, each of the at least one brokerage business that uploads each of the at least one property included in the extracted property list based on the information of the plurality of brokerage businesses stored in the property database A warning determination module configured to determine the number of warnings of, and adjust the maximum value of the random number range in which a random number is output according to the number of warnings from one or more brokerage agencies, and to associate the adjusted random number range with a property uploaded by one or more brokerage agencies. A configured random number range calculation module, a final random number calculation module configured to calculate a final random number within the adjusted random number range for the related property, sort one or more properties in order of the size of the final random number, and create a listing including one or more sorted properties. And an output module configured to output.

Description

A computing device, a method, and a computer-readable storage medium for inspecting false property TECHNICAL FIELD [COMPUTING APPARATUS, METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR INSPECTING FALSE OFFERINGS}

The present disclosure relates to a computing device and a method for inspecting a false property, and more particularly, to a system and method for providing information on a verified property to a user by determining whether the property is true or false using an artificial neural network. About.

In the conventional real estate trading method, the real estate seller/buyer had to visit the real estate in person to confirm/register the property. Typically, a real estate seller visits a real estate brokerage office and informs them of their intention to sell, and a real estate buyer who visits a real estate brokerage office directly checks the real estate sale with a real estate broker and signs a contract.

In this method, there is no way to check whether the desired property is available until the real estate buyer directly visits the real estate brokerage office, and there is a temporal/spatial problem that the buyer must move to the place where the real estate is located. With the development of internet technology, a service that allows real estate brokerage information to be provided through the Internet (online) is in the spotlight, unlike existing real estate sales in which properties were traded in an offline (face-to-face) manner. Specifically, the owner of the property or the broker of the property registers the property information on a site, personal web page, cafe, or blog, etc., which are operated so that the property sale is professionally traded, and by accessing the information registered site online, etc. The obtained information may be provided to a user who is willing to buy or broker a sale.

However, there are often cases in which false/manipulated false property information is registered online by a supplier or broker. Accordingly, there is a problem in that accurate information on the property cannot be provided. In particular, due to the nature of real estate sales, transparent market price information is not provided, and incorrect/manipulated market price information is reflected in some regions, leading to significant differences between online market price information and actual market price.

A false sale by a supplier or broker may include the following:

-Imaginary Sale: If you continue to advertise without deleting the sold property

-Fishing property: If you use someone else's property for advertising without your permission

-False sale: When advertising is not available

-Exaggerated for sale: when it is ridiculously cheaper than the market price of other brokerages

Therefore, there is a need to overcome the problems of existing online listings and provide verified listing information to users.

Embodiments disclosed in the present specification are intended to provide a computing device and method for inspecting a false property that allows a user to access an authentic property without being deceived by a false property by providing information on a verified property to a user.

A computing device for inspecting a false property according to an embodiment of the present disclosure includes a property database configured to store information of a plurality of properties and information of a plurality of brokerage offices, a property of a property desired by a user from a user terminal, and A property extraction module configured to extract a property list including one or more properties that meet the conditions of the received property from among a plurality of properties stored in the database, and included in the extracted property list based on information from a plurality of brokerage businesses stored in the property database A warning determination module configured to determine the number of warnings of each of one or more brokerages that have uploaded each of one or more properties, and adjust the maximum value of the random number range in which a random number is output according to the number of warnings of one or more brokerages, A random number range calculation module configured to associate a range of random numbers with a property uploaded by one or more brokerage agencies, a final random number calculation module configured to calculate a final random number within a range of random numbers adjusted for the related property, and one or more listings in the order of the final random number. And an output module configured to output a list of properties including one or more aligned properties.

In addition, a method for inspecting a false property by a computing device according to an embodiment of the present disclosure includes: preparing a property database configured to store information of a plurality of properties and information of a plurality of brokerage businesses, from a user terminal Receiving the conditions of a desired property, and extracting a property list including one or more properties meeting the conditions of the property received from a plurality of properties stored in the property database, based on information of a plurality of brokerage businesses stored in the property database Determining the number of warnings of each of the one or more brokerages that have uploaded each of the one or more listings included in the list of properties, adjusting the maximum value of the random number range in which the random number is output according to the number of warnings of each of the one or more brokerages, Associating the adjusted random number range with the properties uploaded by one or more brokerage agencies, calculating a final random number within the adjusted random number range for the related property, sorting one or more properties in the order of the size of the final random number, and sorting one It may include the step of outputting a property list including the above properties.

In order to provide verified property information to a user, a computing device for inspecting a false property according to an embodiment of the present disclosure extracts a property based on the condition from a database when a desired property condition is input by the user. , It is possible to analyze the authenticity of the information of the property by sorting the properties according to the size of the random number calculated based on the number of warnings of the brokerage store stored in the database.

In addition, this system uses semi-supervised learning, one of the methods of artificial intelligence (machine learning), to determine whether the property is a false property, thereby providing the user with information on the verified property. I can.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned will be clearly understood by those skilled in the art from the description of the claims.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, where like reference numerals denote like elements, but are not limited thereto.
1 is an exemplary diagram of a system for providing a user-customized property list according to an embodiment of the present disclosure.
2 is a schematic diagram of a computing device for inspecting a false property according to an embodiment of the present disclosure.
3 is a schematic diagram of a server device according to an embodiment of the present disclosure.
4 is a diagram illustrating an example of a property held and information held in a property information DB according to an embodiment of the present disclosure.
5 shows an example of a brokerage business and information held in a brokerage business information DB according to an embodiment of the present disclosure.
6 is a flowchart illustrating a method of providing a system for providing a user-customized property according to an embodiment of the present disclosure.
7 is a structural diagram showing an artificial neural network according to an embodiment of the present disclosure.
8 is a flowchart illustrating a process of calculating a maximum value of a random number range according to an embodiment of the present disclosure
9 is an exemplary view showing a screen of an interface configured to receive a condition of a property desired by a user according to an embodiment of the present disclosure.
10 is an exemplary diagram illustrating an interface screen for outputting information on a property according to an embodiment of the present disclosure.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. However, those of ordinary skill in the art will readily understand that the detailed description given herein with respect to these drawings is for purposes of illustration, and the present disclosure extends beyond these limited embodiments.

In the false sale inspection system using artificial intelligence according to an embodiment of the present disclosure, in order to provide verified property information to the user, when a desired property condition is input from the user, the property based on the condition is extracted from the DB, and then the property Conduct an analysis of the information. In addition, this system uses semi-supervised learning, one of the methods of artificial intelligence (machine learning), to determine whether the property is a false property, thereby providing the user with information on the verified property. I can.

1 is an exemplary diagram of a system for providing a user-customized property list according to an embodiment of the present disclosure. A user may request a property search through an interface of the user terminal 110 (eg, a touch display, a keyboard, a mouse, a touch pen, or a stylus, a microphone, a motion recognition sensor, etc.). The request for output of a desired property may include information input by the user using a user terminal, that is, information indicating an area, a nearby subway station, an office type, a property type, a property area, a deposit, etc., and the input information is a database It can be sorted and stored by user.

In one embodiment, when a user searches for an area of a desired property in the search window 120 to request the output of the property, the property list 140 is displayed on the terminal screen 130. In the listing 140, brief listing information such as monthly rent/jeonse/purchase, and deposit is output together with a photograph of the property. The order of the listings in which the listings are displayed is listed based on the size of the random number calculated according to the number of warnings of the brokerages analyzed using artificial intelligence (deep learning).The less or less warnings of the brokerages, the more listings are at the top. Is placed. Through such a list, the user can select the true property. As another example, the user may once again search for a property of a desired condition, such as a type of property, a deposit limit, a transaction type, and a property area through the filter 150. In this case, the output list may also be listed based on the size of the random number calculated according to the number of warnings of the brokerage agency analyzed using artificial intelligence (deep learning).

2 is a schematic diagram of a computing device for inspecting a false property according to an embodiment of the present disclosure. The system shown in FIG. 2 may receive information input by the user from the user terminal 110 and request the server device 220 to provide a list of properties for which false properties have been inspected. Here, the user terminal 110 may receive property list request information from which the false property has been inspected from the user, and may be an appropriate computing device having a user interface. For example, the user interface of the user terminal 110 may include one or more of a touch display, a keyboard, a mouse, a touch pen or a stylus, a microphone, and a motion recognition sensor, but is not limited thereto. Meanwhile, the user terminal 110 may be any one of a personal computer, a smart phone, a tablet computer, and the like, but is not limited thereto.

The server device 220 receives property information and agency information from a plurality of agency servers 230_1 to 230_n periodically or aperiodically (eg, in real time) through a communication network 210 Can be saved. The server device 220 can read the property information and the brokerage information from the database, and learn the artificial neural network based on the information read as described above, thereby matching the user's region and the sale price based on the information input by the user. You can create a list of properties. Here, the server device 220 is a computing device capable of communicating with other devices through a wired or wireless network, and may use one of a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), etc. It may be a computing device capable of performing an arithmetic operation by using, but is not limited thereto. The server device 220 may provide the generated property list to the user terminal 110 through the communication network 210, and may sort the generated property list by region and sale price and store it in a database.

3 is a schematic diagram of a server device according to an embodiment of the present disclosure. Hereinafter, the components of the server device 220 will be described in more detail. As illustrated in FIG. 3, the server device 220 may include a communication module 310, a processor 320, and a database 340. The processor 320 may include an item extraction module 322, a warning determination module 324, a random number range calculation module 326, a final random number calculation module 328, an output module 330, and a database 340 ) May include a property information DB 350 and a brokerage business information DB 360. The server device 220 shown in FIG. 2 may include functions or components of the server device 220 shown in FIG. 3. In addition, among the functions or components of the server device 220, for components having the same member numbers or names as those described in FIG. 2 described above, detailed descriptions may be omitted to avoid repetition, and changes Or, you can only explain additional parts.

The database 340 is a property information DB 350 in which the area of the property, the sale price, the property area, and the deposit, etc. are classified and stored, and the broker registration number, business registration number, agency address, agency representative name, agency representative number , A brokerage company photo, information on a false sale report, information on a registered property, history information on the registered property, and the number of warnings are classified and stored, and may include a brokerage business information DB (360). The server device 220 receives property information and agency information from a plurality of agency servers 230_1 to 230_n periodically or aperiodically (for example, in real time) and stores them in the property information DB and the agency information DB, respectively. I can.

In one embodiment, the server device 220 may read the information of the property and the information of the agency from the property information DB 350 and the agency information DB 360. In addition, the brokerage business information DB 360 may extract false sale report information from the information of the brokerage business, and adjust the maximum value of the random number range of the brokerage business. Based on such property information and brokerage information, the server device 220 may learn by a semi-supervised learning method given an artificial neural network. The server device 220 may infer and generate a property list based on the condition of the property input through the user terminal 110 by using the learned artificial neural network.

The server device 220 may provide a list of properties in which the generated false properties are checked to the terminal 110 through the communication network 210, and the generated listings are sorted by region and sale price, and the property information DB Can be saved on. In FIG. 3, the database 340 is shown to be included in the server device 220, but is not limited thereto. According to embodiments, the database is separately present outside the server device 220 so that the database 340 is transmitted to the communication network 210. It can also be connected.

The communication module 310 may receive a request from the user terminal 110 for outputting a list of properties in which false properties have been inspected, and in response to the request, the user terminal 110 receives the list of properties extracted by the output module 330. Can be transferred to. The request for outputting a list of products may include an area of the property, a sale price, and an area of the property, input by the user using the user terminal 110. The communication module 310 may transmit, to the processor 320, a request for outputting an item list including such user input information.

를 입력하고, 허위 매물이 검수된 매물 리스트 출력을 요청하게 되면, 통신 모듈(310)은, 사용자의 지역, 매매가격, 매물면적정보(예를 들어, "OO구", "1000만원", "100

")를 서버장치(220)의 프로세서(320)로 전송할 수 있다. According to an embodiment, the user may input user information through the user terminal 110 and request the output of a list of properties for which false properties have been verified. For example, the user uses the user terminal 110 to receive OO balls, 10 million won, 100

When inputting and requesting the output of the listing of the property in which the false property was inspected, the communication module 310, the user's region, the sale price, and the property area information (eg, “OO ward”, “10 million won”, “ 100

") may be transmitted to the processor 320 of the server device 220.

The property extraction module 322 may read the property information stored in the property information DB 350 and the agency information DB based on user input information transmitted by the communication module 310. In addition, the property extraction module 322 may extract information on a type of property, a property deposit, monthly rent / jeonse / sale, and property area information from the property information. The property information extracted by the property extraction module 322 module may tag information on a tag by property type, property deposit, monthly rent/charter/sale, and property area. The property extraction module 322 may store property information divided by tag information (eg, property type, property deposit, monthly rent/charter/sale, property area, etc.) in the property information DB.

The warning determination module 324 may determine the number of warnings of the agency that uploads each of the listings included in the extracted listing, based on the information of the agency stored in the database 340. The warning determination module 324 may determine the number of warnings of the brokerage business based on the false sale report information of the brokerage business stored in the brokerage business information DB. According to an embodiment, a case of applying a warning to a brokerage business through false sale report information is as follows. In the case of a property for which the transaction has already been completed, upon receiving the first report of a false sale, the property is treated as private and then an inspection request is made. When the same property is re-detected through a second report and re-examination, one warning is applied to the brokerage that uploaded the property after deleting the property.

In another example, in the case of a property with a wrong picture, a property with the wrong location, a property with the wrong price, or a property with incorrect information, the property is treated as private when receiving the first notification of the false property, and then "Caution" is applied. If the same brokerage account is detected again through a second report and re-inspection due to the problem, a warning is applied to the brokerage that uploaded the property after deleting the property.

The random number range calculation module 326 includes the number of warnings of the agency stored in the property database, information about the property registered by the agency, and history information about the property, input into the input layer of the artificial neural network to determine the maximum value of the random number range of the agency. It can create an artificial neural network to determine. For example, the artificial neural network can infer the maximum value of the random number range through semi-supervised learning. By using an artificial neural network-based semi-supervised learning method, the number of warnings for each brokerage is analyzed, and based on this, the maximum value of the random number range of the brokerage can be predicted to calculate the final range. The input variable input to the input layer of the artificial neural network may be a vector indicating false property report information and the number of warnings determined by the warning determination module 324. For example, the categories of false property reporting information and warning counts may each be configured as one vector data element. Meanwhile, the output variable output from the output layer of the artificial neural network may be a vector representing the random number range analyzed by the random number range calculation module 326 according to an embodiment. The random number range calculation module 326 may train an artificial neural network using these input variables and output variables.

According to an embodiment, the maximum random number value range of the brokerage property for which the number of warnings determined by the warning determination module 324 is 0 is set to 100, and the maximum range of the random number of the brokerage property for which the number of warnings is one is 100 to 85. Set, the maximum random number range of the brokerage's property with two warning counts is set to 100-75, the maximum random number value of the brokerage's property with three warning counts is set to 100-55, the maximum random number of brokerage's listing with four warnings The value range can be set to 100 to 40, and as the number of warnings of the brokerage office increases, the maximum value of the random number range can be reduced in stages. The final random number range may be calculated using the maximum random number range set based on the number of warnings. The random number range of the brokerage's property with 0 warning counts is set to 100~0, the random number range of the brokerage's property with one warning count is set to (100~85)~0, and the random number range of brokerage listings with two warnings Is set to (100~75)~0, the random number range of brokerage sales with 3 warnings is set to (100~55)~0, and the random number range of brokerage sales with 4 warnings is (100~40) By setting it to ~0, the final random number range can be calculated.

The final random number calculation module 328 may calculate a final random number within the final random number range calculated by the random number range calculation module 326. Random number range calculation module 326, random number range of brokerages with zero warning counts, 100 to 0, brokerages with one warning count, random number range (100-85) to zero, brokerages with two warnings The random number range of (100~75)~0, the random number range of the brokerage property with 3 warning counts is (100~55)~0, the random number range of the brokerage property with 4 warning counts (100~40)~0 Random numbers can be calculated.

The output module 330 may sort and extract the items in the order of the size of the random number finally calculated by the final random number calculation module 328. The extracted listing 140 may be arranged in the order of the size of the random number calculated in the user terminal 110 through the communication module 310.

4 is a diagram illustrating an example of a property held and information held in a property information DB according to an embodiment of the present disclosure. The property information may be input information input through the user terminal 110 or may be information stored in the brokerage business information DB. The information on the property may include a transaction type, a housing type, price information, street information, and environment information for the property. In addition, the information of the property may be basic information of the property such as the address of the property, the planned occupancy date, area, waterproofing, floor number, completion date, parking information, and heating information.

5 shows an example of a brokerage business and information held in a brokerage business information DB according to an embodiment of the present disclosure. The brokerage business information may be member information of each brokerage business registered as a member, for example, information such as a brokerage business name, a representative name, an address, a representative phone number, a representative mobile terminal number, an email address, and information on reporting false sales. The information on reporting false sales of the brokerage may be used in the warning determination module 324. In the case of a property for which the transaction has already been completed, upon receiving the first report of a false sale, the property is treated as private and then an inspection request is made. If the same property is re-detected through a second report and re-examination, one warning is applied to the brokerage that uploaded the property after deleting the property. In the case of a property with an incorrect picture, a property with the wrong location, a property with the wrong price, or a property with incorrect information, the property is treated as confidential when receiving the first notification of the false property, and "Caution" is applied. If the same brokerage account is detected again through a second report and re-inspection due to the problem, a warning is applied to the brokerage that uploaded the property after deleting the property.

6 is a flowchart illustrating a method of providing a list of properties in which a false property has been inspected according to an embodiment of the present disclosure. The method of providing a list of properties in which the false property has been inspected may be initiated by a communication module in step S610 of receiving a property condition from a user terminal through a network. The server device 220 may receive a condition of a property input by a user from a user terminal, and store input information included in the property condition in a database for each user. Here, the request for outputting a list of properties in which the false property has been inspected may include property information indicating an area desired by the user, a sale price, and a property area. In one example, referring to FIG. 3, the communication module 310 may receive a request for providing a list of properties for which false properties have been inspected from the user terminal 110. For example, when a user inputs an OO station using the user terminal 110 and requests the output of a listing, the communication module 310 may provide a property in the area desired by the user (for example, "OO station" ) May be transmitted to the processor 320 of the server device 220.

After receiving the property condition, a property meeting the user's condition may be extracted from the property stored in the database based on the property output request (S620). The property extraction module 322 may extract a property that satisfies a user condition from among the properties stored in the property database based on the property output request. In one example, referring to FIG. 3, the property extraction module 322 may read the property information stored in the property information DB 350 based on user input information transmitted by the communication module 310. .

After that, it is possible to determine the number of warnings of the brokerage that uploaded the extracted sale (S630). The warning determination module 324 may determine the number of warnings of the brokerage business based on the false sale report information of the brokerage business stored in the brokerage business information DB. In one example, if the brokerage agency uploads a property for which the transaction has already been completed, upon receiving the first report of a false sale, the property is treated as private and then a request for inspection is made. If the same property is re-detected through a second report and re-inspection, one warning can be applied to the brokerage that uploaded the property after deleting the property. In another example, if the brokerage agency uploads a property with an incorrect picture, a property with the wrong location, a property with the wrong price, or a property with incorrect information, the property is treated as private when receiving the first report of false property, and then "Caution" Can be applied. If the same brokerage account is detected again through a second report and re-examination due to the problem, a warning can be applied to the brokerage that uploaded the property after deleting the property.

In the next step (S640), it is possible to calculate a random number range according to the number of warnings of the brokerage. Based on the number of warnings determined by the warning determination module 324, the maximum value of the random number range in which the random number is output may be adjusted according to the number of warnings of the agency, and the adjusted random number range may be associated with the property uploaded by the agency. It can be configured to decrease the maximum value of the random number range step by step as the number of warnings of the brokerage business increases. The number of warnings of the brokerage store stored in the property database, information about the property registered by the brokerage business, and history information about the property are input to the input layer of the artificial neural network to create an artificial neural network that determines the maximum value of the random number range of the agency. . For example, the artificial neural network can infer the maximum value of the random number range through semi-supervised learning. By using an artificial neural network-based semi-supervised learning method, the number of warnings for each brokerage is analyzed, and based on this, the maximum value of the random number range of the brokerage can be predicted to calculate the final range. The input variable input to the input layer of the artificial neural network may be a vector indicating false property report information and the number of warnings determined by the warning determination module 324. For example, the categories of false property reporting information and warning counts may each be configured as one vector data element. Meanwhile, the output variable output from the output layer of the artificial neural network may be a vector representing the random number range analyzed by the random number range calculation module 326 according to an embodiment.

According to an embodiment, the maximum random number value range of the brokerage property for which the number of warnings determined by the warning determination module 324 is 0 is set to 100, and the maximum range of the random number of the brokerage property for which the number of warnings is one is 100 to 85. Set, the maximum random number range of the brokerage's property with two warning counts is set to 100-75, the maximum random number value of the brokerage's property with three warning counts is set to 100-55, the maximum random number of brokerage's listing with four warnings The value range can be set to 100 to 40, and as the number of warnings of the brokerage office increases, the maximum value of the random number range can be reduced in stages. The final random number range may be calculated using the maximum random number range set based on the number of warnings. The random number range of the brokerage's property with 0 warning counts is set to 100~0, the random number range of the brokerage's property with one warning count is set to (100~85)~0, and the random number range of brokerage listings with two warnings Is set to (100~75)~0, the random number range of brokerage sales with 3 warnings is set to (100~55)~0, and the random number range of brokerage sales with 4 warnings is (100~40) By setting it to ~0, the final random number range can be calculated.

A final random number may be calculated within the calculated random number range (S650). Random number range calculation module 326, random number range of brokerages with zero warning counts, 100 to 0, brokerages with one warning count, random number range (100-85) to zero, brokerages with two warnings The random number range of (100~75)~0, the random number range of the brokerage property with 3 warning counts is (100~55)~0, the random number range of the brokerage property with 4 warning counts (100~40)~0 Random numbers can be calculated.

The listings may be sorted in the order of the calculated final random number, and the listings may be output (S660). The items may be sorted and extracted in the order of the size of the random number finally calculated by the final random number calculation module 328. The extracted listing 140 may be arranged in the order of the size of the random number calculated in the user terminal 110 through the communication module 310.

7 is a structural diagram showing an artificial neural network 700 according to an embodiment of the present disclosure. The artificial neural network 700 is a statistical learning algorithm implemented based on the structure of a biological neural network or a structure that executes the algorithm in machine learning technology and cognitive science. That is, in the artificial neural network 700, nodes, which are artificial neurons that form a network by combining synapses as in a biological neural network, repeatedly adjust the weight of the synapse, and the correct output and inferred output corresponding to a specific input By learning so that the error between them is reduced, it represents a machine learning model having problem solving ability.

In general, an artificial neural network is implemented as a multilayer perceptron (MLP) composed of multilayer nodes and their connections. The artificial neural network 700 according to the present embodiment may be implemented using one of various artificial neural network structures including MLP. As shown in FIG. 7, the artificial neural network 700 includes an input layer 720 that receives input signals or data 710 and 712 from the outside, and output signals or data 750, 752, 754, and 756 corresponding to the input data. , An output layer 740 that outputs 758, n hidden layers 730_1 that are located between the input layer 720 and the output layer 740, receive signals from the input layer 720, extract characteristics, and transmit them to the output layer 740 To 730_n). Here, the output layer 740 receives signals from the hidden layers 730_1 to 730_n and outputs them to the outside.

In general, the learning method of the artificial neural network 700 includes a supervised learning method in which learning is optimized to solve a problem by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal ( There is an Unsupervised Learning method. The false property inspection system using artificial intelligence (deep learning) according to the present disclosure uses Supervised Learning and Unsupervised Learning together to provide a list of properties for which the false property has been verified to the user. Using semi-supervised learning, it is possible to train the artificial neural network 700 that adjusts the maximum value of the random number range by using the number of warnings from the agency. The artificial neural network 700 learned in this way may provide a list of properties in which the false property has been inspected in response to a request for outputting a list of properties in which the false property has been verified by the user.

According to an embodiment, as shown in FIG. 7, the input variable of the artificial neural network 700 capable of inferring the maximum value of the random number includes one category of false property report information and the number of warnings extracted from the warning determination module. It may be a false sale report vector 710 and a warning count vector 712 composed of vector data elements of.

For example, suppose that the user inputs the district of a property that the user wants to trade through the user terminal as "wht", and the user re-searches the property type and area of the property using the filter 150 among the displayed listings of the property. . In this case, among the data elements of the false sale report vector 710, a value of 1 may be assigned to elements corresponding to the property type and property area, and a value of 0 may be assigned to the remaining elements. In addition, among the data elements of the warning number vector 712, a value of 1 is assigned to elements including the number of warnings determined by the warning determination module 324 from the property information and the brokerage business information, The remaining elements can be assigned a value of 0.

Meanwhile, the output variable output from the output layer 740 of the artificial neural network 700 may be a vector representing the random number range analyzed by the random number range calculation module 326. According to one embodiment, the output variable is a warning number 0 vector 750, warning number 1 vector (752), warning number 2 vector 754, warning number 3 vector 756, warning number 4 It may be composed of a vector 758. For example, each of the vectors 750 to 758 may include a data element that calculates a random number range corresponding to the number of warnings of the brokerage business. In the present disclosure, the output variable of the artificial neural network 700 may not be limited to the five types described above.

In this way, a plurality of output variables corresponding to a plurality of input variables are matched to the input layer 720 and the output layer 740 of the artificial neural network 700, respectively, and the input layer 720, the hidden layers 730_1 to 730_n, and the output layer ( By adjusting the synaptic value between nodes included in 740), it is possible to learn to infer a correct output corresponding to a specific input. Through this learning process, the characteristics hidden in the input variable of the artificial neural network 700 can be identified, and the error between the output variable calculated based on the input variable and the target output is reduced. You can adjust the synaptic value (or weight). Using the artificial neural network 700 learned in this way, it is possible to extract a listing of listings in which false listings have been inspected according to the conditions of listings input by the user.

8 is a flowchart illustrating a process of calculating a maximum value of a random number range according to the embodiment of FIG. 3. The process of calculating the maximum value of the random number range may be initiated with the step (S800) of receiving the number of warnings of the agency determined by the warning determination module 324. After receiving the number of warnings from the brokerage business, it is determined whether there is a warning from the brokerage business (S810). As a result of the determination, if it is determined that there is no warning from the agency, the maximum value of the random number range may be set to the maximum (S812), and the process of calculating the maximum value of the random number range may be terminated. On the contrary, in the determination of the presence or absence of a warning from the brokerage (S810), if the warning from the brokerage is found to be one time (S820), the maximum value of the random number range is set between 100 and 85 (S822) to calculate the maximum value of the random number range. You can end the process. On the contrary, if the brokerage's warning is found to be two warnings (S830) instead of one (S820), the process of calculating the maximum value of the random number range is terminated by setting the maximum value of the random number range between 100 and 70 (S832). can do. On the contrary, if the brokerage's warning is found to be 3 warnings (S840) instead of 2 (S830), the process of calculating the maximum value of the random number range is terminated by setting the maximum value of the random number range between 100 and 55 (S842). can do. On the contrary, if the brokerage's warning is found to be 4 warnings (S850) instead of 3 (S840), the process of calculating the maximum value of the random number range is finalized by setting the maximum value of the random number range between 100 and 40 (S852). You can quit.

FIG. 9 is an exemplary view showing the lower surface of an interface for receiving a condition of a property desired by a user according to an embodiment of the present disclosure, and FIG. 10 is an example showing an interface screen for outputting property information according to an embodiment of the present disclosure Is also. The user may request a property search through a user interface (eg, a touch display, a keyboard, a mouse, a touch pen or a stylus, a microphone, a motion recognition sensor, etc.). The property search request may include an area desired by the user, a subway station, a property number, a price, etc., input by the user using a user terminal, and the input information may be sorted and stored for each user in a database.

In an embodiment, in order to request the output of a list of properties in which a false property has been inspected, as shown in FIG. 9, the desired property type may be divided into selectable tabs 910 and corresponding information may be input. A screen 900 of a preset interface for inputting a region and a subway station may be configured and provided to a user through a user terminal. For example, the user clicks the tab of the type of the corresponding property (for example, office), enters the area where the property is located (914), and then clicks the search button 912, and finally corresponds to the user. A list of properties in which false properties in an area are inspected can be output from the user terminal.

After clicking the search button, a screen 1000 of an interface in which a list of properties suitable for a condition designated by the user is output may be output to the user terminal. The user may select a desired property based on the property list 1010 in which the output false property has been inspected. For example, as shown in FIG. 10, the user may select a property by referring to a picture of the property, information on the property, and the like that are output.

In general, the system for outputting a list of properties in which false properties have been inspected, as described herein, includes a wireless telephone, a cellular telephone, a laptop computer, a wireless multimedia device, a wireless communication personal computer (PC) card, a PDA, an external modem or an internal modem, It may represent various types of devices, such as devices that communicate over a wireless channel. The device includes an access terminal (AT), an access unit, a subscriber unit, a mobile station, a mobile device, a mobile unit, a mobile phone, a mobile, a remote station, a remote terminal, a remote unit, a user device, a user equipment, It may have various names, such as handheld devices. Any device described herein may have a memory for storing instructions and data, as well as hardware, software, firmware, or combinations thereof.

The techniques described herein may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, It may be implemented in a computer, or a combination thereof.

Accordingly, various exemplary logic blocks, modules, and circuits described in connection with the disclosure herein may include general purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed in any combination of those designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, eg, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in association with the DSP core, or any other such configuration.

In the firmware and/or software implementation, the techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), PROM ( on a computer-readable medium such as programmable read-only memory), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage device, etc. It can also be implemented as stored instructions. The instructions may be executable by one or more processors, and may cause the processor(s) to perform certain aspects of the functionality described herein.

When implemented in software, the functions may be stored on a computer-readable medium as one or more instructions or code. Storage media may be any available media that can be accessed by a computer. By way of non-limiting example, such computer-readable medium may contain RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or the desired program code in the form of instructions or data structures. Also, any connection is properly termed a computer-readable medium.

As used herein, disks and disks include CDs, laser disks, optical disks, digital versatile discs (DVDs), floppy disks, and Blu-ray disks, where disks are usually magnetic It reproduces data optically, while discs reproduce data optically using a laser. Combinations of the above should also be included within the scope of computer-readable media.

The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other type of storage medium known in the art. An exemplary storage medium may be coupled to the processor such that the processor can read information from or write information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may also reside within the ASIC. The ASIC may exist in the user terminal. Alternatively, the processor and storage medium may exist as separate components in the user terminal.

The previous description of the present disclosure is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications of the present disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to various modifications without departing from the spirit or scope of the present disclosure. Accordingly, this disclosure is not intended to be limited to the examples described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Although exemplary implementations may refer to utilizing aspects of the currently disclosed subject matter in the context of one or more standalone computer systems, the subject matter is not so limited, but rather is associated with any computing environment, such as a network or distributed computing environment. It can also be implemented. Furthermore, aspects of the presently disclosed subject matter may be implemented in or across multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include PCs, network servers, and handheld devices.

Although the subject matter has been described in language specific to structural features and/or methodological actions, it will be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and acts described above are described as an exemplary form of implementing the claims.

Although the method mentioned in this specification has been described through specific embodiments, it is possible to implement it as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, the computer-readable recording medium is distributed over a computer system connected through a network, so that computer-readable codes can be stored and executed in a distributed manner. Further, functional programs, codes, and code segments for implementing the embodiments can be easily inferred by programmers in the technical field to which the present invention belongs.

Although the present disclosure has been described in connection with some embodiments herein, it should be understood that various modifications and changes may be made without departing from the scope of the present disclosure that can be understood by those skilled in the art to which the present invention belongs. something to do. In addition, such modifications and changes should be considered to fall within the scope of the claims appended to this specification.

110: user terminal 120: search window
130: terminal screen 140: listing
150: filter 210: communication network
220: server device 230_1 to 230_n: brokerage office server
310: communication module 320: processor
322: property extraction module 324: warning decision module
326: random number range calculation module 328: final random number calculation module
330: output module 340: database
350: Property information DB 360: Brokerage information DB
710: false property report vector 712: warning count vector
720: input layer 730_1 to 730_n: hidden layer
740: output layer 750: number of warnings 0 vector
752: warning number 1 vector 754: warning number 2 vector
756: warning count 3 vector 758: warning count 4 vector
900: property condition input interface 910: property type selection tab
912: search button 914: input window
1000: list output interface 1010: property list

Claims (11)

In a computing device for inspecting a false property,
A property extraction module configured to receive a condition of a property desired by the user from the user terminal and extract a property list including at least one property meeting the condition of the received property from among a plurality of properties stored in the property database;
Based on the false sale report information included in the information on the plurality of brokerage businesses stored in the for sale database, configured to determine the number of warnings of each of the one or more brokerage firms that have uploaded each of the one or more listings included in the extracted listing. Warning decision module;
A random number range calculation module configured to adjust a maximum value of a random number range in which a random number is output according to the number of warnings of each of the one or more brokerage firms, and associate the adjusted random number range with a property uploaded by the one or more brokerage firms;
A final random number calculation module configured to calculate a final random number within the adjusted random number range for the associated property; And
And an output module configured to sort the one or more items in the order of the size of the final random number, and to output a list of properties including the sorted one or more items,
The random number range calculation module,
If the first brokerage business among the one or more brokerage businesses is determined to be a brokerage business without warning, the maximum value of the range of random numbers associated with the first brokerage business is set to the maximum,
As the number of warnings of the second brokerage business among the one or more brokerage businesses increases, the maximum value of the random number range associated with the second brokerage business is gradually decreased,
The warning determination module,
It is configured to determine the number of warnings of each of the plurality of brokerages stored in the property database for each predetermined period based on the information of the plurality of brokerages, and to store the determined number of warnings in the property database,
The information on the plurality of brokerage firms further includes a number of warnings to each of the plurality of brokerage firms, information on a property registered by each of the plurality of brokerage firms, and history information on the registered property,
The number of warnings of each of the plurality of brokerages, information on the properties registered by each of the plurality of brokerages, and history information on the registered properties are input to the input layer of the artificial neural network, and the maximum value of the random number range of the brokerage Further comprising a learning module configured to generate the artificial neural network to determine,
The random number range calculation module,
Input the number of warnings of each of the one or more brokerage firms, information on each registered property of the one or more brokerage firms, and history information of each registered property of the one or more brokerage firms into the artificial neural network, and through the artificial neural network And determining a maximum value of each random number range of the at least one brokerage.
delete delete delete delete delete delete The method of claim 1,
The random number range calculation module,
When the second brokerage agency receives one warning, the maximum value of the random number range is randomly set between 100 and 85,
When the second brokerage agency receives two warnings, the maximum value of the random number range is randomly set between 100 and 70,
When the second agency receives three warnings, the maximum value of the random number range is randomly set between 100 and 55,
The computing device configured to randomly set a maximum value of the random number range between 100 and 40 when the second brokerage agency receives the warning 4 times.
In a method for inspecting a false property by a computing device,
Receiving a condition of a property desired by the user from a user terminal, and extracting a property list including at least one property matching the condition of the received property from a plurality of properties stored in a property database;
Determining the number of warnings of each of the one or more brokerage firms that have uploaded each of the one or more listings included in the extracted listing, based on the false sale report information included in the information on the plurality of brokerage firms stored in the listing database;
Adjusting a maximum value of the random number range in which the random number is output according to the number of warnings of each of the one or more brokerage businesses;
Associating the adjusted random number range with a property uploaded by the at least one brokerage agency;
Calculating a final random number within the adjusted random number range for the related article;
Arranging the at least one property in order of the size of the final random number, and outputting a property list including the aligned at least one property,
Adjusting the maximum value of the random number range,
Setting a maximum value of a range of random numbers associated with the first brokerage business to a maximum when the first brokerage business among the one or more brokerage businesses is determined to be a brokerage business without warning; And
As the number of warnings of the second brokerage business among the one or more brokerage businesses increases, the step of decreasing the maximum value of the random number range associated with the second brokerage business in stages,
The step of determining the number of warnings,
Determining the number of warnings of each of the plurality of brokerages stored in the property database for each predetermined period based on the information of the plurality of brokerage businesses, and storing the determined number of warnings in the property database,
The information on the plurality of brokerage firms further includes a number of warnings to each of the plurality of brokerage firms, information on a property registered by each of the plurality of brokerage firms, and history information on the registered property,
In the method, the number of warnings of each of the plurality of brokerages, information on a property registered by each of the plurality of brokerages, and history information on the registered property are input to the input layer of the artificial neural network, and the random number of the brokerage Further comprising the step of generating the artificial neural network to determine the maximum value of the range,
Adjusting the maximum value of the random number range,
Enter the number of warnings of each of the one or more brokerage firms, information on each registered property of the one or more brokerage firms, and history information of each registered property of the one or more brokerage firms into the artificial neural network, and through the artificial neural network Including the step of determining a maximum value of each random number range of the at least one brokerage,
How to inspect false property.
delete A computer-readable storage medium in which a program including instructions for performing each step according to the method of inspecting false property of claim 9 is recorded.

Images