WO2021117928A1 - 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법 및 서버 - Google Patents
소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법 및 서버 Download PDFInfo
- Publication number
- WO2021117928A1 WO2021117928A1 PCT/KR2019/017492 KR2019017492W WO2021117928A1 WO 2021117928 A1 WO2021117928 A1 WO 2021117928A1 KR 2019017492 W KR2019017492 W KR 2019017492W WO 2021117928 A1 WO2021117928 A1 WO 2021117928A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- real estate
- user
- customized
- model
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 235000013410 fast food Nutrition 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Definitions
- the present invention relates to a method for recommending customized real estate information, and more particularly, to a method and a server for recommending personalized real estate information by analyzing major factors affecting decision-making using a consumer selection model.
- Real estate information has traditionally been provided through the human network of real estate agents, but with the development of the Internet, services providing real estate information through the Internet have spread. In particular, it has been widely used for the purpose of helping real estate transaction brokerage by posting real estate sales information through the Internet.
- real estate information provided by large portals, online sites of small and medium-sized real estate franchise companies, and real estate information provided by advertising agencies, etc. are only providing basic specifications such as the area, amount, and area of real estate for sale. It looks like you can find it, but in order to actually get a contract, you have no choice but to find a real estate sale by calling a number of real estate agents or visiting a real estate agent directly and investing a lot of time and effort.
- the present invention provides a method for recommending real estate customized information using a consumer selection model to solve the problems of the prior art.
- a consumer selection model is constructed, and individual weights are calculated using element-specific value analysis techniques to provide personalized information.
- the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.
- the method for recommending customized real estate information using a consumer selection model is to generate real estate information data by applying a pre-processing process to real estate information collected through a network. step; selecting a real estate decision parameter through a consumer selection model based on the real estate information data; When new user information is input, the new user information is input into the real estate information recommendation model to calculate the user weight score for each selected real estate decision parameter, and according to the calculated user weight score, customized real estate information data including recommended real estate information is generated to do; and providing customized real estate information data to the user terminal.
- real estate information data can be generated by applying a pre-processing process including information directly or indirectly generated by users and information collected offline.
- the real estate customized information recommendation server using the consumer selection model includes a memory in which a real estate customized information recommendation program using the consumer selection model is stored; It includes a processor for executing a program stored in the memory.
- the processor generates real estate information data by applying a pre-processing process to real estate information collected through the network by executing the program, selects real estate decision parameters through a consumer selection model based on the real estate information data, and new user information
- new user information is entered into the real estate information recommendation model to calculate the user weight score for each selected real estate decision parameter, and according to the calculated user weight score, customized real estate information data including recommended real estate information is generated, and customized Real estate information data is provided to the user terminal.
- FIG. 1 is a block diagram illustrating a configuration of a real estate customized information recommendation server using a consumer selection model according to an embodiment of the present invention.
- FIG. 2 is a block diagram illustrating a configuration of a real estate customized information recommendation system using a consumer selection model according to an embodiment of the present invention.
- FIG. 3 is a flowchart illustrating a process step of a method for recommending customized real estate information using a consumer selection model according to an embodiment of the present invention.
- FIG. 4 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- FIG. 5 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- FIG. 6 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- FIG. 7 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- FIG. 1 is a block diagram illustrating a configuration of a real estate customized information recommendation server using a consumer selection model according to an embodiment of the present invention.
- the real estate customized information recommendation server 100 using the consumer selection model may include a communication module 110 , a memory 120 , a processor 130 , a database 140 , and an input module 150 .
- the communication module 110 communicates data with the connected user terminal 100 and the interworking server 200, respectively.
- the communication module 110 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals through wired/wireless connection with other network devices.
- the memory 120 stores a real estate customized information recommendation program using a consumer selection model.
- the real estate customized information recommendation program using the consumer selection model generates real estate information data by applying a pre-processing process to the real estate information collected through the network, selects real estate decision-making parameters through the consumer selection model based on the real estate information data, and , when new user information is input, the new user information is input into the real estate information recommendation model to calculate a user weight score for each selected real estate decision parameter, and customized real estate including recommended real estate information according to the calculated user weight score Generate information data, and provide the customized real estate information data to the user terminal.
- various types of data generated during the execution of an operating system for driving the real estate customized information recommendation server 100 using the consumer selection model or the real estate customized information recommendation program using the consumer selection model are stored in the memory 120 .
- the memory 120 collectively refers to a non-volatile storage device that continuously maintains stored information even when power is not supplied, and a volatile storage device that requires power to maintain the stored information.
- the memory 120 may perform a function of temporarily or permanently storing data processed by the processor 130 .
- the memory 120 may include magnetic storage media or flash storage media in addition to the volatile storage device requiring power to maintain stored information, but the scope of the present invention is limited thereto. it is not going to be
- the processor 130 executes the program stored in the memory 140 , but controls the entire process according to the execution of the real estate customized information recommendation program using the consumer selection model. Each operation performed by the processor 130 will be described in more detail later.
- the processor 130 may include any type of device capable of processing data.
- it may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed as a code or instruction included in a program.
- a microprocessor a central processing unit (CPU), a processor core, a multiprocessor, an application-specific (ASIC) An integrated circuit
- a processing device such as a field programmable gate array (FPGA) may be included, but the scope of the present invention is not limited thereto.
- the database 140 stores or provides data required for a real estate customized information recommendation system using a consumer selection model under the control of the processor 130 .
- the database 140 may be included as a component separate from the memory 140 , or may be built in a part of the memory 140 .
- FIG. 2 is a block diagram illustrating a configuration of a real estate customized information recommendation system using a consumer selection model according to an embodiment of the present invention.
- the real estate customized information recommendation method using the consumer selection model may be implemented in the server 100 or the user terminal 200 .
- Data analysis based on the collected real estate information may be performed in the server 100 , and customized real estate information data may be provided to the user terminal 200 .
- FIG. 3 is a flowchart illustrating a process step of a method for recommending customized real estate information using a consumer selection model according to an embodiment of the present invention.
- the processor 130 generates real estate information data by applying a pre-processing process to real estate information collected through a network.
- the processor 130 may recognize and group a plurality of real estate information for the same real estate as one integrated group by applying a pre-processing process. For example, information on the same sale registered on a plurality of real estate information platforms can be organized into one piece of information, or information about the same sale item uploaded by each real estate agent on the same real estate information platform can be integrated into one piece of information.
- the processor 130 may filter the currently invalid real estate information in consideration of the upload timing of real estate information, whether the transaction is completed, and the like.
- the real estate information data includes individual real estate feature data and real estate environment information
- the individual real estate feature data includes one or more of price information, structure information, size information, number of floors, facility aging information, public facility information, or parking information
- the real estate environment information may include one or more of traffic information, school district information, or surrounding environment information.
- the processor 130 selects a real estate decision parameter through a consumer selection model based on the real estate information data.
- the processor 130 may quantitatively analyze major factors affecting decision-making during a real estate transaction through a consumer selection model to select parameters affecting decision-making. For example, when a user selects a real estate, it is possible to extract parameters for size, structure, age, traffic information, school district information, complex size, etc., and determine the payment intention according to the parameter change while adjusting the value of each parameter. have. At this time, the real estate decision parameters may be sorted in the order of the parameters with the highest payment intention, and the real estate decision parameters to be used for the real estate recommendation may be selected according to the set criteria.
- the processor 130 may receive new user information from the user terminal.
- the new user information may include one or more of age, gender, job information, work location information, preferred area information, acquaintance information, budget information, and purchase purpose information.
- the processor 130 may then provide a user value evaluation test to the user terminal, receive the user value evaluation test result, and include it in the new user information.
- the user value evaluation test consists of step-by-step question information, "fitness to go to work (subway/bus/car)", “suitability to study (school/hakwon)", “suitability for shopping (mart facilities, department stores)", “fitness to eat out” (Fast food, Korean restaurant, cafe, etc.) Fit”, “Delivery order (number of companies listed on the mobile app for the user's residential area) Suitability”, “Late night walking (safety) suitability", “Parking It may consist of questions such as “fitness”, “fitness to go to the hospital”, “fitness to exercise”, and “fitness to walk”.
- the processor 130 may collect the user's information while repeating the steps of presenting two pieces of real estate information to the user through a user value evaluation test and allowing the user to select preferred real estate information.
- the processor 130 may provide different prices for each real estate information, and may determine the intention to pay for each parameter of the real estate information according to the user's repeated selection.
- the processor 130 calculates a user weight score for each selected real estate decision parameter by inputting new user information into the real estate information recommendation model.
- the real estate information recommendation model may be to calculate a user weight score using a value analysis technique for each element, and generate recommended real estate information according to the weight score.
- Elemental value analysis is a technique for predicting which product a customer will choose by estimating the value that a customer attaches to each attribute of a product or service. It is one of the methods for measuring specific factors of consumer behavior. . When consumer behavior is triggered with a specific goal, various psychological factors of the consumer are involved, and the mechanism of purchase decision becomes more complex, so it is necessary to conduct research in advance, analyze customer preferences and the results, and provide product can be optimized.
- the real estate information recommendation model may be learned using an artificial neural network by inputting the real estate information data and new user information, calculate a user weight score, and generate recommended real estate information according to the weight score. Also, after providing the customized real estate information data to the user terminal, the method may further include evaluating the accuracy of the recommended real estate information, and updating the evaluated accuracy in the real estate information recommendation model.
- the real estate information recommendation model can use any one of collaborative filtering, content-based filtering, and hybrid, which predicts users' preferred information by analyzing information such as users' usage patterns and consumption records. , it is also possible to use a recommendation model using an artificial neural network.
- the processor 130 may extract text by performing logistic regression on each word in the collected information using a text extraction module based on a recurrent neural network.
- the recurrent neural network may use bidirectional LSTM (Long Short Term Memory models).
- the processor 130 generates customized real estate information data including recommended real estate information according to the calculated user weight score.
- the processor 130 provides the customized real estate information data to the user terminal.
- FIG. 4 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- new user information can be collected through membership registration, etc.
- the main personal information is as follows.
- composition of the family that will be living in the future it is possible to collect information about adults, children's age, school age, number of people, whether there are additional family plans, and pet information. You can collect information on your current residence, major bases, most frequently visited points, frequency of visits, means of transportation, and movement routes. A plurality of preferred local information may be collected. Additionally, age, car ownership, type of car, and hobby information related to real estate selection can be collected.
- Factor-by-factor value analysis can be leveraged to leverage the new user information collected to construct questions for screening real estate decision parameters through a consumer choice model.
- a question for prioritizing real estate decision-making parameters is shown in FIG. 4 .
- the steps of providing the user with two pieces of real estate information and selecting the preferred real estate information may be repeated several times.
- FIG. 5 is a view for explaining a user value evaluation test for new user information collection of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- the question of FIG. 5 is for prioritizing locations.
- a preferred location is selected on the map, user value evaluation is possible according to the selection. For example, if a preferred location is selected based on a component including a school, a subway, a company, and a department store, the weight of each component may be increased according to the selection. You can evaluate location preference by repeating the question.
- FIG. 6 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- the steps of providing the user with two pieces of real estate information and selecting the preferred real estate information may be repeated several times. At this time, by changing the price in the same question and repeating the question, it is possible to determine how much willingness to pay for each component is.
- FIG. 7 is a view for explaining a step of calculating a user weight score for each real estate decision parameter selected in the real estate information recommendation model of the real estate customized information recommendation method using the consumer selection model according to an embodiment of the present invention.
- the value system of Mr. A can be evaluated through new user information collection and user value evaluation test, and the score for each parameter of K apartment can be evaluated from the collected real estate information data, and by combining the results, Mr. A's K An expected evaluation score for the apartment can be calculated.
- a method for recommending customized real estate information using a consumer selection model may transmit step-by-step question information to a user terminal for step-by-step collection of lifestyle data, and store the answer result in a database.
- the server 100 accumulates, for each parameter, a relative rating for a region and a community of a user who operates each user terminal 200 as a 'first staged question information category'.
- the question could be:
- the server 100 asks the user who operates the user terminal 200 "information about the area where they live, apartment", receives the address information as answer information, and transmits the address information to the address information providing server, A dwelling corresponding to the information may receive information on the size of a building or apartment.
- the server 100 collects answer information for each parameter as to whether it is a good place to live through the lifestyle of the user who operates each user terminal 200 as a 'second stage question information category' do.
- the server 100 additionally includes a machine learning module for a lifestyle question (Action oriented question), and statisticizes the evaluation value for each parameter answer by the machine learning module.
- a machine learning module for a lifestyle question Action oriented question
- the server 100 accumulates big data for a preset area including the user's residence for a preset period, the common denominator of users for an apartment or region comes out, and a rating for each parameter is obtained. perform the extraction process. More specifically, the server 100 receives the size information of the building or apartment as answer information for the 'first-stage question information category', and then the 'second-stage question information category in the area for the building or apartment. As the answer information for ', a rating for each parameter for lifestyle is recommended and stored in the database.
- the server 100 performs an individual house characteristic data accumulation process from each seller's terminal or real estate broker's terminal through the network. That is, since the server 100 needs to collect data on the detailed characteristics of individual houses, 'individual house characteristic data' directly from a real estate broker terminal operated by a real estate broker who intends to sell real estate or a seller terminal operated by the landlord It can be received, and it can be collected by extracting a source from big data stored in an external server.
- the individual house characteristic data may include the number and structure of rooms, the size of each room, the number of floors, the degree of deterioration of the facility (toilet, sink, floor, etc.), and state information of public facilities (security room, elevator, hallway, etc.).
- the most similar big data stored in the real estate brokerage server via intranet by each real estate agent terminal is followed by the selection signal received from the real estate agent terminal or the seller terminal. It may be collected in a way the real estate agent or seller selectively chooses.
- a floor plan that automatically draws a floor plan through camera shooting The method of collecting the floor plan drawn through the drawing app, or the method of collecting the calculated room size information through the room area calculation app that automatically calculates the size of the room automatically through camera shooting based on the wall of the individual room can be done with
- the server ( 100) After access to the server 100 through the network for a real estate search request including weight information for each parameter of the lifestyle data to live in of the user terminal 200 and each parameter information of individual house characteristic data, the server ( 100) can perform matching with scores for each parameter generated by statisticizing evaluation values in the step-by-step collection of lifestyle data, and analysis of individual houses having the closest information to each parameter information of individual house characteristic data. .
- the server 100 extracts high-ranked real estate listing information up to a preset rank matching the score for each parameter and individual house characteristic data, and provides it to the user terminal 200 requesting a real estate search through the network. That is, in the stage corresponding to the new user, score analysis for each parameter for the user who requested real estate search is performed, and whether the score for each parameter is matched or not, as well as each parameter information of individual house characteristic data By analyzing whether or not it matches, it is possible to provide real estate sales information for the top five, for example, a preset ranking that matches the most. For this real estate sale information, the server 100 said, "As a result of analyzing the data of 2800 people in the area, which apartment house, which lake, and what price is the house that you would like among them. You can provide online services through the message "We have the following list of items".
- the server 100 After the user terminal 200 accesses the server 100 for a real estate search request, it is possible to analyze the score for each parameter in the step-by-step collection of lifestyle data. That is, after access to the server 100 through the network for a real estate search request including weight information for each parameter of the lifestyle data of the user terminal 200 and each parameter information of individual real estate characteristic data, The server 100 performs analysis of individual real estate having the closest information to each parameter information of individual real estate feature data and matching with scores for each parameter generated by statisticizing evaluation values in the step-by-step collection of lifestyle data. Then, create a list of individual real estate.
- the server 100 collects profile information from the user terminal 200 .
- Information about each user's profile collects information about the area, locality, facilities, acquaintances, budget, and authenticity to find.
- the server 100 hides the provided information and personal identification information of each user and transmits the individual house list and profile information to the designated real estate agent terminal, so that the real estate matched by the real estate agent through the matching of the profile information and the profile information A recommendation to the user terminal 200 that has performed the steps for the item for sale is performed.
- the server operator can acquire a commission for the real estate broker who operates the designated real estate agent terminal, while the real estate brokers are sincere and target customers who will like the real estate sale they have. opportunity may be provided.
- An embodiment of the present invention may be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer.
- Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media.
- Computer-readable media may include computer storage media.
- Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims (10)
- 서버에 의해 수행되는 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법에 있어서,(a) 네트워크를 통해 수집된 부동산 정보에 전처리 프로세스를 적용하여 부동산 정보 데이터를 생성하는 단계;(b) 상기 부동산 정보 데이터에 기초하여 소비자 선택 모델을 통해 부동산 의사결정 파라미터를 선별하는 단계;(c) 신규 사용자 정보가 입력되면 상기 신규 사용자 정보를 부동산 정보 추천 모델에 입력하여 상기 선별된 부동산 의사결정 파라미터 별 사용자 가중치 점수를 계산하고, 상기 계산된 사용자 가중치 점수에 따라 추천 부동산 정보를 포함하는 맞춤형 부동산 정보 데이터를 생성하는 단계; 및(d) 상기 맞춤형 부동산 정보 데이터를 사용자 단말에 제공하는 단계;를 포함하는,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 전처리 프로세스는 동일 부동산에 대한 복수의 부동산 정보들을 하나의 통합된 그룹으로 인식하여 그룹화하고, 기설정된 조건에 해당하는 부동산 정보들을 필터링하는 단계를 포함하는,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 부동산 정보 데이터는 개별 부동산 특징 데이터 및 부동산 환경 정보를 포함하고,상기 개별 부동산 특징 데이터는 가격 정보, 구조 정보, 크기 정보, 층수, 시설의 노후도 정보, 공용시설 정보 또는 주차정보 중 하나 이상을 포함하고,상기 부동산 환경 정보는 교통 정보, 학군 정보 또는 주변 환경 정보 중 하나 이상을 포함하는 것인,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 신규 사용자 정보는 나이, 성별, 직업 정보, 직장위치 정보, 선호 지역 정보, 지인정보, 예산정보 또는 구매목적 정보 중 하나 이상을 포함하는 것인,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 (b)단계 이후 사용자 단말에 사용자 가치 평가 테스트를 제공하고, 상기 (c)단계에서 입력되는 신규 사용자 정보는 상기 사용자 가치 평가 테스트 결과를 포함하는 것인,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 부동산 정보 추천 모델은 요소별 가치 분석 기법을 이용하여 사용자 가중치 점수를 계산하고, 상기 가중치 점수에 따라 추천 부동산 정보를 생성하는 것인,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 1 항에 있어서,상기 부동산 정보 추천 모델은 상기 부동산 정보 데이터 및 신규 사용자 정보를 입력으로 인공신경망을 이용하여 학습되어 사용자 가중치 점수를 계산하고, 상기 가중치 점수에 따라 추천 부동산 정보를 생성하는 것인,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 제 7 항에 있어서,상기 (d)단계 이후 추천 부동산 정보의 정확도를 평가하고, 상기 평가된 정확도를 상기 부동산 정보 추천 모델에 업데이트 하는 단계를 더 포함하는,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법.
- 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 서버에 있어서,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 프로그램이 저장된 메모리;상기 메모리에 저장된 프로그램을 실행하는 프로세서를 포함하며, 상기 프로세서는 상기 프로그램의 실행에 의해,네트워크를 통해 수집된 부동산 정보에 전처리 프로세스를 적용하여 부동산 정보 데이터를 생성하고,상기 부동산 정보 데이터에 기초하여 소비자 선택 모델을 통해 부동산 의사결정 파라미터를 선별하고,신규 사용자 정보가 입력되면 상기 신규 사용자 정보를 부동산 정보 추천 모델에 입력하여 상기 선별된 부동산 의사결정 파라미터 별 사용자 가중치 점수를 계산하고, 상기 계산된 사용자 가중치 점수에 따라 추천 부동산 정보를 포함하는 맞춤형 부동산 정보 데이터를 생성하고,상기 맞춤형 부동산 정보 데이터를 사용자 단말에 제공하는,소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 서버.
- 제 1 항에 따르는 방법을 수행하기 위한 컴퓨터 프로그램이 기록된 비일시적 컴퓨터 판독가능 기록매체.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190164493A KR20210073819A (ko) | 2019-12-11 | 2019-12-11 | 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법 및 서버 |
KR10-2019-0164493 | 2019-12-11 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021117928A1 true WO2021117928A1 (ko) | 2021-06-17 |
Family
ID=76330403
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2019/017492 WO2021117928A1 (ko) | 2019-12-11 | 2019-12-11 | 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법 및 서버 |
Country Status (2)
Country | Link |
---|---|
KR (2) | KR20210073819A (ko) |
WO (1) | WO2021117928A1 (ko) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102432552B1 (ko) * | 2021-11-10 | 2022-08-12 | 김유신 | 인공지능 기반 매수인에게 매물을 자동으로 추천하는 부동산 거래 플랫폼의 운영 방법 |
KR102455636B1 (ko) * | 2022-02-17 | 2022-10-19 | 주식회사 에스씨컴퍼니 | 빅데이터 기반 인공지능을 이용한 맞춤형 3d 인테리어 시뮬레이션 서비스 제공 시스템 |
KR102461336B1 (ko) | 2022-07-12 | 2022-10-31 | 디노바디앤씨 주식회사 | 거주자 동선 기반 공유 주택 그룹 내 맞춤형 주택 추천 방법, 장치 및 시스템 |
KR102566017B1 (ko) * | 2022-08-26 | 2023-08-11 | 주식회사 굿픽 | 분양 대행 상품 정보 제공 관리 시스템 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120110074A (ko) * | 2012-08-23 | 2012-10-09 | 김영환 | 집합건물 매물정보의 제공 방법 및 시스템 |
JP2015001884A (ja) * | 2013-06-17 | 2015-01-05 | 新日鉄住金ソリューションズ株式会社 | 候補提示装置、候補提示方法及びプログラム |
US20170255986A1 (en) * | 2016-03-02 | 2017-09-07 | Social Data Sciences, Inc. | System to Customize Recommendations by Soliciting and Analyzing Suggestions and Evaluations Tailored to a Particular Subject |
KR101826647B1 (ko) * | 2016-10-19 | 2018-03-22 | 김성국 | 머신 러닝 기술을 통한 개인 맞춤형 자동차 중개 시스템 |
KR101975448B1 (ko) * | 2018-08-14 | 2019-05-08 | (주) 에이투연구소 | 인공지능을 이용하여 빅데이터 기반 상품 투자 추천 알고리즘을 평가하는 시스템 및 방법 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090126474A (ko) | 2008-06-04 | 2009-12-09 | 박소미 | 맞춤형 부동산 정보 제공 시스템 |
KR101698262B1 (ko) * | 2015-02-09 | 2017-02-01 | 엄주태 | 부동산 직거래 서비스 방법 |
-
2019
- 2019-12-11 WO PCT/KR2019/017492 patent/WO2021117928A1/ko active Application Filing
- 2019-12-11 KR KR1020190164493A patent/KR20210073819A/ko not_active IP Right Cessation
-
2022
- 2022-05-09 KR KR1020220056635A patent/KR102509598B1/ko active IP Right Grant
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120110074A (ko) * | 2012-08-23 | 2012-10-09 | 김영환 | 집합건물 매물정보의 제공 방법 및 시스템 |
JP2015001884A (ja) * | 2013-06-17 | 2015-01-05 | 新日鉄住金ソリューションズ株式会社 | 候補提示装置、候補提示方法及びプログラム |
US20170255986A1 (en) * | 2016-03-02 | 2017-09-07 | Social Data Sciences, Inc. | System to Customize Recommendations by Soliciting and Analyzing Suggestions and Evaluations Tailored to a Particular Subject |
KR101826647B1 (ko) * | 2016-10-19 | 2018-03-22 | 김성국 | 머신 러닝 기술을 통한 개인 맞춤형 자동차 중개 시스템 |
KR101975448B1 (ko) * | 2018-08-14 | 2019-05-08 | (주) 에이투연구소 | 인공지능을 이용하여 빅데이터 기반 상품 투자 추천 알고리즘을 평가하는 시스템 및 방법 |
Also Published As
Publication number | Publication date |
---|---|
KR20220065735A (ko) | 2022-05-20 |
KR20210073819A (ko) | 2021-06-21 |
KR102509598B1 (ko) | 2023-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021117928A1 (ko) | 소비자 선택 모델을 이용한 부동산 맞춤형 정보 추천 방법 및 서버 | |
US11093992B2 (en) | Smart matching for real estate transactions | |
Griffith et al. | Explorations into the relationship between spatial structure and spatial interaction | |
WO2017150772A1 (ko) | 부동산 정보 제공 및 공유 장치 | |
Walker et al. | Latent lifestyle preferences and household location decisions | |
Hu et al. | Data source combination for tourism demand forecasting | |
WO2020130369A1 (ko) | 온라인 마케팅 전략을 수립하기 위한 인공지능 분석 시스템 | |
Zou | Examining the impact of short-term rentals on housing prices in Washington, DC: Implications for housing policy and equity | |
Cui et al. | Travel behavior classification: an approach with social network and deep learning | |
Lam et al. | An artificial neural network and entropy model for residential property price forecasting in Hong Kong | |
Aznar et al. | An ANP framework for property pricing combining quantitative and qualitative attributes | |
CN105339976A (zh) | 用于允许以才能/履历为导向的学分的教育管理系统和教育管理方法 | |
Inoa et al. | Effect of an accessibility measure in a model for choice of residential location, workplace, and type of employment | |
Lu et al. | Market potential for smart growth neighbourhoods in the USA: A latent class analysis on heterogeneous preference and choice | |
Theisen et al. | House prices and proximity to kindergarten–costs of distance and external effects? | |
Wißotzki et al. | “Analyze & focus your intention” as the first step for applying the digital innovation and transformation process in zoos | |
Kirdar et al. | A decision support model to evaluate liveability in the context of urban vibrancy | |
JP7390633B2 (ja) | Aiを利用した不動産売却計画書オークションシステム | |
Zhou et al. | Evaluating the nonlinear impacts of built environment on online car-hailing: Focus on the whole day | |
JP2013210752A (ja) | 個人行動嗜好分析システムおよび個人行動嗜好分析方法 | |
JP7512635B2 (ja) | 住宅営業支援装置、住宅営業支援システム、住宅営業支援方法および住宅営業支援プログラム | |
JP7212103B2 (ja) | 情報処理装置、情報処理方法及び情報処理プログラム | |
Hanawa et al. | Recommendation system for tourist attractions based on Wi-Fi packet sensor data | |
KR102451835B1 (ko) | 중고 상품 시세 감정 방법 및 장치 | |
KR20150053313A (ko) | 맞춤형 정보 수집 및 효율적 소통을 위한 방법 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19955895 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19955895 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205N DATED 02/08/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19955895 Country of ref document: EP Kind code of ref document: A1 |