KR20200000977A - Real estate point model based on big data analysis and recommendation algorithm system - Google Patents

Real estate point model based on big data analysis and recommendation algorithm system Download PDF

Info

Publication number
KR20200000977A
KR20200000977A KR1020180073353A KR20180073353A KR20200000977A KR 20200000977 A KR20200000977 A KR 20200000977A KR 1020180073353 A KR1020180073353 A KR 1020180073353A KR 20180073353 A KR20180073353 A KR 20180073353A KR 20200000977 A KR20200000977 A KR 20200000977A
Authority
KR
South Korea
Prior art keywords
score
real estate
item
user
scores
Prior art date
Application number
KR1020180073353A
Other languages
Korean (ko)
Inventor
김세정
Original Assignee
김세정
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 김세정 filed Critical 김세정
Priority to KR1020180073353A priority Critical patent/KR20200000977A/en
Publication of KR20200000977A publication Critical patent/KR20200000977A/en

Links

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—Systems or methods specially adapted for 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

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Accounting & Taxation (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The present invention relates to a big data analysis-based real estate product score model and a recommendation algorithm system. The present invention reflects demographic characteristics and preferences and uses public data such as traffic, education, and environment to score the suitability of each item for each individual and show apartments for sale with high scores. An objective of the present invention is to reduce information disparity between a seller, a licensed real estate broker and a buyer and to help the licensed real estate broker to consult with the buyer by actively reflecting various circumstances and preferences of the buyer.

Description

빅데이터분석 기반 부동산 매물 점수 모형 및 추천 알고리즘 시스템{REAL ESTATE POINT MODEL BASED ON BIG DATA ANALYSIS AND RECOMMENDATION ALGORITHM SYSTEM}REAL ESTATE POINT MODEL BASED ON BIG DATA ANALYSIS AND RECOMMENDATION ALGORITHM SYSTEM}

빅데이터 분석 기반 부동산 매물 점수 모형 및 추천 알고리즘 시스템에 관한 것이다.The present invention relates to a real estate sale score model and recommendation algorithm system based on big data analysis.

인구학적특성 및 취향을 반영하고 교통, 교육, 환경등의 공공데이터를 활용하여 개개인별로 각 매물들의 적합도를 점수화 하여 점수가 높은 아파트의 매물을 우선적으로 보여준다. 이는 매도자 및 공인중개사와 매수 희망자 간의 정보 불균형을 줄여주고 매수자의 다양한 상황 및 취향을 적극 반영하여 공인중개사가 상담할 수 있도록 돕는 것을 목표로 한다.It reflects demographic characteristics and tastes and uses public data such as traffic, education, and environment to score the suitability of each item for each individual, and shows the property of apartments with high scores first. This aims to reduce the information disparity between the seller and the authorized broker and the buyer, and to help the authorized broker to consult by actively reflecting the buyer's various circumstances and preferences.

기본 정보는 부동산의 소재지, 면적, 가격 범위를 포함하며, 희망 거래형태(매매,전세,월세)를 선택한다. 이때 매수희망자는 기본 정보 이외 본인의 생년월일, 결혼유무, 자녀 수 등의 개인정보도 입력한다. 서비스 이용자가 가중치를 줄 항목도 선택한다. DB에 저장된 전체 부동산의 기본 점수는 공공데이터를 기반으로 먼저 산출되며, 후에 서비스 이용자가 항목에 가중치를 부여하여 점수를 다시 산출된다. 서비스 이용자의 요구에 맞게 산출된 점수는 화면으로 전송된다. 점수 항목은 교육, 교통, 의료 등 데이터를 기반으로 서비스 모형에 따라 보여진다. 예를 들어 지하철역과의 거리가 가까울수록 교통서비스 모형 점수는 높아진다. 화면상에서는 위 그림과 같이 도출된 점수에 따라 점수로 확인할 수 있다. 따라서, 시스템의 단계는 웹을 통하여 1]사용자로부터 부동산 선정에 관한 기본 정보를 입력 받는 단계 2] 서버에 저장된 부동산 데이터베이스를 검색하여 상기 기본 정보에 맞는 부동산을 선정하는 단계 3] 선정된 부동산의 평가 항목별 점수를 각각 추출하는 단계 4] 항목별 점수에 가중치를 각각 부여하여 선정된 부동산의 평가 점수를 각각 구하는 단계 5] 사용자에게 평가 점수에 대한 정보를 제공하는 단계로 구분된다.The basic information includes the location, area and price range of the property, and selects the desired transaction type (sales, charter, rent). At this time, the purchaser enters personal information such as his / her date of birth, marital status, and number of children in addition to the basic information. The service consumer also selects items to be weighted. The basic score of all real estate stored in the DB is first calculated based on public data, and then the service user recalculates the score by weighting the item. The score calculated according to the request of the service user is transmitted to the screen. Score items are displayed according to the service model based on data such as education, transportation, and medical care. For example, the closer you are to a subway station, the higher the score for the transportation service model. On the screen, you can check the score according to the score derived as shown above. Therefore, the steps of the system are 1) receiving basic information on real estate selection from the user through the web 2] selecting real estate according to the basic information by searching the real estate database stored in the server 3] evaluating the selected real estate Steps for extracting the scores for each item 4] Steps for obtaining evaluation scores for the selected real estate by assigning weights to the scores for each item 5] Providing information on the evaluation scores to the user.

[1] 데이터베이스에 저장된 모든 아파트에 주변환경조건과 주택의 상세조건에 기본점수가 계산되에 데이터로 저장되어 있다.[1] In all apartments stored in the database, the basic scores are calculated and stored as data in the surrounding conditions and detailed conditions of the house.

[2] [1]의 기본점수는 교통안전(교통사고다발지, 어린이사고다발지 위치 등), 교통접근성(KTX, 지하철, 버스정거장 위치 등), 편의시설(백화점, 시장, 마트 위치 등), 치안시설(경찰서, CCTV 위치 등), 관리비(상, 중 하), 공원(산책로 위치 등), 의료시설(병원 위치, 진료과목 등), 주택완공일, 주택 방향, 주택 내부구조 등의 항목에 각각 점수가 부여되고 총점이 계산된다.[2] The basic scores of [1] are traffic safety (location of traffic accidents, location of child accidents, etc.), traffic accessibility (KTX, subway, bus stop location, etc.), convenience facilities (department stores, markets, mart locations, etc.). Items such as security facilities (police stations, CCTV locations, etc.), administrative expenses (upper and middle), parks (walking paths, etc.), medical facilities (hospital locations, medical treatments, etc.), housing completion dates, housing directions, internal structure Each score is assigned to the total score.

각각 항목에 대한 점수는 주택과 각 항목의 위치와의 거리, 각 항목의 개수, 관리비의 상중하를 기준으로 점수가 계산된다. 예를 들어 교통안전 항목은 주택과 사고다발지 위치와 가까울수록 그리고 주택 주변에 사고다발지의 갯수가 많을수록 점수가 낮아진다.The score for each item is calculated based on the distance between the house and the location of each item, the number of each item, and the top and bottom of the management fee. For example, traffic safety items have a lower score as they are closer to the location of the housing and accident cluster, and the greater the number of accident clusters around the housing.

[3] 사용자가 원하는 부동산 조건(위치, 종류, 면적, 거래 종류 등)을 선택한다.[3] Select the real estate conditions (location, type, area, transaction type, etc.) desired by the user.

[4] 데이터베이스에서 [3]에 해당하는 주택이 추출되고 추출된 주택에는 [1]의 기본점수가 부여되어 있다. [4] From the database, the house corresponding to [3] is extracted, and the extracted house is given a base score of [1].

[5] 사용자가 가중치를 주고자 하는 주변환경조건(교통안전, 교통접근성, 편의시설, 의료시설, 교육, 관리비 등)과 주택의 상세조건(관리비, 주택방향, 내부구조, 완공일 등)의 항목을 선택한다. [5] The conditions of the surrounding environment (traffic safety, traffic accessibility, convenience facilities, medical facilities, education, administrative expenses, etc.) and the detailed conditions of the housing (management expenses, housing direction, internal structure, completion date, etc.) Select the item.

예를 들어 사용자의 단말기 화면에 교통안전, 교통접근성, 교육, 치안, 공원, 관리비, 남향, 주택내부구조, 완공 날짜 등 제시된 항목 중 사용자가 중요하다고 판단하는 항목을 한가지 이상 선택한다. For example, select one or more items that the user considers important from among the items presented on the user's terminal screen, such as traffic safety, traffic accessibility, education, security, parks, administrative expenses, south-facing, housing structure, and completion date.

[6] [4]에 추출된 주택에 [5]에서 사용자가 선택한 항목에 가중치가 부여되어 [1]의 기본점수가 아닌 새로운 점수(2차점수)가 부여된다.[6] The house selected in [4] is weighted to the item selected by the user in [5], and a new score (secondary score) is given instead of the basic score of [1].

[7] [6]에 부여된 새로운 점수(2차점수)는 사용자의 단말기로 전송되어 단말기 화면에 보여진다.[7] The new score (secondary score) given to [6] is transmitted to the user's terminal and displayed on the terminal screen.

기본 정보는 부동산의 소재지, 면적, 가격 범위를 포함하며, 희망 거래형태(매매,전세,월세)를 선택한다. 이때 매수희망자는 기본 정보 이외 본인의 생년월일, 결혼유무, 자녀 수 등의 개인정보도 입력한다. 서비스 이용자가 가중치를 줄 항목도 선택한다. DB에 저장된 전체 부동산의 기본 점수는 공공데이터를 기반으로 먼저 산출되며, 후에 서비스 이용자가 항목에 가중치를 부여하여 점수를 다시 산출된다. 서비스 이용자의 요구에 맞게 산출된 점수는 화면으로 전송된다. 점수 항목은 교육, 교통, 의료 등 데이터를 기반으로 서비스 모형에 따라 보여진다. 예를 들어 지하철역과의 거리가 가까울수록 교통서비스 모형 점수는 높아진다. 화면상에서는 위 그림과 같이 도출된 점수에 따라 점수로 확인할 수 있다. 따라서, 시스템의 단계는 웹을 통하여 1]사용자로부터 부동산 선정에 관한 기본 정보를 입력 받는 단계 2] 서버에 저장된 부동산 데이터베이스를 검색하여 상기 기본 정보에 맞는 부동산을 선정하는 단계 3] 선정된 부동산의 평가 항목별 점수를 각각 추출하는 단계 4] 항목별 점수에 가중치를 각각 부여하여 선정된 부동산의 평가 점수를 각각 구하는 단계 5] 사용자에게 평가 점수에 대한 정보를 제공하는 단계로 구분된다.The basic information includes the location, area and price range of the property, and selects the desired transaction type (sales, charter, rent). At this time, the purchaser enters personal information such as his / her date of birth, marital status, and number of children in addition to the basic information. The service consumer also selects items to be weighted. The basic score of all real estate stored in the DB is first calculated based on public data, and then the service user recalculates the score by weighting the item. The score calculated according to the request of the service user is transmitted to the screen. Score items are displayed according to the service model based on data such as education, transportation, and medical care. For example, the closer you are to a subway station, the higher the score for the transportation service model. On the screen, you can check the score according to the score derived as shown above. Therefore, the steps of the system are 1) receiving basic information on real estate selection from the user through the web 2] selecting real estate according to the basic information by searching the real estate database stored in the server 3] evaluating the selected real estate Steps for extracting the scores for each item 4] Steps for obtaining the evaluation scores of the selected real estate by assigning weights to the item scores respectively 5] Providing information on the evaluation scores to the user.

도 1은 본 발명에 따른 단계들을 설명하기 위한 흐름도이다.
도 2 및 3은 구동되는 화면들을 나타내는 도면들이다.1 is a flow chart for explaining the steps according to the present invention.
2 and 3 are diagrams illustrating screens driven.

[1] 데이터베이스에 저장된 모든 아파트에 주변환경조건과 주택의 상세조건에 기본점수가 계산되에 데이터로 저장되어 있다.[1] In all apartments stored in the database, the basic scores are calculated and stored as data in the surrounding conditions and detailed conditions of the house.

[2] [1]의 기본점수는 교통안전(교통사고다발지, 어린이사고다발지 위치 등), 교통접근성(KTX, 지하철, 버스정거장 위치 등), 편의시설(백화점, 시장, 마트 위치 등), 치안시설(경찰서, CCTV 위치 등), 관리비(상, 중 하), 공원(산책로 위치 등), 의료시설(병원 위치, 진료과목 등), 주택완공일, 주택 방향, 주택 내부구조 등의 항목에 각각 점수가 부여되고 총점이 계산된다.[2] The basic scores of [1] are traffic safety (location of traffic accidents, location of child accidents, etc.), traffic accessibility (KTX, subway, bus stop location, etc.), convenience facilities (department stores, markets, mart locations, etc.). Items such as security facilities (police stations, CCTV locations, etc.), administrative expenses (upper and middle), parks (walking paths, etc.), medical facilities (hospital locations, medical treatments, etc.), housing completion dates, housing directions, internal structure Each score is assigned to the total score.

각각 항목에 대한 점수는 주택과 각 항목의 위치와의 거리, 각 항목의 개수, 관리비의 상중하를 기준으로 점수가 계산된다. 예를 들어 교통안전 항목은 주택과 사고다발지 위치와 가까울수록 그리고 주택 주변에 사고다발지의 갯수가 많을수록 점수가 낮아진다.The score for each item is calculated based on the distance between the house and the location of each item, the number of each item, and the top and bottom of the management fee. For example, traffic safety items have a lower score as they are closer to the location of the housing and accident cluster, and the greater the number of accident clusters around the housing.

[3] 사용자가 원하는 부동산 조건(위치, 종류, 면적, 거래 종류 등)을 선택한다.[3] Select the real estate conditions (location, type, area, transaction type, etc.) desired by the user.

[4] 데이터베이스에서 [3]에 해당하는 주택이 추출되고 추출된 주택에는 [1]의 기본점수가 부여되어 있다. [4] From the database, the house corresponding to [3] is extracted, and the extracted house is given a base score of [1].

[5] 사용자가 가중치를 주고자 하는 주변환경조건(교통안전, 교통접근성, 편의시설, 의료시설, 교육, 관리비 등)과 주택의 상세조건(관리비, 주택방향, 내부구조, 완공일 등)의 항목을 선택한다. [5] The conditions of the surrounding environment (traffic safety, traffic accessibility, convenience facilities, medical facilities, education, administrative expenses, etc.) and the detailed conditions of the housing (management expenses, housing direction, internal structure, completion date, etc.) Select the item.

예를 들어 사용자의 단말기 화면에 교통안전, 교통접근성, 교육, 치안, 공원, 관리비, 남향, 주택내부구조, 완공 날짜 등 제시된 항목 중 사용자가 중요하다고 판단하는 항목을 한가지 이상 선택한다. For example, select one or more items that the user considers important from among the items presented on the user's terminal screen, such as traffic safety, traffic accessibility, education, security, parks, administrative expenses, south-facing, housing structure, and completion date.

[6] [4]에 추출된 주택에 [5]에서 사용자가 선택한 항목에 가중치가 부여되어 [1]의 기본점수가 아닌 새로운 점수(2차점수)가 부여된다.[6] The house selected in [4] is weighted to the item selected by the user in [5], and a new score (secondary score) is given instead of the basic score of [1].

[7] [6]에 부여된 새로운 점수(2차점수)는 사용자의 단말기로 전송되어 단말기 화면에 보여진다.[7] The new score (secondary score) given to [6] is transmitted to the user's terminal and displayed on the terminal screen.

Claims (1)

기본 정보는 부동산의 소재지, 면적, 가격 범위를 포함하며, 희망 거래형태(매매,전세,월세)를 선택한다. 이때 매수희망자는 기본 정보 이외 본인의 생년월일, 결혼유무, 자녀 수 등의 개인정보도 입력한다. 서비스 이용자가 가중치를 줄 항목도 선택한다. DB에 저장된 전체 부동산의 기본 점수는 공공데이터를 기반으로 먼저 산출되며, 후에 서비스 이용자가 항목에 가중치를 부여하여 점수를 다시 산출된다. 서비스 이용자의 요구에 맞게 산출된 점수는 화면으로 전송된다. 점수 항목은 교육, 교통, 의료 등 데이터를 기반으로 서비스 모형에 따라 보여진다. 예를 들어 지하철역과의 거리가 가까울수록 교통서비스 모형 점수는 높아진다. 화면상에서는 위 그림과 같이 도출된 점수에 따라 점수로 확인할 수 있다. 따라서, 시스템의 단계는 웹을 통하여 1]사용자로부터 부동산 선정에 관한 기본 정보를 입력 받는 단계 2] 서버에 저장된 부동산 데이터베이스를 검색하여 상기 기본 정보에 맞는 부동산을 선정하는 단계 3] 선정된 부동산의 평가 항목별 점수를 각각 추출하는 단계 4] 항목별 점수에 가중치를 각각 부여하여 선정된 부동산의 평가 점수를 각각 구하는 단계 5] 사용자에게 평가 점수에 대한 정보를 제공하는 단계로 구분된다.The basic information includes the location, area and price range of the property, and selects the desired transaction type (sales, charter, rent). At this time, the purchaser enters personal information such as his / her date of birth, marital status, and number of children in addition to the basic information. The service consumer also selects items to be weighted. The basic score of all real estate stored in the DB is first calculated based on public data, and then the service user recalculates the score by weighting the item. The score calculated according to the request of the service user is transmitted to the screen. Score items are displayed according to the service model based on data such as education, transportation, and medical care. For example, the closer you are to a subway station, the higher the score for the transportation service model. On the screen, you can check the score according to the score derived as shown above. Therefore, the steps of the system are 1) receiving basic information on real estate selection from the user through the web 2] selecting real estate according to the basic information by searching the real estate database stored in the server 3] evaluating the selected real estate Steps for extracting the scores for each item 4] Steps for obtaining evaluation scores for the selected real estate by assigning weights to the scores for each item 5] Providing information on the evaluation scores to the user.
KR1020180073353A 2018-06-26 2018-06-26 Real estate point model based on big data analysis and recommendation algorithm system KR20200000977A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020180073353A KR20200000977A (en) 2018-06-26 2018-06-26 Real estate point model based on big data analysis and recommendation algorithm system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020180073353A KR20200000977A (en) 2018-06-26 2018-06-26 Real estate point model based on big data analysis and recommendation algorithm system

Publications (1)

Publication Number Publication Date
KR20200000977A true KR20200000977A (en) 2020-01-06

Family

ID=69158991

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020180073353A KR20200000977A (en) 2018-06-26 2018-06-26 Real estate point model based on big data analysis and recommendation algorithm system

Country Status (1)

Country Link
KR (1) KR20200000977A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220010941A (en) * 2020-07-20 2022-01-27 홍익대학교세종캠퍼스산학협력단 Bigdata-based residential model recommendation system for users and a method for recommending a residential model using the same

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220010941A (en) * 2020-07-20 2022-01-27 홍익대학교세종캠퍼스산학협력단 Bigdata-based residential model recommendation system for users and a method for recommending a residential model using the same

Similar Documents

Publication Publication Date Title
Kang et al. Validating activity, time, and space diversity as essential components of urban vitality
Önder et al. Spatial price dependencies between the traditional accommodation sector and the sharing economy
Widener et al. Using urban commuting data to calculate a spatiotemporal accessibility measure for food environment studies
Rosero-Bixby Spatial access to health care in Costa Rica and its equity: a GIS-based study
Burgoine et al. Assessing the obesogenic environment of North East England
Liu et al. Place niche and its regional variability: Measuring spatial context patterns for points of interest with representation learning
Liggett et al. Journeys to crime: Assessing the effects of a light rail line on crime in the neighborhoods
Bernasco et al. Where do dealers solicit customers and sell them drugs? A micro-level multiple method study
Zhang et al. The perceived importance and objective measurement of walkability in the built environment rating
Crotty et al. The red-light network: Exploring the locational strategies of illicit massage businesses in Houston, Texas
Vaitla et al. Big Data and the Well-being of women and girls: Applications on the Social Scientific Frontier
Smith Some social implications of ubiquitous wireless networks
Opfer Using GIS technology to identify and analyze ‘Food deserts’ on the southern Oregon coast
Xu et al. Spatial effect of crime on peer-to-peer lodging performance
Liu et al. Assessing the intraday variation of the spillover effect of tweets-derived ambient population on crime
Wuerzer et al. Retail gravitation and economic impact: A market-driven analytical framework for bike-share station location analysis in the United States
Tacoral et al. A sustainability assessment of quality of life in a traditional settlement pattern: The case of Kemaliye, Turkey
Huang Simulating individual work trips for transit-facilitated accessibility study
KR20200000977A (en) Real estate point model based on big data analysis and recommendation algorithm system
WO2018123358A1 (en) Information processing device, information processing method, and program
Bowie et al. Variation in health and social equity in the spaces where we live: a review of previous literature from the GeoHealth Laboratory
Lesan et al. A mixed methods approach to understanding streetscape preferences in a multicultural setting
US20190362432A1 (en) Compliance Aware Crime Risk Avoidance System
Douard et al. Retail attraction revisited: From gravitation to purchase flows, a geomarketing application
Matti et al. The location of urban healthcare services: Evidence from Phoenix Yelp reviews