KR20220063969A - AI-based custom data delivery system - Google Patents

AI-based custom data delivery system Download PDF

Info

Publication number
KR20220063969A
KR20220063969A KR1020200149957A KR20200149957A KR20220063969A KR 20220063969 A KR20220063969 A KR 20220063969A KR 1020200149957 A KR1020200149957 A KR 1020200149957A KR 20200149957 A KR20200149957 A KR 20200149957A KR 20220063969 A KR20220063969 A KR 20220063969A
Authority
KR
South Korea
Prior art keywords
user
product
unit
data
value
Prior art date
Application number
KR1020200149957A
Other languages
Korean (ko)
Inventor
이희성
Original Assignee
플레인브레드 주식회사
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 플레인브레드 주식회사 filed Critical 플레인브레드 주식회사
Priority to KR1020200149957A priority Critical patent/KR20220063969A/en
Publication of KR20220063969A publication Critical patent/KR20220063969A/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
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • 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
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention relates to a data providing system based on artificial intelligence, wherein the behavioral pattern of a user can be predicted and data information optimized for the personal preference and propensity of the user can be provided in real time. According to the present invention, the behavioral pattern of the user can be predicted by reflecting the changing propensity of the user without relying on piecemeal information in real time, so data can be recommended by reflecting the propensity of the individual user, which cannot be known by average estimation, the scarcity problem of data and the expandability problem of the system can be overcome, and past data can be prevented from being recommended excessively if temporal analysis is applied, thereby enabling strategic marketing.

Description

AI 기반 맞춤형 데이터 제공 시스템{AI-based custom data delivery system}AI-based custom data delivery system {AI-based custom data delivery system}

본 발명은 통계 분석에 관한 것으로, 보다 구체적으로, 사용자의 행동 패턴을 예측하여 실시간으로 개인의 선호나 취향에 최적화된 데이터 정보를 제공할 수 있는 인공지능에 기반한 데이터 제공 시스템에 관한 것이다.The present invention relates to statistical analysis, and more particularly, to a data providing system based on artificial intelligence that can predict a user's behavior pattern and provide data information optimized for personal preference or taste in real time.

일반적으로, 통계에 기반한 마케팅 시스템은 관리자가 직접 설문지를 작성하고 집계한 후 입력하여 내용을 구축하며, 소비자가 입력한 내용은 관리자가 직접 검색 및 조회하여 이에 수동으로 응답하는 형태를 띠고 있다. 또한 통계 및 분석을 하는 데이터베이스 역시 구조적으로 저장과 출력을 하고 통계에 대한 결과만을 출력할 뿐 개인에게 적절한 데이터를 제시하지는 못한다.In general, in a marketing system based on statistics, a manager directly fills out a questionnaire, aggregates it, and then inputs it to build the contents, and the manager directly searches and inquires the contents entered by the consumer and manually responds to it. In addition, the database for statistics and analysis also stores and outputs structurally, and only outputs statistical results, but does not present appropriate data to individuals.

본 발명이 이루고자 하는 기술적 과제는 실시간으로 단편적인 정보에 의존하지 않고 변화하는 사용자의 취향을 반영하여 사용자의 행동 패턴을 예측하고, 데이터의 희박성 문제와 시스템 확장성 문제를 극복할 수 있는 인공지능에 기반한 맞춤형 데이터를 제공하는 데 있다.The technical task of the present invention is to predict the user's behavior pattern by reflecting the changing user's taste without relying on fragmentary information in real time, and to develop artificial intelligence that can overcome the problem of data sparseness and system scalability. It is to provide customized data based on

상기의 기술적 과제를 이루기 위하여, 본 발명은 사용자의 로그인 정보를 포함하는 현재 패턴 데이터 분석부; 사용자가 선택한 데이터를 수집하고 분석된 결과와 질의를 이용하여 행태 분석 및 시간 분석을 수행하여 대응하는 데이터 정보를 데이터베이스에서 추출 후 맞춤형 인터페이스 생성부를 포함하는, 인공지능에 기반한 개인별 맞춤형 데이터 제공 장치를 제공한다In order to achieve the above technical problem, the present invention provides a current pattern data analysis unit including login information of a user; It collects the data selected by the user, performs behavioral analysis and time analysis using the analyzed results and queries, extracts the corresponding data information from the database, and provides a personalized data providing device based on artificial intelligence, including a custom interface generator do

본 발명에 의하면, 실시간으로 단편적인 정보에 의존하지 않고 변화하는 사용자의 취향을 반영하여 사용자의 행동 패턴을 예측함으로써, 평균적인 예측으로 알 수 없는 개별 사용자의 취향을 반영하여 데이터를 추천할 수 있고, 데이터의 희박성 문제와 시스템 확장성 문제를 극복할 수 있으며, 시간 분석을 적용하는 경우, 과거의 데이터가 과도하게 추천되는 것을 방지할 수 있어 전략적인 마케팅을 가능하게 한다.According to the present invention, by predicting the user's behavior pattern by reflecting the user's changing taste without relying on piecemeal information in real time, it is possible to recommend data by reflecting the taste of individual users, which cannot be known by the average prediction, and , it can overcome the problem of sparseness of data and system scalability, and when time analysis is applied, it can prevent over-recommendation of past data, enabling strategic marketing.

도 1은 본 발명의 따른 인공지능에 기반한 개인별 맞춤형 상품 제공 방법의 흐름도이다.1 is a flowchart of a method for providing personalized products based on artificial intelligence according to the present invention.

본 발명에 대해 여러 가지 예를 가질 수 있는 바, 상세하게 설명하고자 한다. 상기의 기술적 과제를 이루기 위하여, 본 발명은 사용자의 로그인 정보를 포함하는 현재 패턴 데이터 분석부; 사용자가 선택한 데이터를 수집하고 분석된 결과와 질의를 이용하여 행태 분석 및 시간 분석을 수행하여 대응하는 데이터 정보를 데이터베이스에서 추출 후 맞춤형 인터페이스 생성부를 포함하는, 인공지능에 기반한 개인별 맞춤형 데이터 제공 장치를 제공한다.Since various examples of the present invention can be provided, it will be described in detail. In order to achieve the above technical problem, the present invention provides a current pattern data analysis unit including login information of a user; It collects the data selected by the user, performs behavioral analysis and time analysis using the analyzed results and queries, extracts the corresponding data information from the database, and provides a personalized data providing device based on artificial intelligence, including a custom interface generator do.

그러나, 이는 본 발명을 특정한 실시 형태에 대해 한정하려는 것이 아니며, 본 발명을 설명함에 있어서 관련된 공지 기술에 대한 구체적인 설명이 본 발명의 요지를 흐릴 수 있다고 판단되는 경우 그 상세한 설명을 생략한다.However, this is not intended to limit the present invention to specific embodiments, and when it is determined that a detailed description of a related known technology may obscure the gist of the present invention in describing the present invention, a detailed description thereof will be omitted.

도면1을 참고.See Figure 1.

Claims (1)

사용자의 로그인 정보를 포함하는 현재 패턴 데이터를 수집하여 분석하는 사용자 정보 분석부; 사용자가 선택하거나 구매한 상품과 관련된 데이터를 수집하여 분석하는 상품 정보 분석부; 상기 사용자 정보 분석부 및 상기 상품 정보 분석부에서 분석된 결과에 기반하여 상기 사용자의 속성 및 상기 상품의 속성들 사이의 관계를 설정하는 속성 매칭부; 상기 사용자의 속성 및 상기 상품의 속성들 각각의 가치를 측정하고 상기 설정된 관계에 대한 가치를 계산하는 가치 측정부; 상기 사용자가 상품마다 머문 시간 또는 현재 시간 중 적어도 하나에 기반하여 시간 분석을 수행하여 상기 가치 측정부에서 계산된 가치에 가중치를 부여하는 시간 분석부; 상기 가중치가 부여된 가치를 클러스터링하여 클러스터링 클래스를 추출하는 클러스터링부; 상기 추출된 클러스터링 클래스에 대응하는 상품 정보를 상품 데이터베이스에서 추출하는 맞춤형 상품 추출부; 및 상기 클러스터링 클래스에 대응하는 인터페이스를 구성하는 맞춤형 인터페이스 생성부를 포함하는, 인공지능에기반한 개인별 맞춤형 상품 제공 장치.a user information analysis unit that collects and analyzes current pattern data including the user's login information; a product information analysis unit that collects and analyzes data related to the product selected or purchased by the user; an attribute matching unit for setting a relationship between the user's attribute and the product's attributes based on the results analyzed by the user information analyzing unit and the product information analyzing unit; a value measuring unit for measuring the value of each of the attributes of the user and the attributes of the product and calculating a value for the set relationship; a time analysis unit that performs time analysis based on at least one of the time the user stayed for each product or the current time, and assigns a weight to the value calculated by the value measurement unit; a clustering unit for extracting a clustering class by clustering the weighted values; a customized product extraction unit for extracting product information corresponding to the extracted clustering class from a product database; and a custom interface generator that configures an interface corresponding to the clustering class.
KR1020200149957A 2020-11-11 2020-11-11 AI-based custom data delivery system KR20220063969A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020200149957A KR20220063969A (en) 2020-11-11 2020-11-11 AI-based custom data delivery system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020200149957A KR20220063969A (en) 2020-11-11 2020-11-11 AI-based custom data delivery system

Publications (1)

Publication Number Publication Date
KR20220063969A true KR20220063969A (en) 2022-05-18

Family

ID=81804289

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020200149957A KR20220063969A (en) 2020-11-11 2020-11-11 AI-based custom data delivery system

Country Status (1)

Country Link
KR (1) KR20220063969A (en)

Similar Documents

Publication Publication Date Title
CN108876526B (en) Commodity recommendation method and device and computer-readable storage medium
Jacobs et al. Model-based purchase predictions for large assortments
Thorleuchter et al. Predicting e-commerce company success by mining the text of its publicly-accessible website
CA2938561C (en) System for individualized customer interaction
US7016936B2 (en) Real time electronic service interaction management system and method
Fuchs et al. Multi-criteria ratings for recommender systems: an empirical analysis in the tourism domain
CN101271558A (en) Multi-policy commercial product recommending system based on context information
KR102451099B1 (en) Purchsase inducement system and method through inferencing user's needs based on artificial intelligence
US20170011421A1 (en) Preference analyzing system
US20210241310A1 (en) Intelligent advertisement campaign effectiveness and impact evaluation
KR101639656B1 (en) Method and server apparatus for advertising
Cao et al. Integrating OWA and data mining for analyzing customers churn in E-commerce
Mulyono et al. Evaluation of customer satisfaction on Indonesian banking chatbot services during the COVID-19 pandemic
CN111127074B (en) Data recommendation method
US20220188876A1 (en) Advertising method and apparatus for generating advertising strategy
Huseynov et al. Food decision-making under time pressure
Alzyadat et al. Big data, classification, clustering and generate rules: an inevitably intertwined for prediction
WO2002079901A2 (en) Customer preference system
KR20220063969A (en) AI-based custom data delivery system
US20230274155A1 (en) Systems and methods for empathy-based machine learning
Diamantaras et al. Predicting Shopping Intent of e-Commerce Users using LSTM Recurrent Neural Networks.
KR20200123086A (en) Create user-specific user interfaces
CN112116024B (en) Method and device for classifying models by user, electronic equipment and storage medium
Singh et al. Improving customer segmentation in e-commerce using predictive neural network
CN114840759A (en) Recommendation method and device and computer readable storage medium