KR20020025579A - AI Music system - Google Patents

AI Music system Download PDF

Info

Publication number
KR20020025579A
KR20020025579A KR1020000057502A KR20000057502A KR20020025579A KR 20020025579 A KR20020025579 A KR 20020025579A KR 1020000057502 A KR1020000057502 A KR 1020000057502A KR 20000057502 A KR20000057502 A KR 20000057502A KR 20020025579 A KR20020025579 A KR 20020025579A
Authority
KR
South Korea
Prior art keywords
music
user
list
users
downloaded
Prior art date
Application number
KR1020000057502A
Other languages
Korean (ko)
Inventor
김은민
정의용
Original Assignee
정문재
주식회사 미디어 스테이션
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 정문재, 주식회사 미디어 스테이션 filed Critical 정문재
Priority to KR1020000057502A priority Critical patent/KR20020025579A/en
Publication of KR20020025579A publication Critical patent/KR20020025579A/en

Links

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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]

Landscapes

  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Reverberation, Karaoke And Other Acoustics (AREA)

Abstract

PURPOSE: A method for recommending and embodying an artificial intelligent music is provided to recommend a music which downloaded many times by analyzing previous downloaded/streaming music data of a user, searching a user's music tendency, and comparing the data with downloaded/streaming music data of the other users. CONSTITUTION: If a user have downloaded/streamed 'a', 'b', and 'c' music, a site extracts a list of other users who have received at least one music, and forms a plurality of groups. The groups are classified according to a list including the groups of music. A weight value is provided to the user group having the list.

Description

인공지능형 음악 추천 구현 방법 {AI Music system}How to implement AI music recommendation {AI Music system}

일반적인 사용자들의 경우 음악을 듣는 특성과 취향이 개인적으로 많이 다를 수 밖에 없으나 일정한 패턴이나 동일한 경향을 나타난다. 비슷한 음악을 좋아하는 사용자들의 다운로드 목록은 많이 비슷한 비율의 같은 곡을 목록에 포함하고 있다는 점을 착안하여 사용자들 끼리의 목록을 비교하면 동일한 곡들의 다운로드가 많이 겹치는 곡을 골라낼 수 있다. 동일한 곡들이 목록에 많이 겹치는 사용자들은 비슷한 취향의 사용자 집단으로 분리 가능하며 이들 목록에 들어있는 곡들 중 가장 많은 다운로드/스트리밍을 한 곡 들부터 순위를 정할 수 있다. 사용자의 다운로드/스트리밍 목록을 이 순위목록과 비교하여 사용자의 목록에 없는 곡 중 높은 순위에 있는 곡부터 사용자에게 추천한다.For general users, the characteristics and tastes of listening to music are very different from each other, but there is a certain pattern or the same tendency. Considering that the download list of users who like similar music includes the same songs in the list with much similar ratio, comparing the lists among users can select the songs in which the downloads of the same songs overlap a lot. Users with the same songs overlapping the list can be divided into groups of users with similar tastes and can be ranked from the most downloaded / streamed songs in the list. The user's download / streaming list is compared to the ranking list and recommended to the user, starting with the highest ranking song that is not on the user's list.

A 사용자가 이제까지 a,b,c 3 곡을 다운로드/스트리밍 받은 상태라면 사이트는 A 사용자가 받은 a,b,c 3곡 중 한 곡이라도 받은 다른 사용자의 목록을 뽑아내어 그룹으로 분리한다. a,b,c 3곡을 모두 포함하는 목록을 가진 사용자 그룹, 3곡 중 2곡을 포함하는 목록을 가진 그룹, 3곡 중 1곡만이 포함된 목록을 가진 그룹으로 분리하여 3곡을 모두 포함하는 목록을 가진 사용자들은 A 사용자와 거의 비슷한 음악성향을 가지고 있다고 판단하며 가중치를 준다. B 사용자의 목록은 a,b,c,d , C 사용자는 a,b,d,eIf user A has been downloading / streaming three songs a, b, and c so far, the site extracts a list of other users who received at least one of the three songs a, b, and c received by user A, and divides them into groups. a, b, c User group with list containing all 3 songs, group with list with 2 of 3 songs, group with list with only 1 of 3 songs, all 3 songs included Users with a list of "A" are given a weight, judging that they have a similar music propensity as user A. The list of users B is a, b, c, d, and the user C is a, b, d, e

D 사용자는 a,e,f,g 라는 목록을 가지고 있을 때 B 사용자는 x3의 가중차를 C 사용자는 x2의 가중치를 D 사용자는 가중치를 두지 않는다.결과를 보면 A 사용자의 목록에 있는 a,b,c를 제외한 나머지 곡 들 중 가중치를 부여하면 B 사용자는 d,d,d. C 사용자는 d,d,e,e D 사용자는 e,f,g 를 자동 추천하게 된다. 순위표를 만들면 d,e,f,g 순서로 만들어지며 순서에 따라 A 사용자에게 추천한다.When user D has a list of a, e, f, g, user B has a weighted difference of x3, user C has a weight of x2, user D has no weight. If the weight is given among the remaining songs except b, c, user B will receive d, d, d. C user d, d, e, e D user e, f, g will automatically recommend. When you create a leaderboard, it is created in the order of d, e, f, g and recommended to user A in order.

본 발명은 인터넷을 통하여 사용자가 음악을 다운로드 받거나 스트리밍으로 감상을 할 때 사용자가 알지 못하여 다운로드/스트리밍 하지 못하는 곡을 사이트가 비슷한 취향의 다른 사용자의 다운로드/스트리밍 목록과 사용자의 목록을 비교하여 자동적으로 음악을 추천하여 사용자로 하여금 취향에 맞는 곡을 선택하여 들어볼 수 있도록 하는 방법이다.According to the present invention, when a user downloads music or listens to streaming music through the Internet, the site does not know and cannot download / stream the song automatically by comparing the user's list with another user's download / streaming list of similar taste. It is a way of recommending music so that the user can select and listen to a song that suits his taste.

이상에서 서술한 바와 같이 본 발명은 인터넷을 통해 음악을 다운로드/스트리밍 받는 사용자가 별다른 행위를 하지 않고도 비슷한 취향의 다른 사용자들과 비교하여 아직 들어보지 못한 비슷한 취향의 다른 음악을 들어볼 수 있다. 사용자가 많아지고 다운 받는 목록의 곡 수가 많아질수록 추천의 정확도가 높아진다.As described above, according to the present invention, a user who downloads / streams music through the Internet can listen to other music of similar taste that has not been heard yet compared to other users of similar taste without any other action. The more users you have and the more songs you have downloaded, the higher the accuracy of your recommendations.

Claims (1)

서버에서 사용자의 취향을 분석해 내고 자동적으로 사용자의 취향에 맞는 음악을 추천하는 방법과 기술How to analyze the user's taste on the server and automatically recommend music that suits the user's taste
KR1020000057502A 2000-09-29 2000-09-29 AI Music system KR20020025579A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020000057502A KR20020025579A (en) 2000-09-29 2000-09-29 AI Music system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020000057502A KR20020025579A (en) 2000-09-29 2000-09-29 AI Music system

Publications (1)

Publication Number Publication Date
KR20020025579A true KR20020025579A (en) 2002-04-04

Family

ID=19691190

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020000057502A KR20020025579A (en) 2000-09-29 2000-09-29 AI Music system

Country Status (1)

Country Link
KR (1) KR20020025579A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20030094943A (en) * 2002-06-10 2003-12-18 푸른정보기술(주) The way of service and system that make chart with ranking from Internet radio station
WO2006075032A1 (en) * 2005-01-05 2006-07-20 Musicstrands, S.A.U. System and method for recommending multimedia elements
KR100775585B1 (en) * 2006-12-13 2007-11-15 삼성전자주식회사 Method for recommending music about character message and system thereof
US7650570B2 (en) 2005-10-04 2010-01-19 Strands, Inc. Methods and apparatus for visualizing a music library
US10936653B2 (en) 2017-06-02 2021-03-02 Apple Inc. Automatically predicting relevant contexts for media items

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20030094943A (en) * 2002-06-10 2003-12-18 푸른정보기술(주) The way of service and system that make chart with ranking from Internet radio station
WO2006075032A1 (en) * 2005-01-05 2006-07-20 Musicstrands, S.A.U. System and method for recommending multimedia elements
US7650570B2 (en) 2005-10-04 2010-01-19 Strands, Inc. Methods and apparatus for visualizing a music library
US8276076B2 (en) 2005-10-04 2012-09-25 Apple Inc. Methods and apparatus for visualizing a media library
KR100775585B1 (en) * 2006-12-13 2007-11-15 삼성전자주식회사 Method for recommending music about character message and system thereof
US8410347B2 (en) 2006-12-13 2013-04-02 Samsung Electronics Co., Ltd. Music recommendation method with respect to message service
US10936653B2 (en) 2017-06-02 2021-03-02 Apple Inc. Automatically predicting relevant contexts for media items

Similar Documents

Publication Publication Date Title
Prey Musica analytica: The datafication of listening
BR0015441A (en) Internet radio and broadcasting method
CN104899302B (en) Recommend the method and apparatus of music to user
US20030014407A1 (en) System and method for making media recommendations
US20080268772A1 (en) Personalized radio engine for mobile devices
US20020002899A1 (en) System for content based music searching
KR101144333B1 (en) Method for offering social music service using location based service
US20100049862A1 (en) Personalized streaming digital content
CN108255840A (en) A kind of recommendation method and system of song
EP0813159A3 (en) Method and system for prioritised downloading of embedded web objects
JP2002540496A (en) Manufacturing systems, methods and articles for user-centered training experiences
EP1835455A1 (en) System and method for recommending multimedia elements
WO2014028891A1 (en) Music generator
KR20150054917A (en) System and method for combining inputs to generate and modify playlists
WO2008066503A3 (en) Service that gathers, processes and distributes the information from multiple sources to multipule users and communities
Laplante Improving music recommender systems: What can we learn from research on music tastes?
CN106294831A (en) A kind of information recommendation method and electronic equipment
WO2015031345A1 (en) Method and system for preparing a playlist for an internet content provider
Urquía The re‐branding of salsa in London’s dance clubs: how an ethnicised form of cultural capital was institutionalised
US8452329B2 (en) Multilayer correlation profiling engines
US20030041066A1 (en) System and methods for training a trainee to classify fundamental properties of media entites
Mckeown Green What is music? Is there a definitive answer?
KR20210091125A (en) Entity-based search system using user engagement
CN104199864B (en) The method and apparatus that keypad tone prompts in a kind of input process
KR20020025579A (en) AI Music system

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination