이 애플리케이션의 일부 콘텐츠는 현재 사용할 수 없습니다.
이 상황이 계속되면 다음 주소로 문의하십시오피드백 및 연락
1. (CN104598643) Article similarity contribution factor, similarity acquiring method, as well as article recommendation method and system thereof

특허청 : 중국
출원번호: 201510076573.7 출원일: 13.02.2015
공개번호: 104598643 공개일: 06.05.2015
공개유형: A
IPC:
G06F 17/30
G SECTION G — 물리학
06
산술논리연산; 계산; 계수
F
전기에 의한 디지털 데이터처리
17
디지털 컴퓨팅 또는 데이터 프로세싱 장비, 방법으로서 특정 기능을 위해 특히 적합한 형태의 것
30
정보검색; 이를 위한 데이터베이스 구조
출원인: CHENDU PINGUO TECHNOLOGY CO., LTD.
발명자: CHEN RUOTIAN
대리인: yuan chunxiao
우선권 정보
발명의 명칭: (EN) Article similarity contribution factor, similarity acquiring method, as well as article recommendation method and system thereof
(ZH) 一种物品相似度贡献系数、相似度获取方法及物品推荐方法及其系统
요약서: front page image
(EN) The invention discloses an article similarity contribution factor, a similarity acquiring method, as well as an article recommendation method and a system thereof, relates to the technical field of data mining, and aims to provide an acquiring method for acquiring the similarity contribution factor, a method for acquiring more effective and accurate particle similarity on the basis of the similarity contribution factor, and a method for article recommendation according to the similarity. The technical points of the invention comprise the following steps: acquiring the behavior record of accessing articles of each user in a target user collection on the Internet; establishing a list containing the accessed articles for each user according to the behavior record; calculating the similarity contribution factor C (u): (as is shown in the Specification) of each user according to the amount of articles accessed by the user, wherein N (u) is the amount of articles accessed by a user u, theta is the activeness threshold, and a is a constant greater than or equal to 0.
(ZH)

本发明公开了一种物品相似度贡献系数、相似度获取方法及物品推荐方法及其系统,涉及数据挖掘技术领域,旨在提供获取相似度贡献系数的获取方法,基于相似度贡献系数获取更加有效、准确的物品相似度的方法以及根据该相似度进行物品推荐的方法。本发明技术要点包括:在网络上获取目标用户集合中每个用户访问物品的行为记录;根据所述行为记录为所述每个用户建立一个包含其访问过的物品的列表;根据每个用户的访问过的物品数量计算该用户的相似度贡献系数C(u):其中N(u)为用户u访问过的物品数量,θ为活跃度阈值,a为大于或等于0的常数。